Compare commits
1 Commits
hush/aggre
...
aleix/exam
| Author | SHA1 | Date | |
|---|---|---|---|
|
6e518cc704 |
34
.github/workflows/build.yaml
vendored
34
.github/workflows/build.yaml
vendored
@@ -21,20 +21,24 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
|
||||
- name: Install project in editable mode
|
||||
run: uv pip install --editable .
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Install project and other Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
pip install --editable .
|
||||
|
||||
37
.github/workflows/coverage.yaml
vendored
37
.github/workflows/coverage.yaml
vendored
@@ -18,28 +18,35 @@ jobs:
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
- name: Cache virtual environment
|
||||
uses: actions/cache@v3
|
||||
with:
|
||||
# We are hashing dev-requirements.txt and test-requirements.txt which
|
||||
# contain all dependencies needed to run the tests.
|
||||
key: venv-${{ runner.os }}-${{ steps.setup_python.outputs.python-version}}-${{ hashFiles('dev-requirements.txt') }}-${{ hashFiles('test-requirements.txt') }}
|
||||
path: .venv
|
||||
- name: Install system packages
|
||||
id: install_system_packages
|
||||
run: |
|
||||
sudo apt-get install -y portaudio19-dev
|
||||
|
||||
- name: Install dependencies
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt -r test-requirements.txt
|
||||
- name: Run tests with coverage
|
||||
run: |
|
||||
uv run coverage run
|
||||
uv run coverage xml
|
||||
|
||||
source .venv/bin/activate
|
||||
coverage run
|
||||
coverage xml
|
||||
- name: Upload coverage to Codecov
|
||||
uses: codecov/codecov-action@v5
|
||||
with:
|
||||
|
||||
31
.github/workflows/format.yaml
vendored
31
.github/workflows/format.yaml
vendored
@@ -22,22 +22,25 @@ jobs:
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install development Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Ruff formatter
|
||||
id: ruff-format
|
||||
run: uv run ruff format --diff
|
||||
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
ruff format --diff
|
||||
- name: Ruff linter (all rules)
|
||||
id: ruff-check
|
||||
run: uv run ruff check
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
ruff check
|
||||
|
||||
24
.github/workflows/publish.yaml
vendored
24
.github/workflows/publish.yaml
vendored
@@ -17,17 +17,23 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.event.inputs.gitref }}
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Upload wheels
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
|
||||
25
.github/workflows/publish_test.yaml
vendored
25
.github/workflows/publish_test.yaml
vendored
@@ -12,16 +12,23 @@ jobs:
|
||||
with:
|
||||
fetch-tags: true
|
||||
fetch-depth: 100
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Upload wheels
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
@@ -31,7 +38,7 @@ jobs:
|
||||
publish-to-test-pypi:
|
||||
name: "Publish to Test PyPI"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
needs: [ build ]
|
||||
environment:
|
||||
name: testpypi
|
||||
url: https://pypi.org/p/pipecat-ai
|
||||
|
||||
61
.github/workflows/python-compatibility.yaml
vendored
61
.github/workflows/python-compatibility.yaml
vendored
@@ -1,61 +0,0 @@
|
||||
name: Python Compatibility Test
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main, develop]
|
||||
paths: ['pyproject.toml']
|
||||
pull_request:
|
||||
branches: [main, develop]
|
||||
paths: ['pyproject.toml']
|
||||
|
||||
jobs:
|
||||
test-compatibility:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']
|
||||
|
||||
name: Python ${{ matrix.python-version }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y \
|
||||
portaudio19-dev \
|
||||
libcairo2-dev \
|
||||
libgirepository1.0-dev \
|
||||
pkg-config
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
with:
|
||||
version: 'latest'
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
run: |
|
||||
uv python install ${{ matrix.python-version }}
|
||||
uv python pin ${{ matrix.python-version }}
|
||||
|
||||
- name: Test uv sync with all extras (Python < 3.13)
|
||||
if: "!startsWith(matrix.python-version, '3.13.')"
|
||||
run: |
|
||||
uv sync --group dev --all-extras --no-extra krisp
|
||||
|
||||
- name: Test uv sync without PyTorch extras (Python 3.13+)
|
||||
if: startsWith(matrix.python-version, '3.13.')
|
||||
run: |
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra krisp \
|
||||
--no-extra ultravox \
|
||||
--no-extra local-smart-turn \
|
||||
--no-extra moondream \
|
||||
--no-extra mlx-whisper
|
||||
|
||||
- name: Verify installation
|
||||
run: |
|
||||
uv run python --version
|
||||
uv run python -c "import pipecat; print('✅ Pipecat imports successfully')"
|
||||
11
.github/workflows/sync-quickstart.yaml
vendored
11
.github/workflows/sync-quickstart.yaml
vendored
@@ -23,12 +23,17 @@ jobs:
|
||||
token: ${{ secrets.QUICKSTART_SYNC_TOKEN }}
|
||||
path: quickstart-repo
|
||||
|
||||
- name: Sync files (excluding uv.lock and README.md)
|
||||
- name: Sync files (excluding READMEs)
|
||||
run: |
|
||||
# Copy all files except uv.lock and README.md
|
||||
# Copy code files only, skip READMEs
|
||||
cp examples/quickstart/bot.py quickstart-repo/
|
||||
cp examples/quickstart/requirements.txt quickstart-repo/
|
||||
cp examples/quickstart/env.example quickstart-repo/
|
||||
|
||||
# Copy any other files that aren't README.md
|
||||
find examples/quickstart -type f \
|
||||
-not -name "README.md" \
|
||||
-not -name "uv.lock" \
|
||||
-not -name "*.md" \
|
||||
-exec cp {} quickstart-repo/ \;
|
||||
|
||||
- name: Commit and push changes
|
||||
|
||||
34
.github/workflows/tests.yaml
vendored
34
.github/workflows/tests.yaml
vendored
@@ -22,23 +22,31 @@ jobs:
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
- name: Cache virtual environment
|
||||
uses: actions/cache@v3
|
||||
with:
|
||||
# We are hashing dev-requirements.txt and test-requirements.txt which
|
||||
# contain all dependencies needed to run the tests.
|
||||
key: venv-${{ runner.os }}-${{ steps.setup_python.outputs.python-version}}-${{ hashFiles('dev-requirements.txt') }}-${{ hashFiles('test-requirements.txt') }}
|
||||
path: .venv
|
||||
- name: Install system packages
|
||||
id: install_system_packages
|
||||
run: |
|
||||
sudo apt-get install -y portaudio19-dev
|
||||
|
||||
- name: Install dependencies
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt -r test-requirements.txt
|
||||
- name: Test with pytest
|
||||
run: |
|
||||
uv run pytest
|
||||
source .venv/bin/activate
|
||||
pytest
|
||||
|
||||
42
.github/workflows/update-lockfile.yaml
vendored
Normal file
42
.github/workflows/update-lockfile.yaml
vendored
Normal file
@@ -0,0 +1,42 @@
|
||||
name: Update lockfile
|
||||
|
||||
on:
|
||||
push:
|
||||
paths:
|
||||
- 'pyproject.toml'
|
||||
branches:
|
||||
- main
|
||||
workflow_dispatch: # Allows manual triggering from GitHub UI
|
||||
|
||||
jobs:
|
||||
update-lockfile:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
# This gives the workflow permission to push back to the repo
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v1
|
||||
|
||||
- name: Update lockfile
|
||||
run: uv lock
|
||||
|
||||
- name: Check for changes
|
||||
id: verify-changed-files
|
||||
run: |
|
||||
if [ -n "$(git status --porcelain)" ]; then
|
||||
echo "changed=true" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "changed=false" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
|
||||
- name: Commit lockfile
|
||||
if: steps.verify-changed-files.outputs.changed == 'true'
|
||||
run: |
|
||||
git config --local user.email "action@github.com"
|
||||
git config --local user.name "GitHub Action"
|
||||
git add uv.lock
|
||||
git commit -m "chore: update uv.lock after dependency changes"
|
||||
git push
|
||||
@@ -9,14 +9,22 @@ build:
|
||||
- python3-dev
|
||||
- libasound2-dev
|
||||
jobs:
|
||||
post_install:
|
||||
- pip install uv
|
||||
- UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
pre_build:
|
||||
- python -m pip install --upgrade pip
|
||||
- pip install wheel setuptools
|
||||
post_build:
|
||||
- echo "Build completed"
|
||||
|
||||
sphinx:
|
||||
configuration: docs/api/conf.py
|
||||
fail_on_warning: false
|
||||
|
||||
python:
|
||||
install:
|
||||
- requirements: docs/api/requirements.txt
|
||||
- method: pip
|
||||
path: .
|
||||
|
||||
search:
|
||||
ranking:
|
||||
api/*: 5
|
||||
|
||||
930
CHANGELOG.md
930
CHANGELOG.md
@@ -5,941 +5,17 @@ All notable changes to **Pipecat** will be documented in this file.
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
||||
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
|
||||
## [0.0.86] - 2025-09-24
|
||||
|
||||
### Added
|
||||
|
||||
- Added `HeyGenTransport`. This is an integration for HeyGen Interactive
|
||||
Avatar. A video service that handles audio streaming and requests HeyGen to
|
||||
generate avatar video responses. (see https://www.heygen.com/). When used, the
|
||||
Pipecat bot joins the same virtual room as the HeyGen Avatar and the user.
|
||||
|
||||
- Added support to `TwilioFrameSerializer` for `region` and `edge` settings.
|
||||
|
||||
- Added support for using universal `LLMContext` with:
|
||||
|
||||
- `LLMLogObserver`
|
||||
- `GatedLLMContextAggregator` (formerly `GatedOpenAILLMContextAggregator`)
|
||||
- `LangchainProcessor`
|
||||
- `Mem0MemoryService`
|
||||
|
||||
- Added `StrandsAgentProcessor` which allows you to use the Strands Agents
|
||||
framework to build your voice agents.
|
||||
See https://strandsagents.com
|
||||
|
||||
- Added `ElevenLabsSTTService` for speech-to-text transcription.
|
||||
|
||||
- Added a peer connection monitor to the `SmallWebRTCConnection` that
|
||||
automatically disconnects if the connection fails to establish within
|
||||
the timeout (1 minute by default).
|
||||
|
||||
- Added memory cleanup improvements to reduce memory peaks.
|
||||
|
||||
- Added `on_before_process_frame`, `on_after_process_frame`,
|
||||
`on_before_push_frame` and `on_after_push_frame`. These are synchronous events
|
||||
that get called before and after a frame is processed or pushed. Note that
|
||||
these events are synchrnous so they should ideally perform lightweight tasks
|
||||
in order to not block the pipeline. See
|
||||
`examples/foundational/45-before-and-after-events.py`.
|
||||
|
||||
- Added `on_before_leave` synchronous event to `DailyTransport`.
|
||||
|
||||
- Added `on_before_disconnect` synchronous event to `LiveKitTransport`.
|
||||
|
||||
- It is now possible to register synchronous event handlers. By default, all
|
||||
event handlers are executed in a separate task. However, in some cases we want
|
||||
to guarantee order of execution, for example, executing something before
|
||||
disconnecting a transport.
|
||||
|
||||
```python
|
||||
self._register_event_handler("on_event_name", sync=True)
|
||||
```
|
||||
|
||||
- Added support for global location in `GoogleVertexLLMService`. The service now
|
||||
supports both regional locations (e.g., "us-east4") and the "global" location
|
||||
for Vertex AI endpoints. When using "global" location, the service will use
|
||||
`aiplatform.googleapis.com` as the API host instead of the regional format.
|
||||
|
||||
- Added `on_pipeline_finished` event to `PipelineTask`. This event will get
|
||||
fired when the pipeline is done running. This can be the result of a
|
||||
`StopFrame`, `CancelFrame` or `EndFrame`.
|
||||
|
||||
```python
|
||||
@task.event_handler("on_pipeline_finished")
|
||||
async def on_pipeline_finished(task: PipelineTask, frame: Frame):
|
||||
...
|
||||
```
|
||||
|
||||
- Added support for new RTVI `send-text` event, along with the ability to toggle
|
||||
the audio response off (skip tts) while handling the new context.
|
||||
## [Unreleased]
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated `aiortc` to 1.13.0.
|
||||
|
||||
- Updated `sentry` to 2.38.0.
|
||||
|
||||
- `BaseOutputTransport` methods `write_audio_frame` and `write_video_frame` now
|
||||
return a boolean to indicate if the transport implementation was able to write
|
||||
the given frame or not.
|
||||
|
||||
- Updated Silero VAD model to v6.
|
||||
|
||||
- Updated `livekit` to 1.0.13.
|
||||
|
||||
- `torch` and `torchaudio` are no longer required for running Smart Turn
|
||||
locally. This avoids gigabytes of dependencies being installed.
|
||||
|
||||
- Updated `websockets` dependency to support version 15.0. Removed deprecated
|
||||
usage of `ConnectionClosed.code` and `ConnectionClosed.reason` attributes in
|
||||
`AWSTranscribeSTTService` for compatibility.
|
||||
|
||||
- Refactored `pyproject.toml` to reduce websockets dependency repetition using
|
||||
self-referencing extras. All websockets-dependent services now reference a
|
||||
shared `websockets-base` extra.
|
||||
|
||||
### Deprecated
|
||||
|
||||
- `GladiaSTTService`'s `confidence` arg is deprecated. `confidence` is no
|
||||
longer needed to determine which transcription or translation frames to
|
||||
emit.
|
||||
|
||||
- `PipelineTask` events `on_pipeline_stopped`, `on_pipeline_ended` and
|
||||
`on_pipeline_cancelled` are now deprecated. Use `on_pipeline_finished`
|
||||
instead.
|
||||
|
||||
- Support for the RTVI `append-to-context` event, in lieu of the new `send-text`
|
||||
event and making way for future events like `send-image`.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue where the pipeline could freeze if a task cancellation never
|
||||
completed because a third-party library swallowed asyncio.CancelledError. We
|
||||
now apply a timeout to task cancellations to prevent these freezes. If the
|
||||
timeout is reached, the system logs warnings and leaves dangling tasks behind,
|
||||
which can help diagnose where cancellation is being blocked.
|
||||
|
||||
- Fixed an `AudioBufferProcessor` issues that was causing user audio to be
|
||||
missing in stereo recordings causing bot and user overlaps.
|
||||
|
||||
- Fixed a `BaseOutputTransport` issue that could produce large saved
|
||||
`AudioBufferProcessor` files when using an audio mixer.
|
||||
|
||||
- Fixed a `PipelineRunner` issue on Windows where setting up SIGINT and SIGTERM
|
||||
was raising an exception.
|
||||
|
||||
- Fixed an issue where multiple handlers for an event would not run in parallel.
|
||||
|
||||
- Fixed `DailyTransport.sip_call_transfer()` to automatically use the session
|
||||
ID from the `on_dialin_connected` event, when not explicitly provided. Now
|
||||
supports cold transfers (from incoming dial-in calls) by automatically
|
||||
tracking session IDs from connection events.
|
||||
|
||||
- Fixed a memory leak in `SmallWebRTCTransport`. In `aiortc`, when you receive
|
||||
a `MediaStreamTrack` (audio or video), frames are produced asynchronously. If
|
||||
the code never consumes these frames, they are queued in memory, causing a
|
||||
memory leak.
|
||||
|
||||
- Fixed an issue in `AsyncAITTSService`, where `TTSTextFrames` were not being
|
||||
pushed.
|
||||
|
||||
- Fixed an issue that would cause `push_interruption_task_frame_and_wait()` to
|
||||
not wait if a previous interruption had already happened.
|
||||
|
||||
- Fixed a couple of bugs in `ServiceSwitcher`:
|
||||
|
||||
- Using multiple `ServiceSwitcher`s in a pipeline would result in an error.
|
||||
- `ServiceSwitcherFrame`s (such as `ManuallySwitchServiceFrame`s) were having
|
||||
an effect too early, essentially "jumping the queue" in terms of pipeline
|
||||
frame ordering.
|
||||
|
||||
- Fixed a self-cancellation deadlock in `UserIdleProcessor` when returning
|
||||
`False` from an idle callback. The task now terminates naturally instead of
|
||||
attempting to cancel itself.
|
||||
|
||||
- Fixed an issue in `AudioBufferProcessor` where a recording is not created
|
||||
when a bot speaks and user input is blocked.
|
||||
|
||||
- Fixed a `FastAPIWebsocketTransport` and `SmallWebRTCTransport` issue where
|
||||
`on_client_disconnected` would be triggered when the bot ends the
|
||||
conversation. That is, `on_client_disconnected` should only be triggered when
|
||||
the remote client actually disconnects.
|
||||
|
||||
- Fixed an issue in `HeyGenVideoService` where the `BotStartedSpeakingFrame`
|
||||
was blocked from moving through the Pipeline.
|
||||
|
||||
## [0.0.85] - 2025-09-12
|
||||
|
||||
### Added
|
||||
|
||||
- `AzureSTTService` now pushes interim transcriptions.
|
||||
|
||||
- Added `voice_cloning_key` to `GoogleTTSService` to support custom cloned
|
||||
voices.
|
||||
|
||||
- Added `speaking_rate` to `GoogleTTSService.InputParams` to control the
|
||||
speaking rate.
|
||||
|
||||
- Added a `speed` arg to `OpenAITTSService` to control the speed of the voice
|
||||
response.
|
||||
|
||||
- Added `FrameProcessor.push_interruption_task_frame_and_wait()`. Use this
|
||||
method to programatically interrupt the bot from any part of the
|
||||
pipeline. This guarantees that all the processors in the pipeline are
|
||||
interrupted in order (from upstream to downstream). Internally, this works by
|
||||
first pushing an `InterruptionTaskFrame` upstream until it reaches the
|
||||
pipeline task. The pipeline task then generates an `InterruptionFrame`, which
|
||||
flows downstream through all processors. Once the `InterruptionFrame` has
|
||||
reaches the processor waiting for the interruption, the function returns and
|
||||
execution continues after the call. Think of it as sending an upstream request
|
||||
for interruption and waiting until the acknowledgment flows back downstream.
|
||||
|
||||
- Added new base `TaskFrame` (which is a system frame). This is the base class
|
||||
for all task frames (`EndTaskFrame`, `CancelTaskFrame`, etc.) that are meant
|
||||
to be pushed upstream to reach the pipeline task.
|
||||
|
||||
- Expanded support for universal `LLMContext` to the AWS Bedrock LLM service.
|
||||
Using the universal `LLMContext` and associated `LLMContextAggregatorPair` is
|
||||
a pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
|
||||
|
||||
- Added new fields to the development runner's `parse_telephony_websocket`
|
||||
method in support of providing dynamic data to a bot.
|
||||
|
||||
- Twilio: Added a new `body` parameter, which parses the websocket message
|
||||
for `customParameters`. Provide data via the `Parameter` nouns in your
|
||||
TwiML to use this feature.
|
||||
- Telnyx & Exotel: Both providers make the `to` and `from` phone numbers
|
||||
available in the websocket messages. You can now access these numbers as
|
||||
`call_data["to"]` and `call_data["from"]`.
|
||||
|
||||
Note: Each telephony provider offers different features. Refer to the
|
||||
corresponding example in `pipecat-examples` to see how to pass custom data
|
||||
to your bot.
|
||||
|
||||
- Added `body` to the `WebsocketRunnerArguments` as an optional parameter.
|
||||
Custom `body` information can be passed from the server into the bot file via
|
||||
the `bot()` method using this new parameter.
|
||||
|
||||
- Added video streaming support to `LiveKitTransport`.
|
||||
|
||||
- Added `OpenAIRealtimeLLMService` and `AzureRealtimeLLMService` which provide
|
||||
access to OpenAI Realtime.
|
||||
|
||||
### Changed
|
||||
|
||||
- `pipeline.tests.utils.run_test()` now allows passing `PipelineParams` instead
|
||||
of individual parameters.
|
||||
|
||||
### Removed
|
||||
|
||||
- Remove `VisionImageRawFrame` in favor of context frames (`LLMContextFrame` or
|
||||
`OpenAILLMContextFrame`).
|
||||
|
||||
### Deprecated
|
||||
|
||||
- `BotInterruptionFrame` is now deprecated, use `InterruptionTaskFrame` instead.
|
||||
|
||||
- `StartInterruptionFrame` is now deprected, use `InterruptionFrame` instead.
|
||||
|
||||
- Deprecate `VisionImageFrameAggregator` because `VisionImageRawFrame` has been
|
||||
removed. See the `12*` examples for the new recommended replacement pattern.
|
||||
|
||||
- `NoisereduceFilter` is now deprecated and will be removed in a future
|
||||
version. Use other audio filters like `KrispFilter` or `AICFilter`.
|
||||
|
||||
- Deprecated `OpenAIRealtimeBetaLLMService` and `AzureRealtimeBetaLLMService`.
|
||||
Use `OpenAIRealtimeLLMService` and `AzureRealtimeLLMService`, respectively.
|
||||
Each service will be removed in an upcoming version, 1.0.0.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed a `BaseOutputTransport` issue that caused incorrect detection of when
|
||||
the bot stopped talking while using an audio mixer.
|
||||
|
||||
- Fixed a `LiveKitTransport` issue where RTVI messages were not properly
|
||||
encoded.
|
||||
|
||||
- Add additional fixups to Mistral context messages to ensure they meet
|
||||
Mistral-specific requirements, avoiding Mistral "invalid request" errors.
|
||||
|
||||
- Fixed `DailyTransport` transcription handling to gracefully handle missing
|
||||
`rawResponse` field in transcription messages, preventing KeyError crashes.
|
||||
|
||||
## [0.0.84] - 2025-09-05
|
||||
|
||||
### Added
|
||||
|
||||
- Add the ability to send DTMF to `LiveKitTransport`.
|
||||
|
||||
- Expanded support for universal `LLMContext` to the Anthropic LLM service.
|
||||
Using the universal `LLMContext` and associated `LLMContextAggregatorPair` is
|
||||
a pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated `daily-python` to 0.19.9.
|
||||
|
||||
- Restored `DailyTransport`'s native DTMF support using Daily's `send_dtmf()`
|
||||
method instead of generated audio tones.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed a `AWSBedrockLLMService` crash caused by an extra `await`.
|
||||
|
||||
- Fixed a `OpenAIImageGenService` issue where it was not creating
|
||||
`URLImageRawFrame` correctly.
|
||||
|
||||
## [0.0.83] - 2025-09-03
|
||||
|
||||
### Added
|
||||
|
||||
- Added multilingual support for AsyncAI in `AsyncAITTSService` and `AsyncAIHttpTTSService`.
|
||||
|
||||
- New `languages`: `es`, `fr`, `de`, `it`.
|
||||
|
||||
- Added new frames `InputTransportMessageUrgentFrame` and
|
||||
`DailyInputTransportMessageUrgentFrame` for transport messages received from
|
||||
external sources.
|
||||
|
||||
- Added `UserSpeakingFrame`. This will be sent upstream and downstream while VAD
|
||||
detects the user is speaking.
|
||||
|
||||
- Expanded support for universal `LLMContext` to more LLM services. Using the
|
||||
universal `LLMContext` and associated `LLMContextAggregatorPair` is a
|
||||
pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
|
||||
Here are the newly-supported services:
|
||||
|
||||
- Azure
|
||||
- Cerebras
|
||||
- Deepseek
|
||||
- Fireworks AI
|
||||
- Google Vertex AI
|
||||
- Grok
|
||||
- Groq
|
||||
- Mistral
|
||||
- NVIDIA NIM
|
||||
- Ollama
|
||||
- OpenPipe
|
||||
- OpenRouter
|
||||
- Perplexity
|
||||
- Qwen
|
||||
- SambaNova
|
||||
- Together.ai
|
||||
|
||||
- Added support for WhatsApp User-initiated Calls.
|
||||
|
||||
- Added new audio filter `AICFilter`, speech enhancement for improving VAD/STT
|
||||
performance, no ONNX dependency.
|
||||
See https://ai-coustics.com/sdk/
|
||||
|
||||
- Added a timeout around cancel input tasks to prevent indefinite hangs when
|
||||
cancellation is swallowed by third-party code.
|
||||
|
||||
- Added `pipecat.extensions.ivr` for automated IVR system navigation with
|
||||
configurable goals and conversation handling. Supports DTMF input, verbal
|
||||
responses, and intelligent menu traversal.
|
||||
|
||||
Basic usage:
|
||||
|
||||
```python
|
||||
from pipecat.extensions.ivr.ivr_navigator import IVRNavigator
|
||||
|
||||
# Create IVR navigator with your goal
|
||||
ivr_navigator = IVRNavigator(
|
||||
llm=llm_service,
|
||||
ivr_prompt="Navigate to billing department to dispute a charge"
|
||||
)
|
||||
|
||||
# Handle different outcomes
|
||||
@ivr_navigator.event_handler("on_conversation_detected")
|
||||
async def on_conversation(processor, conversation_history):
|
||||
# Switch to normal conversation mode
|
||||
pass
|
||||
|
||||
@ivr_navigator.event_handler("on_ivr_status_changed")
|
||||
async def on_ivr_status(processor, status):
|
||||
if status == IVRStatus.COMPLETED:
|
||||
# End pipeline, transfer call, or start bot conversation
|
||||
elif status == IVRStatus.STUCK:
|
||||
# Handle navigation failure
|
||||
```
|
||||
|
||||
- `BaseOutputTransport` now implements `write_dtmf()` by loading DTMF audio and
|
||||
sending it through the transport. This makes sending DTMF generic across all
|
||||
output transports.
|
||||
|
||||
- Added new config parameters to `GladiaSTTService`.
|
||||
- PreProcessingConfig > `audio_enhancer` to enhance audio quality.
|
||||
- CustomVocabularyItem > `pronunciations` and `language` to specify special
|
||||
pronunciations and in which language it will be pronounced.
|
||||
|
||||
### Changed
|
||||
|
||||
- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` are also pushed
|
||||
upstream.
|
||||
|
||||
- `ParallelPipeline` now waits for `CancelFrame` to finish in all branches
|
||||
before pushing it downstream.
|
||||
|
||||
- Added `sip_codecs` to the `DailyRoomSipParams`.
|
||||
|
||||
- Updated the `configure()` function in `pipecat.runner.daily` to include new
|
||||
args to create SIP-enabled rooms. Additionally, added new args to control the
|
||||
room and token expiration durations.
|
||||
|
||||
- `pipecat.frames.frames.KeypadEntry` is deprecated and has been moved to
|
||||
`pipecat.audio.dtmf.types.KeypadEntry`.
|
||||
|
||||
- Updated `RimeTTSService`'s flush_audio message to conform with Rime's official
|
||||
API.
|
||||
|
||||
- Updated the default model for `CerebrasLLMService` to GPT-OSS-120B.
|
||||
|
||||
### Removed
|
||||
|
||||
- Remove `StopInterruptionFrame`. This was a legacy frame that was not being
|
||||
used really anywhere and it didn't provide any useful meaning. It was only
|
||||
pushed after `UserStoppedSpeakingFrame`, so developers can just use
|
||||
`UserStoppedSpeakingFrame`.
|
||||
|
||||
- `DailyTransport.write_dtmf()` has been removed in favor of the generic
|
||||
`BaseOutputTransport.write_dtmf()`.
|
||||
|
||||
- Remove deprecated `DailyTransport.send_dtmf()`.
|
||||
|
||||
### Deprecated
|
||||
|
||||
- Transports have been re-organized.
|
||||
|
||||
```
|
||||
pipecat.transports.network.small_webrtc -> pipecat.transports.smallwebrtc.transport
|
||||
pipecat.transports.network.webrtc_connection -> pipecat.transports.smallwebrtc.connection
|
||||
pipecat.transports.network.websocket_client -> pipecat.transports.websocket.client
|
||||
pipecat.transports.network.websocket_server -> pipecat.transports.websocket.server
|
||||
pipecat.transports.network.fastapi_websocket -> pipecat.transports.websocket.fastapi
|
||||
pipecat.transports.services.daily -> pipecat.transports.daily.transport
|
||||
pipecat.transports.services.helpers.daily_rest -> pipecat.transports.daily.utils
|
||||
pipecat.transports.services.livekit -> pipecat.transports.livekit.transport
|
||||
pipecat.transports.services.tavus -> pipecat.transports.tavus.transport
|
||||
```
|
||||
|
||||
- `pipecat.frames.frames.KeypadEntry` is deprecated use
|
||||
`pipecat.audio.dtmf.types.KeypadEntry` instead.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue where messages received from the transport were always being resent.
|
||||
|
||||
- Fixed `SmallWebRTCTransport` to not use `mid` to decide if the transceiver should
|
||||
be `sendrecv` or not.
|
||||
|
||||
- Fixed an issue where Deepgram swallowed `asyncio.CancelledError` during
|
||||
disconnect, preventing tasks from being cancelled.
|
||||
|
||||
- Fixed an issue where `PipelineTask` was not cleaning up the observers.
|
||||
|
||||
### Performance
|
||||
|
||||
- Reduced latency and improved memory performance in `Mem0MemoryService`.
|
||||
|
||||
## [0.0.82] - 2025-08-28
|
||||
|
||||
### Added
|
||||
|
||||
- Added a new `LLMRunFrame` to trigger an LLM response:
|
||||
|
||||
```python
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
```
|
||||
|
||||
This replaces `OpenAILLMContextFrame`, which you’d previously typically use
|
||||
like this:
|
||||
|
||||
```python
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
```
|
||||
|
||||
Use this way of kicking off your conversation when you’ve already initialized
|
||||
your context and are simply instructing the bot when to go:
|
||||
|
||||
```python
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
# ...
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
```
|
||||
|
||||
Note that if you want to add new messages when kicking off the conversation,
|
||||
you could use `LLMMessagesAppendFrame` with `run_llm=True` instead:
|
||||
|
||||
```python
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([LLMMessagesAppendFrame(new_messages, run_llm=True)])
|
||||
```
|
||||
|
||||
In the rare case you don’t have a context aggregator in your pipeline, then
|
||||
you may continue using a context frame.
|
||||
|
||||
- Added support for switching between audio+text to text-only modes within the
|
||||
same pipeline. This is done by pushing
|
||||
`LLMConfigureOutputFrame(skip_tts=True)` to enter text-only mode, and
|
||||
disabling it to return to audio+text. The LLM will still generate tokens and
|
||||
add them to the context, but they will not be sent to TTS.
|
||||
|
||||
- Added `skip_tts` field to `TextFrame`. This lets a text frame bypass TTS while
|
||||
still being included in the LLM context. Useful for cases like structured text
|
||||
that isn’t meant to be spoken but should still contribute to context.
|
||||
|
||||
- Added a `cancel_timeout_secs` argument to `PipelineTask` which defines how
|
||||
long the pipeline has to complete cancellation. When `PipelineTask.cancel()`
|
||||
is called, a `CancelFrame` is pushed through the pipeline and must reach the
|
||||
end. If it does not reach the end within the specified time, a warning is
|
||||
shown and the wait is aborted.
|
||||
|
||||
- Added a new "universal" (LLM-agnostic) `LLMContext` and accompanying
|
||||
`LLMContextAggregatorPair`, which will eventually replace `OpenAILLMContext`
|
||||
(and the other under-the-hood contexts) and the other context aggregators.
|
||||
The new universal `LLMContext` machinery allows a single context to be shared
|
||||
between different LLMs, enabling runtime LLM switching and scenarios like
|
||||
failover.
|
||||
|
||||
From the developer's point of view, switching to using the new universal
|
||||
context machinery will usually be a matter of going from this:
|
||||
|
||||
```python
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
```
|
||||
|
||||
To this:
|
||||
|
||||
```python
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
```
|
||||
|
||||
To start, the universal `LLMContext` is supported with the following LLM
|
||||
services:
|
||||
|
||||
- `OpenAILLMService`
|
||||
- `GoogleLLMService`
|
||||
|
||||
- Added a new `LLMSwitcher` class to enable runtime LLM switching, built atop a
|
||||
new generic `ServiceSwitcher`.
|
||||
|
||||
Switchers take a switching strategy. The first available strategy is
|
||||
`ServiceSwitcherStrategyManual`.
|
||||
|
||||
To switch LLMs at runtime, the LLMs must be sharing one instance of the new
|
||||
universal `LLMContext` (see above bullet).
|
||||
|
||||
```python
|
||||
# Instantiate your LLM services
|
||||
llm_openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm_google = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
|
||||
|
||||
# Instantiate a switcher
|
||||
# (ServiceSwitcherStrategyManual defaults to OpenAI, as it's first in the list)
|
||||
llm_switcher = LLMSwitcher(
|
||||
llms=[llm_openai, llm_google], strategy_type=ServiceSwitcherStrategyManual
|
||||
)
|
||||
|
||||
# Create your pipeline
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
context_aggregator.user(),
|
||||
llm_switcher,
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
|
||||
|
||||
# ...
|
||||
# Whenever is appropriate, switch LLMs!
|
||||
await task.queue_frames([ManuallySwitchServiceFrame(service=llm_google)])
|
||||
```
|
||||
|
||||
- Added an `LLMService.run_inference()` method to LLM services to enable
|
||||
direct, out-of-band (i.e. out-of-pipeline) inference.
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated `daily-python` to 0.19.8.
|
||||
|
||||
- `PipelineTask` now waits for `StartFrame` to reach the end of the pipeline
|
||||
before pushing any other frames.
|
||||
|
||||
- Updated `CartesiaTTSService` and `CartesiaHttpTTSService` to align with
|
||||
Cartesia's changes for the `speed` parameter. It now takes only an enum of
|
||||
`slow`, `normal`, or `fast`.
|
||||
|
||||
- Added support to `AWSBedrockLLMService` for setting authentication
|
||||
credentials through environment variables.
|
||||
|
||||
- Updated `SarvamTTSService` to use WebSocket streaming for real-time audio
|
||||
generation with multiple Indian languages, with HTTP support still available
|
||||
via `SarvamHttpTTSService`.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an RTVI issue that was causing frames to be pushed before pipeline was
|
||||
properly initialized.
|
||||
|
||||
- Fixed some `get_messages_for_logging()` that were returning a JSON string
|
||||
instead of a list.
|
||||
|
||||
- Fixed a `DailyTransport` issue that prevented DTMF tones from being sent.
|
||||
|
||||
- Fixed a missing import in `SentryMetrics`.
|
||||
|
||||
- Fixed `AWSPollyTTSService` to support AWS credential provider chain (IAM
|
||||
roles, IRSA, instance profiles) instead of requiring explicit environment
|
||||
variables.
|
||||
|
||||
- Fixed a `CartesiaTTSService` issue that was causing the application to hang
|
||||
after Cartesia's 5 minutes timed out.
|
||||
|
||||
- Fixed an issue preventing `SpeechmaticsSTTService` from transcribing audio.
|
||||
|
||||
## [0.0.81] - 2025-08-25
|
||||
|
||||
### Added
|
||||
|
||||
- Added `pipecat.extensions.voicemail`, a module for detecting voicemail vs.
|
||||
live conversation, primarily intended for use in outbound calling scenarios.
|
||||
The voicemail module is optimized for text LLMs only.
|
||||
|
||||
- Added new frames to the `idle_timeout_frames` arg: `TranscriptionFrame`,
|
||||
`InterimTranscriptionFrame`, `UserStartedSpeakingFrame`, and
|
||||
`UserStoppedSpeakingFrame`. These additions serve as indicators of user
|
||||
activity in the pipeline idle detection logic.
|
||||
|
||||
- Allow passing custom pipeline sink and source processors to a
|
||||
`Pipeline`. Pipeline source and sink processors are used to know and control
|
||||
what's coming in and out of a `Pipeline` processor.
|
||||
|
||||
- Added `FrameProcessor.pause_processing_system_frames()` and
|
||||
`FrameProcessor.resume_processing_system_frames()`. These allow to pause and
|
||||
resume the processing of system frame.
|
||||
|
||||
- Added new `on_process_frame()` observer method which makes it possible to know
|
||||
when a frame is being processed.
|
||||
|
||||
- Added new `FrameProcessor.entry_processor()` method. This allows you to access
|
||||
the first non-compound processor in a pipeline.
|
||||
|
||||
- Added `FrameProcessor` properties `processors`, `next` and `previous`.
|
||||
|
||||
- `ElevenLabsTTSService` now supports additional runtime changes to the `model`,
|
||||
`language`, and `voice_settings` parameters.
|
||||
|
||||
- Added `apply_text_normalization` support to `ElevenLabsTTSService` and
|
||||
`ElevenLabsHttpTTSService`.
|
||||
|
||||
- Added `MistralLLMService`, using Mistral's chat completion API.
|
||||
|
||||
- Added the ability to retry executing a chat completion after a timeout period
|
||||
for `OpenAILLMService` and its subclasses, `AnthropicLLMService`, and
|
||||
`AWSBedrockLLMService`. The LLM services accept new args:
|
||||
`retry_timeout_secs` and `retry_on_timeout`. This feature is disabled by
|
||||
default.
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated `daily-python` to 0.19.7.
|
||||
|
||||
### Deprecated
|
||||
|
||||
- `FrameProcessor.wait_for_task()` is deprecated. Use `await task` or
|
||||
`await asyncio.wait_for(task, timeout)` instead.
|
||||
|
||||
### Removed
|
||||
|
||||
- Watchdog timers have been removed. They were introduced in 0.0.72 to help
|
||||
diagnose pipeline freezes. Unfortunately, they proved ineffective since they
|
||||
required developers to use Pipecat-specific queues, iterators, and events to
|
||||
correctly reset the timer, which limited their usefulness and added friction.
|
||||
|
||||
- Removed unused `FrameProcessor.set_parent()` and
|
||||
`FrameProcessor.get_parent()`.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue that would cause `PipelineRunner` and `PipelineTask` to not
|
||||
handle external asyncio task cancellation properly.
|
||||
|
||||
- Added `SpeechmaticsSTTService` exception handling on connection and sending.
|
||||
|
||||
- Replaced `asyncio.wait_for()` for `wait_for2.wait_for()` for Python <
|
||||
3.12. because of issues regarding task cancellation (i.e. cancellation is
|
||||
never propagated).
|
||||
See https://bugs.python.org/issue42130
|
||||
|
||||
- Fixed an `AudioBufferProcessor` issues that would cause audio overlap when
|
||||
setting a max buffer size.
|
||||
|
||||
- Fixed an issue where `AsyncAITTSService` had very high latency in responding
|
||||
by adding `force=true` when sending the flush command.
|
||||
|
||||
### Performance
|
||||
|
||||
- Improve `PipelineTask` performance by using direct mode processors and by
|
||||
removing unnecessary tasks.
|
||||
|
||||
- Improve `ParallelPipeline` performance by using direct mode, by not
|
||||
creating a task for each frame and every sub-pipeline and also by removing
|
||||
other unnecessary tasks.
|
||||
|
||||
- `Pipeline` performance improvements by using direct mode.
|
||||
|
||||
### Other
|
||||
|
||||
- Added `14w-function-calling-mistal.py` using `MistralLLMService`.
|
||||
|
||||
- Added `13j-azure-transcription.py` using `AzureSTTService`.
|
||||
|
||||
## [0.0.80] - 2025-08-13
|
||||
|
||||
### Added
|
||||
|
||||
- Added `GeminiTTSService` which uses Google Gemini to generate TTS output. The
|
||||
Gemini model can be prompted to insert styled speech to control the TTS
|
||||
output.
|
||||
|
||||
- Added Exotel support to Pipecat's development runner. You can now connect
|
||||
using the runner with `uv run bot.py -t exotel` and an ngrok connection to
|
||||
HTTP port 7860.
|
||||
|
||||
- Added `enable_direct_mode` argument to `FrameProcessor`. The direct mode is
|
||||
for processors which require very little I/O or compute resources, that is
|
||||
processors that can perform their task almost immediately. These type of
|
||||
processors don't need any of the internal tasks and queues usually created by
|
||||
frame processors which means overall application performance might be slightly
|
||||
increased. Use with care.
|
||||
|
||||
- Added TTFB metrics for `HeyGenVideoService` and `TavusVideoService`.
|
||||
|
||||
- Added `endpoint_id` parameter to `AzureSTTService`. ([Custom EndpointId](https://docs.azure.cn/en-us/ai-services/speech-service/how-to-recognize-speech?pivots=programming-language-python#use-a-custom-endpoint))
|
||||
|
||||
### Changed
|
||||
|
||||
- `WatchdogPriorityQueue` now requires the items to be inserted to always be
|
||||
tuples and the size of the tuple needs to be specified in the constructor when
|
||||
creating the queue with the `tuple_size` argument.
|
||||
|
||||
- Updated Moondream to revision `2025-01-09`.
|
||||
|
||||
- Updated `PlayHTHttpTTSService` to no longer use the `pyht` client to remove
|
||||
compatibility issues with other packages. Now you can use the PlayHT HTTP
|
||||
service with other services, like GoogleLLMService.
|
||||
|
||||
- Updated `pyproject.toml` to once again pin `numba` to `>=0.61.2` in order to
|
||||
resolve package versioning issues.
|
||||
|
||||
- Updated the `STTMuteFilter` to include `VADUserStartedSpeakingFrame` and
|
||||
`VADUserStoppedSpeakingFrame` in the list of frames to filter when the
|
||||
filtering is on.
|
||||
|
||||
### Performance
|
||||
|
||||
- Improving the latency of the `HeyGenVideoService`.
|
||||
|
||||
- Improved some frame processors performance by using the new frame processor
|
||||
direct mode. In direct mode a frame processor will process frames right away
|
||||
avoiding the need for internal queues and tasks. This is useful for some
|
||||
simple processors. For example, in processors that wrap other processors
|
||||
(e.g. `Pipeline`, `ParallelPipeline`), we add one processor before and one
|
||||
after the wrapped processors (internally, you will see them as sources and
|
||||
sinks). These sources and sinks don't do any special processing and they
|
||||
basically forward frames. So, for these simple processors we now enable the
|
||||
new direct mode which avoids creating any internal tasks (and queues) and
|
||||
therefore improves performance.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue with the `BaseWhisperSTTService` where the language was
|
||||
specified as an enum and not a string.
|
||||
|
||||
- Fixed an issue where `SmallWebRTCTransport` ended before TTS finished.
|
||||
|
||||
- Fixed an issue in `OpenAIRealtimeBetaLLMService` where specifying a `text`
|
||||
`modalities` didn't result in text being outputted from the model.
|
||||
|
||||
- Added SSML reserved character escaping to `AzureBaseTTSService` to properly
|
||||
handle special characters in text sent to Azure TTS. This fixes an issue
|
||||
where characters like `&`, `<`, `>`, `"`, and `'` in LLM-generated text would
|
||||
cause TTS failures.
|
||||
|
||||
- Fixed a `WatchdogPriorityQueue` issue that could cause an exception when
|
||||
compating watchdog cancel sentinel items with other items in the queue.
|
||||
|
||||
- Fixed an issue that would cause system frames to not be processed with higher
|
||||
priority than other frames. This could cause slower interruption times.
|
||||
|
||||
- Fixed an issue where retrying a websocket connection error would result in an
|
||||
error.
|
||||
|
||||
### Other
|
||||
|
||||
- Add foundation example `19b-openai-realtime-beta-text.py`, showing how to use
|
||||
`OpenAIRealtimeBetaLLMService` to output text to a TTS service.
|
||||
|
||||
- Add vision support to release evals so we can run the foundational examples 12
|
||||
series.
|
||||
|
||||
- Added foundational example `15a-switch-languages.py` to release evals. It is
|
||||
able to detect if we switched the language properly.
|
||||
|
||||
- Updated foundational examples to show how to enclose complex logic
|
||||
(e.g. `ParallelPipeline`) into a single processor so the main pipeline becomes
|
||||
simpler.
|
||||
|
||||
- Added `07n-interruptible-gemini.py`, demonstrating how to use
|
||||
`GeminiTTSService`.
|
||||
|
||||
## [0.0.79] - 2025-08-07
|
||||
|
||||
### Changed
|
||||
|
||||
- Changed `pipecat-ai`'s `openai` dependency to `>=1.74.0,<=1.99.1` due to a
|
||||
breaking change in `openai` 1.99.2 ([commit](https://github.com/openai/openai-python/commit/657f551dbe583ffb259d987dafae12c6211fba06))
|
||||
|
||||
### Deprecated
|
||||
|
||||
- `TTSService.say()` is deprecated, push a `TTSSpeakFrame` instead. Calling
|
||||
functions directly is a discouraged pattern in Pipecat because, for example,
|
||||
it might cause issues with frame ordering.
|
||||
|
||||
- `LLMMessagesFrame` is deprecated, in favor of either:
|
||||
|
||||
- `LLMMessagesUpdateFrame` with `run_llm=True`
|
||||
- `OpenAILLMContextFrame` with desired messages in a new context
|
||||
|
||||
- `LLMUserResponseAggregator` and `LLMAssistantResponseAggregator` are
|
||||
deprecated, as they depended on the now-deprecated `LLMMessagesFrame`. Use
|
||||
`LLMUserContextAggregator` and `LLMAssistantResponseAggregator` (or
|
||||
LLM-specific subclasses thereof) instead.
|
||||
|
||||
## [0.0.78] - 2025-08-07
|
||||
|
||||
### Added
|
||||
|
||||
- Added `enable_emulated_vad_interruptions` to `LLMUserAggregatorParams`.
|
||||
When user speech is emulated (e.g. when a transcription is received but
|
||||
VAD doesn't detect speech), this parameter controls whether the emulated
|
||||
speech can interrupt the bot. Default is False (emulated speech is ignored
|
||||
while the bot is speaking).
|
||||
|
||||
- Added new `handle_sigint` and `handle_sigterm` to `RunnerArguments`. This
|
||||
allows applications to know what settings they should use for the environment
|
||||
they are running on. Also, added `pipeline_idle_timeout_secs` to be able to
|
||||
control the `PipelineTask` idle timeout.
|
||||
|
||||
- Added `processor` field to `ErrorFrame` to indicate `FrameProcessor` that
|
||||
generated the error.
|
||||
|
||||
- Added new language support for `AWSTranscribeSTTService`. All languages
|
||||
supporting streaming data input are now supported:
|
||||
https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html
|
||||
|
||||
- Added support for Simli Trinity Avatars. A new `is_trinity_avatar` parameter
|
||||
has been introduced to specify whether the provided `faceId` corresponds to a
|
||||
Trinity avatar, which is required for optimal Trinity avatar performance.
|
||||
|
||||
- The development runner how handles custom `body` data for `DailyTransport`.
|
||||
The `body` data is passed to the Pipecat client. You can POST to the `/start`
|
||||
endpoint with a request body of:
|
||||
|
||||
```
|
||||
{
|
||||
"createDailyRoom": true,
|
||||
"dailyRoomProperties": { "start_video_off": true },
|
||||
"body": { "custom_data": "value" }
|
||||
}
|
||||
```
|
||||
|
||||
The `body` information is parsed and used in the application. The
|
||||
`dailyRoomProperties` are currently not handled.
|
||||
|
||||
- Added detailed latency logging to `UserBotLatencyLogObserver`, capturing
|
||||
average response time between user stop and bot start, as well as minimum and
|
||||
maximum response latency.
|
||||
|
||||
- Added Chinese, Japanese, Korean word timestamp support to
|
||||
`CartesiaTTSService`.
|
||||
|
||||
- Added `region` parameter to `GladiaSTTService`. Accepted values: eu-west
|
||||
(default), us-west.
|
||||
|
||||
### Changed
|
||||
|
||||
- System frames are now queued. Before, system frames could be generated from
|
||||
any task and would not guarantee any order which was causing undesired
|
||||
behavior. Also, it was possible to get into some rare recursion issues because
|
||||
of the way system frames were executed (they were executed in-place, meaning
|
||||
calling `push_frame()` would finish after the system frame traversed all the
|
||||
pipeline). This makes system frames more deterministic.
|
||||
|
||||
- Changed the default model for both `ElevenLabsTTSService` and
|
||||
`ElevenLabsHttpTTSService` to `eleven_turbo_v2_5`. The rationale for this
|
||||
change is that the Turbo v2.5 model exhibits the most stable voice quality
|
||||
along with very low latency TTFB; latencies are on par with the Flash v2.5
|
||||
model. Also, the Turbo v2.5 model outputs word/timestamp alignment data with
|
||||
correct spacing.
|
||||
|
||||
- The development runners `/connect` and `/start` endpoint now both return
|
||||
`dailyRoom` and `dailyToken` in place of the previous `room_url` and `token`.
|
||||
|
||||
- Updated the `pipecat.runner.daily` utility to only a take `DAILY_API_URL` and
|
||||
`DAILY_SAMPLE_ROOM_URL` environment variables instead of argparsing `-u` and
|
||||
`-k`, respectively.
|
||||
|
||||
- Updated `daily-python` to 0.19.6.
|
||||
|
||||
- Changed `TavusVideoService` to send audio or video frames only after the
|
||||
transport is ready, preventing warning messages at startup.
|
||||
|
||||
- The development runner now strips any provided protocol (e.g. https://) from
|
||||
the proxy address and issues a warning. It also strips trailing `/`.
|
||||
|
||||
### Deprecated
|
||||
|
||||
- In the `pipecat.runner.daily`, the `configure_with_args()` function is
|
||||
deprecated. Use the `configure()` function instead.
|
||||
|
||||
- The development runner's `/connect` endpoint is deprecated and will be
|
||||
removed in a future version. Use the `/start` endpoint in its place. In the
|
||||
meantime, both endpoints work and deliver equivalent functionality.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed a `DailyTransport` issue that would result in an unhandled
|
||||
`concurrent.futures.CancelledError` when a future is cancelled.
|
||||
|
||||
- Fixed a `RivaSTTService` issue that would result in an unhandled
|
||||
`concurrent.futures.CancelledError` when a future is cancelled when reading
|
||||
from the audio chunks from the incoming audio stream.
|
||||
|
||||
- Fixed an issue in the `BaseOutputTransport`, mainly reproducible with
|
||||
`FastAPIWebsocketOutputTransport` when the audio mixer was enabled, where the
|
||||
loop could consume 100% CPU by continuously returning without delay, preventing
|
||||
other asyncio tasks (such as cancellation or shutdown signals) from being
|
||||
processed.
|
||||
|
||||
- Fixed an issue where `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame`
|
||||
were not emitted when using `TavusVideoService` or `HeyGenVideoService`.
|
||||
|
||||
- Fixed an issue in `LiveKitTransport` where empty `AudioRawFrame`s were pushed
|
||||
down the pipeline. This resulted in warnings by the STT processor.
|
||||
- Fixed `PiperTTSService` to send text as a JSON object in the request body,
|
||||
@@ -958,9 +34,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
### Other
|
||||
|
||||
- Added `07aa-interruptible-soniox.py`, `07ab-interruptible-inworld-http.py`,
|
||||
`07ac-interruptible-asyncai.py` and `07ac-interruptible-asyncai-http.py`
|
||||
release evals.
|
||||
- Allow Daily transport to quickstart bot example.
|
||||
|
||||
## [0.0.77] - 2025-07-31
|
||||
|
||||
|
||||
@@ -31,23 +31,6 @@ git push origin your-branch-name
|
||||
|
||||
Our maintainers will review your PR, and once everything is good, your contributions will be merged!
|
||||
|
||||
## Dependency Management
|
||||
|
||||
This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.
|
||||
|
||||
### Adding or Updating Dependencies
|
||||
|
||||
1. Edit `pyproject.toml` to add/update dependencies
|
||||
2. Run `uv lock` to update the lockfile with new dependency resolution
|
||||
3. Run `uv sync` to install the updated dependencies locally
|
||||
4. Always commit both files together:
|
||||
```bash
|
||||
git add pyproject.toml uv.lock
|
||||
git commit -m "feat: add new dependency for feature X"
|
||||
```
|
||||
|
||||
**Important:** Never manually edit `uv.lock`. It's auto-generated by `uv lock`.
|
||||
|
||||
## Code Style and Documentation
|
||||
|
||||
### Python Code Style
|
||||
|
||||
165
README.md
165
README.md
@@ -2,7 +2,7 @@
|
||||
<img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
|
||||
</div></h1>
|
||||
|
||||
[](https://pypi.org/project/pipecat-ai)  [](https://codecov.io/gh/pipecat-ai/pipecat) [](https://docs.pipecat.ai) [](https://discord.gg/pipecat) [](https://deepwiki.com/pipecat-ai/pipecat)
|
||||
[](https://pypi.org/project/pipecat-ai)  [](https://codecov.io/gh/pipecat-ai/pipecat) [](https://docs.pipecat.ai) [](https://discord.gg/pipecat)
|
||||
|
||||
# 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
|
||||
|
||||
@@ -21,8 +21,6 @@
|
||||
|
||||
🧭 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
|
||||
|
||||
🔍 Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
|
||||
|
||||
## 🧠 Why Pipecat?
|
||||
|
||||
- **Voice-first**: Integrates speech recognition, text-to-speech, and conversation handling
|
||||
@@ -30,41 +28,6 @@
|
||||
- **Composable Pipelines**: Build complex behavior from modular components
|
||||
- **Real-Time**: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
|
||||
|
||||
## 📱 Client SDKs
|
||||
|
||||
You can connect to Pipecat from any platform using our official SDKs:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<td>
|
||||
<img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/javascript/javascript-original.svg" width="40" height="40" alt="JavaScript"/>
|
||||
<a href="https://docs.pipecat.ai/client/js/introduction">JavaScript</a>
|
||||
</td>
|
||||
<td>
|
||||
<img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React"/>
|
||||
<a href="https://docs.pipecat.ai/client/react/introduction">React</a>
|
||||
</td>
|
||||
<td>
|
||||
<img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React Native"/>
|
||||
<a href="https://docs.pipecat.ai/client/react-native/introduction">React Native</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/swift/swift-original.svg" width="40" height="40" alt="Swift"/>
|
||||
<a href="https://docs.pipecat.ai/client/ios/introduction">Swift</a>
|
||||
</td>
|
||||
<td>
|
||||
<img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/kotlin/kotlin-original.svg" width="40" height="40" alt="Kotlin"/>
|
||||
<a href="https://docs.pipecat.ai/client/android/introduction">Kotlin</a>
|
||||
</td>
|
||||
<td>
|
||||
<img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/cplusplus/cplusplus-original.svg" width="40" height="40" alt="JavaScript"/>
|
||||
<a href="https://docs.pipecat.ai/client/c++/introduction">C++</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## 🎬 See it in action
|
||||
|
||||
<p float="left">
|
||||
@@ -75,113 +38,111 @@ You can connect to Pipecat from any platform using our official SDKs:
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/moondream-chatbot/image.png" width="400" /></a>
|
||||
</p>
|
||||
|
||||
## 📱 Client SDKs
|
||||
|
||||
You can connect to Pipecat from any platform using our official SDKs:
|
||||
|
||||
| Platform | SDK Repo | Description |
|
||||
| -------- | ------------------------------------------------------------------------------ | -------------------------------- |
|
||||
| Web | [pipecat-client-web](https://github.com/pipecat-ai/pipecat-client-web) | JavaScript and React client SDKs |
|
||||
| iOS | [pipecat-client-ios](https://github.com/pipecat-ai/pipecat-client-ios) | Swift SDK for iOS |
|
||||
| Android | [pipecat-client-android](https://github.com/pipecat-ai/pipecat-client-android) | Kotlin SDK for Android |
|
||||
| C++ | [pipecat-client-cxx](https://github.com/pipecat-ai/pipecat-client-cxx) | C++ client SDK |
|
||||
|
||||
## 🧩 Available services
|
||||
|
||||
| Category | Services |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai) |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
|
||||
| Serializers | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) |
|
||||
| Video | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) |
|
||||
| Memory | [mem0](https://docs.pipecat.ai/server/services/memory/mem0) |
|
||||
| Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
|
||||
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
||||
|
||||
## ⚡ Getting started
|
||||
|
||||
You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you're ready.
|
||||
You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready.
|
||||
|
||||
1. Install uv
|
||||
```shell
|
||||
# Install the module
|
||||
pip install pipecat-ai
|
||||
|
||||
```bash
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
```
|
||||
# Set up your environment
|
||||
cp dot-env.template .env
|
||||
```
|
||||
|
||||
> **Need help?** Refer to the [uv install documentation](https://docs.astral.sh/uv/getting-started/installation/).
|
||||
To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
|
||||
|
||||
2. Install the module
|
||||
|
||||
```bash
|
||||
# For new projects
|
||||
uv init my-pipecat-app
|
||||
cd my-pipecat-app
|
||||
uv add pipecat-ai
|
||||
|
||||
# Or for existing projects
|
||||
uv add pipecat-ai
|
||||
```
|
||||
|
||||
3. Set up your environment
|
||||
|
||||
```bash
|
||||
cp env.example .env
|
||||
```
|
||||
|
||||
4. To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
|
||||
|
||||
```bash
|
||||
uv add "pipecat-ai[option,...]"
|
||||
```
|
||||
|
||||
> **Using pip?** You can still use `pip install pipecat-ai` and `pip install "pipecat-ai[option,...]"` to get set up.
|
||||
```shell
|
||||
pip install "pipecat-ai[option,...]"
|
||||
```
|
||||
|
||||
## 🧪 Code examples
|
||||
|
||||
- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
|
||||
- [Example apps](https://github.com/pipecat-ai/pipecat-examples) — complete applications that you can use as starting points for development
|
||||
|
||||
## 🛠️ Contributing to the framework
|
||||
## 🛠️ Hacking on the framework itself
|
||||
|
||||
### Prerequisites
|
||||
1. Set up a virtual environment before following these instructions. From the root of the repo:
|
||||
|
||||
**Minimum Python Version:** 3.10
|
||||
**Recommended Python Version:** 3.12
|
||||
|
||||
### Setup Steps
|
||||
|
||||
1. Clone the repository and navigate to it:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/pipecat-ai/pipecat.git
|
||||
cd pipecat
|
||||
```shell
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
```
|
||||
|
||||
2. Install development and testing dependencies:
|
||||
2. Install the development dependencies:
|
||||
|
||||
```bash
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra gstreamer \
|
||||
--no-extra krisp \
|
||||
--no-extra local \
|
||||
--no-extra ultravox # (ultravox not fully supported on macOS)
|
||||
```shell
|
||||
pip install -r dev-requirements.txt
|
||||
```
|
||||
|
||||
3. Install the git pre-commit hooks:
|
||||
3. Install the git pre-commit hooks (these help ensure your code follows project rules):
|
||||
|
||||
```bash
|
||||
uv run pre-commit install
|
||||
```shell
|
||||
pre-commit install
|
||||
```
|
||||
|
||||
> **Note**: Some extras (local, gstreamer) require system dependencies. See documentation if you encounter build errors.
|
||||
4. Install the `pipecat-ai` package locally in editable mode:
|
||||
|
||||
```shell
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
> The `-e` or `--editable` option allows you to modify the code without reinstalling.
|
||||
|
||||
5. Include optional dependencies as needed. For example:
|
||||
|
||||
```shell
|
||||
pip install -e ".[daily,deepgram,cartesia,openai,silero]"
|
||||
```
|
||||
|
||||
6. (Optional) If you want to use this package from another directory:
|
||||
|
||||
```shell
|
||||
pip install "path_to_this_repo[option,...]"
|
||||
```
|
||||
|
||||
### Running tests
|
||||
|
||||
To run all tests, from the root directory:
|
||||
Install the test dependencies:
|
||||
|
||||
```bash
|
||||
uv run pytest
|
||||
```shell
|
||||
pip install -r test-requirements.txt
|
||||
```
|
||||
|
||||
Run a specific test suite:
|
||||
From the root directory, run:
|
||||
|
||||
```bash
|
||||
uv run pytest tests/test_name.py
|
||||
```shell
|
||||
pytest
|
||||
```
|
||||
|
||||
### Setting up your editor
|
||||
|
||||
13
dev-requirements.txt
Normal file
13
dev-requirements.txt
Normal file
@@ -0,0 +1,13 @@
|
||||
build~=1.2.2
|
||||
coverage~=7.9.1
|
||||
grpcio-tools~=1.67.1
|
||||
pip-tools~=7.4.1
|
||||
pre-commit~=4.2.0
|
||||
pyright~=1.1.402
|
||||
pytest~=8.4.1
|
||||
pytest-asyncio~=1.0.0
|
||||
pytest-aiohttp==1.1.0
|
||||
ruff~=0.12.1
|
||||
setuptools~=78.1.1
|
||||
setuptools_scm~=8.3.1
|
||||
python-dotenv~=1.1.1
|
||||
10
docs/README.md
Normal file
10
docs/README.md
Normal file
@@ -0,0 +1,10 @@
|
||||
# Pipecat Docs
|
||||
|
||||
## [Architecture Overview](architecture.md)
|
||||
|
||||
Learn about the thinking behind the framework's design.
|
||||
|
||||
## [A Frame's Progress](frame-progress.md)
|
||||
|
||||
See how a Frame is processed through a Transport, a Pipeline, and a series of Frame Processors.
|
||||
|
||||
@@ -1,27 +1,17 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Build docs using uv
|
||||
echo "Installing dependencies with uv..."
|
||||
uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
|
||||
# Check if sphinx-build is available
|
||||
if ! uv run sphinx-build --version &> /dev/null; then
|
||||
echo "Error: sphinx-build is not available" >&2
|
||||
# Check if sphinx-build is installed
|
||||
if ! command -v sphinx-build &> /dev/null; then
|
||||
echo "Error: sphinx-build is not installed or not in PATH" >&2
|
||||
echo "Please install Sphinx using: pip install -r requirements.txt" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Clean previous build
|
||||
rm -rf _build
|
||||
|
||||
echo "Building documentation..."
|
||||
# Build docs matching ReadTheDocs configuration
|
||||
uv run sphinx-build -b html -d _build/doctrees . _build/html -W --keep-going
|
||||
sphinx-build -b html -d _build/doctrees . _build/html -W --keep-going
|
||||
|
||||
if [ $? -eq 0 ]; then
|
||||
echo "Documentation built successfully!"
|
||||
# Open docs (MacOS)
|
||||
open _build/html/index.html
|
||||
else
|
||||
echo "Documentation build failed!" >&2
|
||||
exit 1
|
||||
fi
|
||||
# Open docs (MacOS)
|
||||
open _build/html/index.html
|
||||
154
docs/api/conf.py
154
docs/api/conf.py
@@ -1,5 +1,4 @@
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
@@ -29,7 +28,6 @@ extensions = [
|
||||
|
||||
suppress_warnings = [
|
||||
"autodoc.mocked_object",
|
||||
"toc.not_included",
|
||||
]
|
||||
|
||||
# Napoleon settings
|
||||
@@ -47,40 +45,85 @@ autodoc_default_options = {
|
||||
|
||||
# Mock imports for optional dependencies
|
||||
autodoc_mock_imports = [
|
||||
# Krisp - has build issues on some platforms
|
||||
"pipecat_ai_krisp",
|
||||
"riva",
|
||||
"livekit",
|
||||
"pyht", # Base PlayHT package
|
||||
"pyht.async_client", # PlayHT specific imports
|
||||
"pyht.client",
|
||||
"pyht.protos",
|
||||
"pyht.protos.api_pb2",
|
||||
"pipecat_ai_playht", # PlayHT wrapper
|
||||
"aiortc",
|
||||
"aiortc.mediastreams",
|
||||
"cv2",
|
||||
"av",
|
||||
"pyneuphonic",
|
||||
"mem0",
|
||||
"mlx_whisper",
|
||||
"anthropic",
|
||||
"assemblyai",
|
||||
"boto3",
|
||||
"azure",
|
||||
"cartesia",
|
||||
"deepgram",
|
||||
"elevenlabs",
|
||||
"fal",
|
||||
"gladia",
|
||||
"google",
|
||||
"krisp",
|
||||
# System-specific GUI libraries
|
||||
"langchain",
|
||||
"lmnt",
|
||||
"noisereduce",
|
||||
"openpipe",
|
||||
"simli",
|
||||
"soundfile",
|
||||
"soniox",
|
||||
"pipecat_ai_krisp",
|
||||
"pyaudio",
|
||||
"_tkinter",
|
||||
"tkinter",
|
||||
# Platform-specific audio libraries (if needed)
|
||||
"gi",
|
||||
"gi.require_version",
|
||||
"gi.repository",
|
||||
# OpenCV - sometimes has import issues during docs build
|
||||
"cv2",
|
||||
# Heavy ML packages excluded from ReadTheDocs
|
||||
# ultravox dependencies
|
||||
"daily",
|
||||
"daily_python",
|
||||
# Moondream dependencies
|
||||
"torch",
|
||||
"transformers",
|
||||
"intel_extension_for_pytorch",
|
||||
# Ultravox dependencies
|
||||
"huggingface_hub",
|
||||
"vllm",
|
||||
"vllm.engine.arg_utils",
|
||||
# local-smart-turn dependencies
|
||||
"coremltools",
|
||||
"coremltools.models",
|
||||
"coremltools.models.MLModel",
|
||||
"torch",
|
||||
"torch.nn",
|
||||
"torch.nn.functional",
|
||||
"torchaudio",
|
||||
# moondream dependencies
|
||||
"transformers",
|
||||
"transformers.AutoTokenizer",
|
||||
"transformers.AutoFeatureExtractor",
|
||||
"AutoFeatureExtractor",
|
||||
"timm",
|
||||
"einops",
|
||||
"intel_extension_for_pytorch",
|
||||
"huggingface_hub",
|
||||
# riva dependencies
|
||||
# Langchain dependencies
|
||||
"langchain_core",
|
||||
"langchain_core.messages",
|
||||
"langchain_core.runnables",
|
||||
"langchain_core.messages.AIMessageChunk",
|
||||
"langchain_core.runnables.Runnable",
|
||||
# LiveKit dependencies
|
||||
"livekit",
|
||||
"livekit.rtc",
|
||||
"livekit_api",
|
||||
"livekit_protocol",
|
||||
"tenacity",
|
||||
"tenacity.retry",
|
||||
"tenacity.stop_after_attempt",
|
||||
"tenacity.wait_exponential",
|
||||
"rtc",
|
||||
"rtc.Room",
|
||||
"rtc.RoomOptions",
|
||||
"rtc.AudioSource",
|
||||
"rtc.LocalAudioTrack",
|
||||
"rtc.TrackPublishOptions",
|
||||
"rtc.TrackSource",
|
||||
"rtc.AudioStream",
|
||||
"rtc.AudioFrameEvent",
|
||||
"rtc.AudioFrame",
|
||||
"rtc.Track",
|
||||
"rtc.TrackKind",
|
||||
"rtc.RemoteParticipant",
|
||||
"rtc.RemoteTrackPublication",
|
||||
"rtc.DataPacket",
|
||||
# Riva dependencies
|
||||
"riva",
|
||||
"riva.client",
|
||||
"riva.client.Auth",
|
||||
@@ -90,14 +133,57 @@ autodoc_mock_imports = [
|
||||
"riva.client.AudioEncoding",
|
||||
"riva.client.proto.riva_tts_pb2",
|
||||
"riva.client.SpeechSynthesisService",
|
||||
# MLX dependencies (Apple Silicon specific)
|
||||
"mlx",
|
||||
"mlx_whisper", # Note: might need underscore format too
|
||||
# Local CoreML Smart Turn dependencies
|
||||
"coremltools",
|
||||
"coremltools.models",
|
||||
"coremltools.models.MLModel",
|
||||
"torch",
|
||||
"torch.nn",
|
||||
"torch.nn.functional",
|
||||
"transformers",
|
||||
"transformers.AutoFeatureExtractor",
|
||||
# Also add specific classes that are imported
|
||||
"AutoFeatureExtractor",
|
||||
# Sentry dependencies
|
||||
"sentry_sdk",
|
||||
# AWS Nova Sonic dependencies
|
||||
"aws_sdk_bedrock_runtime",
|
||||
"aws_sdk_bedrock_runtime.client",
|
||||
"aws_sdk_bedrock_runtime.config",
|
||||
"aws_sdk_bedrock_runtime.models",
|
||||
"smithy_aws_core",
|
||||
"smithy_aws_core.credentials_resolvers",
|
||||
"smithy_aws_core.credentials_resolvers.static",
|
||||
"smithy_aws_core.identity",
|
||||
"smithy_core",
|
||||
"smithy_core.aio",
|
||||
"smithy_core.aio.eventstream",
|
||||
# MCP dependencies (you may already have these)
|
||||
"mcp",
|
||||
"mcp.client",
|
||||
"mcp.client.session_group",
|
||||
"mcp.client.sse",
|
||||
"mcp.client.stdio",
|
||||
"mcp.ClientSession",
|
||||
"mcp.StdioServerParameters",
|
||||
# gstreamer
|
||||
"gi",
|
||||
"gi.require_version",
|
||||
"gi.repository",
|
||||
# Protobuf mocks
|
||||
"pipecat.frames.protobufs.frames_pb2",
|
||||
"pipecat.serializers.protobuf",
|
||||
"google.protobuf",
|
||||
"google.protobuf.descriptor",
|
||||
"google.protobuf.descriptor_pool",
|
||||
"google.protobuf.runtime_version",
|
||||
"google.protobuf.symbol_database",
|
||||
"google.protobuf.internal.builder",
|
||||
]
|
||||
|
||||
# HTML output settings
|
||||
html_theme = "sphinx_rtd_theme"
|
||||
html_static_path = ["_static"] if os.path.exists("_static") else []
|
||||
html_static_path = ["_static"]
|
||||
autodoc_typehints = "signature" # Show type hints in the signature only, not in the docstring
|
||||
html_show_sphinx = False
|
||||
|
||||
|
||||
@@ -14,14 +14,13 @@ Quick Links
|
||||
* `Join our Community <https://discord.gg/pipecat>`_
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:maxdepth: 3
|
||||
:caption: API Reference
|
||||
:hidden:
|
||||
|
||||
Adapters <api/pipecat.adapters>
|
||||
Audio <api/pipecat.audio>
|
||||
Clocks <api/pipecat.clocks>
|
||||
Extensions <api/pipecat.extensions>
|
||||
Frames <api/pipecat.frames>
|
||||
Metrics <api/pipecat.metrics>
|
||||
Observers <api/pipecat.observers>
|
||||
|
||||
59
docs/api/requirements.txt
Normal file
59
docs/api/requirements.txt
Normal file
@@ -0,0 +1,59 @@
|
||||
# Sphinx dependencies
|
||||
sphinx>=8.1.3
|
||||
sphinx-rtd-theme
|
||||
sphinx-markdown-builder
|
||||
sphinx-autodoc-typehints
|
||||
toml
|
||||
|
||||
# Install all extras individually to ensure they're properly resolved
|
||||
pipecat-ai[anthropic]
|
||||
pipecat-ai[assemblyai]
|
||||
pipecat-ai[asyncai]
|
||||
pipecat-ai[aws]
|
||||
pipecat-ai[azure]
|
||||
pipecat-ai[cartesia]
|
||||
pipecat-ai[cerebras]
|
||||
pipecat-ai[deepseek]
|
||||
pipecat-ai[daily]
|
||||
pipecat-ai[deepgram]
|
||||
pipecat-ai[elevenlabs]
|
||||
pipecat-ai[fal]
|
||||
pipecat-ai[fireworks]
|
||||
pipecat-ai[fish]
|
||||
pipecat-ai[gladia]
|
||||
pipecat-ai[google]
|
||||
pipecat-ai[grok]
|
||||
pipecat-ai[groq]
|
||||
pipecat-ai[inworld]
|
||||
# pipecat-ai[krisp] # Mocked
|
||||
pipecat-ai[koala]
|
||||
# pipecat-ai[langchain] # Mocked
|
||||
# pipecat-ai[livekit] # Mocked
|
||||
pipecat-ai[lmnt]
|
||||
pipecat-ai[local]
|
||||
# pipecat-ai[local-smart-turn] # Mocked
|
||||
# pipecat-ai[mem0] # Mocked
|
||||
# pipecat-ai[mlx-whisper] # Mocked
|
||||
# pipecat-ai[moondream] # Mocked
|
||||
pipecat-ai[nim]
|
||||
# pipecat-ai[neuphonic] # Mocked
|
||||
pipecat-ai[noisereduce]
|
||||
pipecat-ai[openai]
|
||||
# pipecat-ai[openpipe]
|
||||
# pipecat-ai[playht] # Mocked due to grpcio conflict with riva
|
||||
pipecat-ai[qwen]
|
||||
pipecat-ai[remote-smart-turn]
|
||||
# pipecat-ai[riva] # Mocked
|
||||
pipecat-ai[runner]
|
||||
pipecat-ai[sambanova]
|
||||
pipecat-ai[silero]
|
||||
pipecat-ai[simli]
|
||||
pipecat-ai[soundfile]
|
||||
pipecat-ai[soniox]
|
||||
pipecat-ai[speechmatics]
|
||||
pipecat-ai[tavus]
|
||||
pipecat-ai[together]
|
||||
# pipecat-ai[ultravox] # Mocked
|
||||
# pipecat-ai[webrtc] # Mocked
|
||||
pipecat-ai[websocket]
|
||||
pipecat-ai[whisper]
|
||||
17
docs/architecture.md
Normal file
17
docs/architecture.md
Normal file
@@ -0,0 +1,17 @@
|
||||
# Pipecat architecture guide
|
||||
|
||||
## Frames
|
||||
|
||||
Frames can represent discrete chunks of data, for instance a chunk of text, a chunk of audio, or an image. They can also be used to as control flow, for instance a frame that indicates that there is no more data available, or that a user started or stopped talking. They can also represent more complex data structures, such as a message array used for an LLM completion.
|
||||
|
||||
## FrameProcessors
|
||||
|
||||
Frame processors operate on frames. Every frame processor implements a `process_frame` method that consumes one frame and produces zero or more frames. Frame processors can do simple transforms, such as concatenating text fragments into sentences, or they can treat frames as input for an AI Service, and emit chat completions based on message arrays or transform text into audio or images.
|
||||
|
||||
## Pipelines
|
||||
|
||||
Pipelines are lists of frame processors linked together. Frame processors can push frames upstream or downstream to their peers. A very simple pipeline might chain an LLM frame processor to a text-to-speech frame processor, with a transport as an output.
|
||||
|
||||
## Transports
|
||||
|
||||
Transports provide input and output frame processors to receive or send frames respectively. For example, the `DailyTransport` does this with a WebRTC session joined to a Daily.co room.
|
||||
46
docs/frame-progress.md
Normal file
46
docs/frame-progress.md
Normal file
@@ -0,0 +1,46 @@
|
||||
# A Frame's Progress
|
||||
|
||||
1. A user says “Hello, LLM” and the cloud transcription service delivers a transcription to the Transport.
|
||||
|
||||
|
||||
2. The Transport places a Transcription frame in the Pipeline’s source queue.
|
||||
|
||||
|
||||
3. The Pipeline passes the Transcription frame to the first Frame Processor in its list, the LLM User Message Aggregator.
|
||||
|
||||
|
||||
4. The LLM User Message Aggregator updates the LLM Context with a `{“user”: “Hello LLM”}` message.
|
||||
|
||||
|
||||
5. The LLM User Message Aggregator yields an LLM Message Frame, containing the updated LLM Context. The Pipeline passes this frame to the LLM Frame Processor.
|
||||
|
||||
|
||||
6. The LLM Frame Processor creates a streaming chat completion based on the LLM context and yields the first chunk of a response, Text Frame with the value “Hi, “. The Pipeline passes this frame to the TTS Frame Processor. The TTS Frame Processor aggregates this response but doesn’t yield anything, yet, because it’s waiting for a full sentence.
|
||||
|
||||
|
||||
7. The LLM Frame Processor yields another Text Frame with the value “there.”. The Pipeline passes this frame to the TTS Frame Processor.
|
||||
|
||||
|
||||
8. The TTS Frame Processor now has a full sentence, so it starts streaming audio based on “Hi, there.” It yields the first chunk of streaming audio as an Audio frame, which the Pipeline passes to the LLM Assistant Message Aggregator.
|
||||
|
||||
|
||||
9. The LLM Assistant Message Aggregator doesn’t do anything with Audio frames, so it immediately yields the frame, unchanged. This is the convention for all Frame Processors: frames that the processor doesn’t process should be immediately yielded.
|
||||
|
||||
|
||||
10. The Pipeline places the first Audio frame in its sink queue, which is being watched by the Transport. Since the frame is now in a queue, the Pipeline can continue processing other frames. Note that the source and sink queues form a sort of “boundary of concurrent processing” between a Pipeline and the outside world. In a Pipeline, Frames are processed sequentially; once a Frame is on a queue it can be processed in parallel with the frames being processed by the Pipeline. TODO: link to a more in-depth section about this.
|
||||
|
||||
|
||||
11. The TTS Frame Processor yields another Audio frame as the Transport transmits the first Audio frame.
|
||||
|
||||
|
||||
12. As before, the LLM Assistant Message Aggregator immediately yields the Audio frame and the Pipeline places the Audio frame in the sink queue.
|
||||
|
||||
|
||||
13. The TTS Frame Processor has no more frames to yield. The LLM Frame Processor emits an LLM Response End Frame, which the Pipeline passes to the TTS Frame Processor.
|
||||
|
||||
|
||||
14. The TTS Frame Processor immediately yields the LLM Response End Frame, so the Pipeline passes it along to the LLM Assistant Message Aggregator. The LLM Assistant Message Aggregator updates the LLM Context with the full response from the LLM. TODO TODO: I realized I forgot that the TSS Frame Processor also yields the Text frames that the LLM emitted so that the LLM Assistant Message Aggregator could accumulate them, arrggh.
|
||||
|
||||
|
||||
15. The system is quiet, and waiting for the next message from the Transport.
|
||||
|
||||
110
docs/frame.md
Normal file
110
docs/frame.md
Normal file
@@ -0,0 +1,110 @@
|
||||
# Understanding Different Frame Types in the Pipecat System
|
||||
|
||||
In the Pipecat system, frames are used to represent different types of data and control signals that flow through the pipeline. Understanding these frame types is crucial for working with the system effectively. This tutorial will cover the main categories of frames and their specific uses.
|
||||
|
||||
## 1. Base Frame Classes
|
||||
|
||||
### Frame
|
||||
The `Frame` class is the base class for all frames. It includes:
|
||||
- `id`: A unique identifier
|
||||
- `name`: A descriptive name
|
||||
- `pts`: Presentation timestamp (optional)
|
||||
|
||||
### DataFrame
|
||||
`DataFrame` is a subclass of `Frame` and serves as a base for most data-carrying frames.
|
||||
|
||||
## 2. Audio Frames
|
||||
|
||||
### AudioRawFrame
|
||||
Represents a chunk of audio with properties:
|
||||
- `audio`: Raw audio data
|
||||
- `sample_rate`: Audio sample rate
|
||||
- `num_channels`: Number of audio channels
|
||||
|
||||
Subclasses include:
|
||||
- `InputAudioRawFrame`: For audio from input sources
|
||||
- `OutputAudioRawFrame`: For audio to be played by output devices
|
||||
- `TTSAudioRawFrame`: For audio generated by Text-to-Speech services
|
||||
|
||||
## 3. Image Frames
|
||||
|
||||
### ImageRawFrame
|
||||
Represents an image with properties:
|
||||
- `image`: Raw image data
|
||||
- `size`: Image dimensions
|
||||
- `format`: Image format (e.g., JPEG, PNG)
|
||||
|
||||
Subclasses include:
|
||||
- `InputImageRawFrame`: For images from input sources
|
||||
- `OutputImageRawFrame`: For images to be displayed
|
||||
- `UserImageRawFrame`: For images associated with a specific user
|
||||
- `VisionImageRawFrame`: For images with associated text for description
|
||||
- `URLImageRawFrame`: For images with an associated URL
|
||||
|
||||
### SpriteFrame
|
||||
Represents an animated sprite, containing a list of `ImageRawFrame` objects.
|
||||
|
||||
## 4. Text and Transcription Frames
|
||||
|
||||
### TextFrame
|
||||
Represents a chunk of text, used for various purposes in the pipeline.
|
||||
|
||||
### TranscriptionFrame
|
||||
A specialized `TextFrame` for speech transcriptions, including:
|
||||
- `user_id`: ID of the speaking user
|
||||
- `timestamp`: When the transcription was generated
|
||||
- `language`: Detected language of the speech
|
||||
|
||||
### InterimTranscriptionFrame
|
||||
Similar to `TranscriptionFrame`, but for interim (not final) transcriptions.
|
||||
|
||||
## 5. LLM (Language Model) Frames
|
||||
|
||||
### LLMMessagesFrame
|
||||
Contains a list of messages for an LLM service to process.
|
||||
|
||||
### LLMMessagesAppendFrame and LLMMessagesUpdateFrame
|
||||
Used to modify the current context of LLM messages.
|
||||
|
||||
### LLMSetToolsFrame
|
||||
Specifies tools (functions) available for the LLM to use.
|
||||
|
||||
### LLMEnablePromptCachingFrame
|
||||
Controls prompt caching in certain LLMs.
|
||||
|
||||
## 6. System and Control Frames
|
||||
|
||||
### SystemFrame
|
||||
Base class for system-level frames.
|
||||
|
||||
Important system frames include:
|
||||
- `StartFrame`: Initiates a pipeline
|
||||
- `CancelFrame`: Stops a pipeline immediately
|
||||
- `ErrorFrame`: Notifies of errors (with `FatalErrorFrame` for unrecoverable errors)
|
||||
- `EndTaskFrame` and `CancelTaskFrame`: Control pipeline tasks
|
||||
- `StartInterruptionFrame` and `StopInterruptionFrame`: Indicate user speech for interruptions
|
||||
|
||||
### ControlFrame
|
||||
Base class for control-flow frames.
|
||||
|
||||
Notable control frames:
|
||||
- `EndFrame`: Signals the end of a pipeline
|
||||
- `LLMFullResponseStartFrame` and `LLMFullResponseEndFrame`: Bracket LLM responses
|
||||
- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame`: Indicate user speech activity
|
||||
- `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame`: Indicate bot speech activity
|
||||
- `TTSStartedFrame` and `TTSStoppedFrame`: Bracket Text-to-Speech responses
|
||||
|
||||
## 7. Special Purpose Frames
|
||||
|
||||
### MetricsFrame
|
||||
Contains performance metrics data.
|
||||
|
||||
### FunctionCallInProgressFrame and FunctionCallResultFrame
|
||||
Used for handling LLM function (tool) calls.
|
||||
|
||||
### ServiceUpdateSettingsFrame
|
||||
Base class for updating service settings, with specific subclasses for LLM, TTS, and STT services.
|
||||
|
||||
## Conclusion
|
||||
|
||||
Understanding these frame types is essential for working with the Pipecat system. Each frame type serves a specific purpose in the pipeline, whether it's carrying data (like audio or images), controlling the flow of the pipeline, or managing system-level operations. By using the appropriate frame types, you can effectively process and transmit various kinds of information through your pipeline.
|
||||
BIN
docs/images/frame-progress-01.png
Normal file
BIN
docs/images/frame-progress-01.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
BIN
docs/images/frame-progress-02.png
Normal file
BIN
docs/images/frame-progress-02.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 91 KiB |
BIN
docs/images/frame-progress-03.png
Normal file
BIN
docs/images/frame-progress-03.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 92 KiB |
BIN
docs/images/frame-progress-04.png
Normal file
BIN
docs/images/frame-progress-04.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 92 KiB |
BIN
docs/images/frame-progress-05.png
Normal file
BIN
docs/images/frame-progress-05.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
BIN
docs/images/frame-progress-06.png
Normal file
BIN
docs/images/frame-progress-06.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 94 KiB |
BIN
docs/images/frame-progress-07.png
Normal file
BIN
docs/images/frame-progress-07.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 94 KiB |
BIN
docs/images/frame-progress-08.png
Normal file
BIN
docs/images/frame-progress-08.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 95 KiB |
BIN
docs/images/frame-progress-09.png
Normal file
BIN
docs/images/frame-progress-09.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 94 KiB |
BIN
docs/images/frame-progress-10.png
Normal file
BIN
docs/images/frame-progress-10.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 96 KiB |
BIN
docs/images/frame-progress-11.png
Normal file
BIN
docs/images/frame-progress-11.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 110 KiB |
BIN
docs/images/frame-progress-12.png
Normal file
BIN
docs/images/frame-progress-12.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 102 KiB |
BIN
docs/images/frame-progress-13.png
Normal file
BIN
docs/images/frame-progress-13.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 111 KiB |
BIN
docs/images/frame-progress-14.png
Normal file
BIN
docs/images/frame-progress-14.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 117 KiB |
BIN
docs/images/frame-progress-15.png
Normal file
BIN
docs/images/frame-progress-15.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
@@ -1,6 +1,3 @@
|
||||
# AI-COUSTICS
|
||||
AICOUSTICS_LICENSE_KEY=...
|
||||
|
||||
# Anthropic
|
||||
ANTHROPIC_API_KEY=...
|
||||
|
||||
@@ -32,9 +29,6 @@ CARTESIA_API_KEY=...
|
||||
DAILY_API_KEY=...
|
||||
DAILY_SAMPLE_ROOM_URL=https://...
|
||||
|
||||
# Deepgram
|
||||
DEEPGRAM_API_KEY=...
|
||||
|
||||
# ElevenLabs
|
||||
ELEVENLABS_API_KEY=...
|
||||
ELEVENLABS_VOICE_ID=...
|
||||
@@ -50,24 +44,14 @@ FIREWORKS_API_KEY=...
|
||||
|
||||
# Gladia
|
||||
GLADIA_API_KEY=...
|
||||
GLADIA_REGION=...
|
||||
|
||||
# Google
|
||||
GOOGLE_API_KEY=...
|
||||
GOOGLE_CLOUD_PROJECT_ID=...
|
||||
GOOGLE_TEST_CREDENTIALS=...
|
||||
GOOGLE_VERTEX_TEST_CREDENTIALS=...
|
||||
|
||||
# LMNT
|
||||
LMNT_API_KEY=...
|
||||
LMNT_VOICE_ID=...
|
||||
|
||||
# Perplexity
|
||||
PERPLEXITY_API_KEY=...
|
||||
|
||||
# PlayHT
|
||||
PLAYHT_USER_ID=...
|
||||
PLAYHT_API_KEY=...
|
||||
PLAY_HT_USER_ID=...
|
||||
PLAY_HT_API_KEY=...
|
||||
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
@@ -138,6 +122,7 @@ SONIOX_API_KEY=
|
||||
# Speechmatics
|
||||
SPEECHMATICS_API_KEY=...
|
||||
|
||||
|
||||
# SambaNova
|
||||
SAMBANOVA_API_KEY=...
|
||||
|
||||
@@ -145,13 +130,4 @@ SAMBANOVA_API_KEY=...
|
||||
SENTRY_DSN=...
|
||||
|
||||
# Heygen
|
||||
HEYGEN_API_KEY=...
|
||||
|
||||
# Mistral
|
||||
MISTRAL_API_KEY=...
|
||||
|
||||
# NVIDIA
|
||||
NVIDIA_API_KEY=...
|
||||
|
||||
# Qwen
|
||||
QWEN_API_KEY=...
|
||||
HEYGEN_API_KEY=...
|
||||
@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.piper.tts import PiperTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -34,7 +34,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -43,17 +43,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -61,7 +58,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.rime.tts import RimeHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -33,7 +33,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -44,17 +44,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
aiohttp_session=session,
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -62,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -17,8 +17,8 @@ from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -33,7 +33,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
@@ -41,17 +41,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -59,7 +56,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,13 +11,13 @@ import sys
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import TTSSpeakFrame
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.livekit import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
|
||||
from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -50,7 +50,7 @@ async def main():
|
||||
async def on_first_participant_joined(transport, participant_id):
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frame(
|
||||
TTSSpeakFrame(
|
||||
TextFrame(
|
||||
"Hello there! How are you doing today? Would you like to talk about the weather?"
|
||||
)
|
||||
)
|
||||
|
||||
@@ -17,8 +17,8 @@ from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.riva.tts import FastPitchTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -33,22 +33,19 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -56,7 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -9,18 +9,17 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, LLMContextFrame
|
||||
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -35,7 +34,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
@@ -52,17 +51,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
}
|
||||
]
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([llm, tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(Pipeline([llm, tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([LLMContextFrame(LLMContext(messages)), EndFrame()])
|
||||
await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -70,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -18,7 +18,7 @@ from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.fal.image import FalImageGenService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -40,7 +40,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -51,10 +51,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([imagegen, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(Pipeline([imagegen, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -66,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -74,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -17,7 +17,7 @@ from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.google.image import GoogleImageGenService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,7 +39,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
imagegen = GoogleImageGenService(
|
||||
@@ -52,7 +52,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@@ -67,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -75,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -17,22 +17,17 @@ from fastapi.responses import RedirectResponse
|
||||
from loguru import logger
|
||||
from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
|
||||
from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
|
||||
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
|
||||
from pipecat.transports.network.webrtc_connection import IceServer, SmallWebRTCConnection
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -60,8 +55,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
params=TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -81,8 +75,8 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -109,7 +103,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
|
||||
@@ -12,20 +12,15 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.daily import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.daily.transport import DailyLogLevel, DailyParams, DailyTransport
|
||||
from pipecat.transports.services.daily import DailyLogLevel, DailyParams, DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,8 +40,7 @@ async def main():
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
transport.set_log_level(DailyLogLevel.Info)
|
||||
@@ -65,8 +59,8 @@ async def main():
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -92,7 +86,7 @@ async def main():
|
||||
await transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_participant_left")
|
||||
async def on_participant_left(transport, participant, reason):
|
||||
|
||||
@@ -9,30 +9,27 @@ import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
from deepgram import LiveOptions
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import (
|
||||
InterruptionFrame,
|
||||
BotInterruptionFrame,
|
||||
TextFrame,
|
||||
TranscriptionFrame,
|
||||
TTSSpeakFrame,
|
||||
UserStartedSpeakingFrame,
|
||||
UserStoppedSpeakingFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.livekit import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
|
||||
from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -50,12 +47,16 @@ async def main():
|
||||
params=LiveKitParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
stt = DeepgramSTTService(
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
live_options=LiveOptions(
|
||||
vad_events=True,
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
@@ -74,23 +75,23 @@ async def main():
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
runner = PipelineRunner()
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
context_aggregator.user(),
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
],
|
||||
),
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
@@ -103,7 +104,7 @@ async def main():
|
||||
async def on_first_participant_joined(transport, participant_id):
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frame(
|
||||
TTSSpeakFrame(
|
||||
TextFrame(
|
||||
"Hello there! How are you doing today? Would you like to talk about the weather?"
|
||||
)
|
||||
)
|
||||
@@ -120,7 +121,7 @@ async def main():
|
||||
|
||||
await task.queue_frames(
|
||||
[
|
||||
InterruptionFrame(),
|
||||
BotInterruptionFrame(),
|
||||
UserStartedSpeakingFrame(),
|
||||
TranscriptionFrame(
|
||||
user_id=participant_id,
|
||||
@@ -131,8 +132,6 @@ async def main():
|
||||
],
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
|
||||
@@ -14,16 +14,14 @@ from loguru import logger
|
||||
from pipecat.frames.frames import (
|
||||
DataFrame,
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
LLMFullResponseStartFrame,
|
||||
LLMMessagesFrame,
|
||||
TextFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.sentence import SentenceAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
@@ -32,7 +30,7 @@ from pipecat.services.cartesia.tts import CartesiaHttpTTSService
|
||||
from pipecat.services.fal.image import FalImageGenService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -85,7 +83,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
"""Run the Calendar Month Narration bot using WebRTC transport.
|
||||
|
||||
Args:
|
||||
@@ -155,12 +153,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
}
|
||||
]
|
||||
frames.append(MonthFrame(month=month))
|
||||
frames.append(LLMContextFrame(LLMContext(messages)))
|
||||
frames.append(LLMMessagesFrame(messages))
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
# Set up transport event handlers
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -175,14 +170,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
await task.cancel()
|
||||
|
||||
# Run the pipeline
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -15,7 +15,7 @@ from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
LLMMessagesFrame,
|
||||
OutputAudioRawFrame,
|
||||
TextFrame,
|
||||
TTSAudioRawFrame,
|
||||
@@ -25,8 +25,6 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.sentence import SentenceAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
|
||||
@@ -139,7 +137,7 @@ async def main():
|
||||
)
|
||||
|
||||
task = PipelineTask(pipeline)
|
||||
await task.queue_frame(LLMContextFrame(LLMContext(messages)))
|
||||
await task.queue_frame(LLMMessagesFrame(messages))
|
||||
await task.stop_when_done()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -9,11 +9,8 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import Frame, LLMRunFrame, MetricsFrame
|
||||
from pipecat.frames.frames import Frame, MetricsFrame
|
||||
from pipecat.metrics.metrics import (
|
||||
LLMUsageMetricsData,
|
||||
ProcessingMetricsData,
|
||||
@@ -23,8 +20,7 @@ from pipecat.metrics.metrics import (
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -32,8 +28,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -65,25 +61,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -104,8 +97,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -126,7 +119,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -134,21 +126,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,22 +10,17 @@ from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from PIL import Image
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import (
|
||||
BotStartedSpeakingFrame,
|
||||
BotStoppedSpeakingFrame,
|
||||
Frame,
|
||||
LLMRunFrame,
|
||||
OutputImageRawFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -33,7 +28,7 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -70,7 +65,7 @@ class ImageSyncAggregator(FrameProcessor):
|
||||
)
|
||||
)
|
||||
|
||||
await self.push_frame(frame, direction)
|
||||
await self.push_frame(frame)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
@@ -83,8 +78,7 @@ transport_params = {
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
@@ -92,13 +86,12 @@ transport_params = {
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -117,8 +110,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
image_sync_aggregator = ImageSyncAggregator(
|
||||
os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
|
||||
@@ -144,28 +137,27 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -9,24 +9,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -75,8 +67,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -96,7 +88,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -104,14 +95,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -119,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -9,24 +9,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -37,25 +32,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -74,8 +66,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -95,7 +87,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -103,14 +94,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -118,7 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -9,15 +9,13 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
@@ -26,8 +24,8 @@ from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -50,7 +48,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
"""Speechmatics STT Service Example
|
||||
|
||||
This example demonstrates using Speechmatics Speech-to-Text service with speaker diarization and intelligent speaker management. Key features:
|
||||
@@ -124,8 +122,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
@@ -148,7 +146,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -156,14 +153,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Say a short hello to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -171,7 +168,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -9,19 +9,14 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
@@ -30,8 +25,8 @@ from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -42,25 +37,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
"""Run example using Speechmatics STT.
|
||||
|
||||
This example will use diarization within our STT service and output the words spoken by
|
||||
@@ -113,8 +105,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
@@ -137,7 +129,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -145,14 +136,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Say a short hello to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -160,7 +151,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.soniox.stt import SonioxSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -35,25 +30,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = SonioxSTTService(
|
||||
@@ -74,8 +66,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -94,7 +86,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -102,14 +93,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -117,7 +108,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,24 +11,19 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.inworld.tts import InworldTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -74,6 +66,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
voice_id="Ashley",
|
||||
model="inworld-tts-1",
|
||||
streaming=streaming, # True: real-time chunks, False: complete audio then playback
|
||||
params=InworldTTSService.InputParams(
|
||||
temperature=0.8,
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
@@ -85,8 +80,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -106,7 +101,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -114,14 +108,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -129,7 +123,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,24 +11,19 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.asyncai.tts import AsyncAIHttpTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -40,25 +35,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -80,8 +72,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -101,7 +93,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -109,14 +100,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -124,7 +115,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.asyncai.tts import AsyncAITTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -76,8 +68,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -97,7 +89,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -105,14 +96,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -120,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -1,169 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import datetime
|
||||
import os
|
||||
import wave
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.filters.aic_filter import AICFilter
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.audio.audio_buffer_processor import AudioBufferProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# Create audio buffer processor so we can hear the audio fitler results.
|
||||
audiobuffer = AudioBufferProcessor(
|
||||
num_channels=2, # 1 for mono, 2 for stereo (user left, bot right)
|
||||
enable_turn_audio=False, # Enable per-turn audio recording
|
||||
)
|
||||
|
||||
|
||||
def _create_aic_filter() -> AICFilter:
|
||||
license_key = os.getenv("AICOUSTICS_LICENSE_KEY", "")
|
||||
|
||||
return AICFilter(
|
||||
license_key=license_key,
|
||||
enhancement_level=1.0,
|
||||
)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
audio_in_filter=_create_aic_filter(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
audio_in_filter=_create_aic_filter(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
audio_in_filter=_create_aic_filter(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
audiobuffer, # write audio data to a file
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
await audiobuffer.start_recording()
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@audiobuffer.event_handler("on_audio_data")
|
||||
async def on_audio_data(buffer, audio, sample_rate, num_channels):
|
||||
# Save or process the composite audio
|
||||
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
filename = f"./conversation_{timestamp}.wav"
|
||||
|
||||
# Create the WAV file
|
||||
with wave.open(filename, "wb") as wf:
|
||||
wf.setnchannels(num_channels)
|
||||
wf.setsampwidth(2) # 16-bit audio
|
||||
wf.setframerate(sample_rate)
|
||||
wf.writeframes(audio)
|
||||
|
||||
logger.info(f"Saved recording to {filename}")
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -15,24 +15,21 @@ from langchain_core.runnables.history import RunnableWithMessageHistory
|
||||
from langchain_openai import ChatOpenAI
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMMessagesUpdateFrame
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator,
|
||||
LLMUserResponseAggregator,
|
||||
)
|
||||
from pipecat.processors.frameworks.langchain import LangchainProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -53,25 +50,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -101,18 +95,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
)
|
||||
lc = LangchainProcessor(history_chain)
|
||||
|
||||
context = LLMContext()
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
tma_in = LLMUserResponseAggregator()
|
||||
tma_out = LLMAssistantResponseAggregator()
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
tma_in, # User responses
|
||||
lc, # Langchain
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
tma_out, # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
@@ -122,25 +116,24 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
# An `LLMContextFrame` will be picked up by the LangchainProcessor using
|
||||
# the `LLMMessagesFrame` will be picked up by the LangchainProcessor using
|
||||
# only the content of the last message to inject it in the prompt defined
|
||||
# above. So no role is required here.
|
||||
messages = [({"content": "Please briefly introduce yourself to the user."})]
|
||||
await task.queue_frames([LLMMessagesUpdateFrame(messages, run_llm=True)])
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -148,7 +141,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -12,24 +12,23 @@ from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import (
|
||||
InterruptionFrame,
|
||||
LLMRunFrame,
|
||||
BotInterruptionFrame,
|
||||
StopInterruptionFrame,
|
||||
UserStartedSpeakingFrame,
|
||||
UserStoppedSpeakingFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -53,7 +52,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(
|
||||
@@ -72,8 +71,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -93,30 +92,29 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@stt.event_handler("on_speech_started")
|
||||
async def on_speech_started(stt, *args, **kwargs):
|
||||
await task.queue_frames([InterruptionFrame(), UserStartedSpeakingFrame()])
|
||||
await task.queue_frames([BotInterruptionFrame(), UserStartedSpeakingFrame()])
|
||||
|
||||
@stt.event_handler("on_utterance_end")
|
||||
async def on_utterance_end(stt, *args, **kwargs):
|
||||
await task.queue_frames([UserStoppedSpeakingFrame()])
|
||||
await task.queue_frames([StopInterruptionFrame(), UserStoppedSpeakingFrame()])
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -124,7 +122,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -73,8 +65,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -94,7 +86,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -102,14 +93,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -117,7 +108,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,25 +11,19 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -41,33 +35,27 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = ElevenLabsSTTService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
aiohttp_session=session,
|
||||
)
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = ElevenLabsHttpTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
||||
@@ -84,8 +72,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -105,7 +93,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -113,14 +100,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -128,7 +115,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -76,8 +68,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -97,7 +89,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -105,14 +96,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -120,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.playht.tts import PlayHTHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -76,8 +68,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -97,7 +89,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -105,14 +96,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -120,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,16 +10,11 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
@@ -27,8 +22,8 @@ from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.playht.tts import PlayHTTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -78,8 +70,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -99,7 +91,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -107,14 +98,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -122,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.azure.llm import AzureLLMService
|
||||
from pipecat.services.azure.stt import AzureSTTService
|
||||
from pipecat.services.azure.tts import AzureTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AzureSTTService(
|
||||
@@ -82,8 +74,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -103,7 +95,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -111,14 +102,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -126,7 +117,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.openai.stt import OpenAISTTService
|
||||
from pipecat.services.openai.tts import OpenAITTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = OpenAISTTService(
|
||||
@@ -76,8 +68,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -98,7 +90,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -106,14 +97,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -121,7 +112,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,24 +11,19 @@ import time
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openpipe.llm import OpenPipeLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -81,8 +73,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -102,7 +94,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -110,14 +101,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -125,7 +116,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,24 +11,19 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.xtts.tts import XTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -79,8 +71,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -100,7 +92,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -108,14 +99,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -123,7 +114,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,16 +10,11 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
@@ -28,8 +23,8 @@ from pipecat.services.gladia.stt import GladiaSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -40,30 +35,26 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GladiaSTTService(
|
||||
api_key=os.getenv("GLADIA_API_KEY", ""),
|
||||
region=os.getenv("GLADIA_REGION"),
|
||||
params=GladiaInputParams(
|
||||
language_config=LanguageConfig(
|
||||
languages=[Language.EN],
|
||||
@@ -85,8 +76,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -106,7 +97,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -114,21 +104,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.lmnt.tts import LmntTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -72,8 +64,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -93,7 +85,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -101,14 +92,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -116,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,25 +10,20 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.groq.llm import GroqLLMService
|
||||
from pipecat.services.groq.stt import GroqSTTService
|
||||
from pipecat.services.groq.tts import GroqTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"))
|
||||
@@ -75,8 +67,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(
|
||||
context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
|
||||
)
|
||||
|
||||
@@ -98,7 +90,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -106,14 +97,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -121,7 +112,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -1,177 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesAppendFrame, LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frameworks.strands_agents import StrandsAgentsProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.aws.stt import AWSTranscribeSTTService
|
||||
from pipecat.services.aws.tts import AWSPollyTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
# Strands agent setup
|
||||
try:
|
||||
from strands import Agent, tool
|
||||
from strands.models import BedrockModel
|
||||
except ImportError:
|
||||
logger.warning("Strands not installed. Please install with: pip install strands-agents")
|
||||
Agent = None
|
||||
BedrockModel = None
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def build_agent(model_id: str, max_tokens: int):
|
||||
"""Create and configure a Strands agent for NAB customer service coaching.
|
||||
|
||||
Args:
|
||||
model_id: The AWS Bedrock model ID to use
|
||||
max_tokens: Maximum tokens for the model
|
||||
|
||||
Returns:
|
||||
Configured Strands Agent
|
||||
"""
|
||||
|
||||
@tool
|
||||
def check_weather(location: str) -> str:
|
||||
if location.lower() == "san francisco":
|
||||
return "The weather in San Francisco is sunny and 30 degrees."
|
||||
elif location.lower() == "sydney":
|
||||
return "The weather in Sydney is cloudy and 20 degrees."
|
||||
else:
|
||||
return "I'm not sure about the weather in that location."
|
||||
|
||||
agent = Agent(
|
||||
model=BedrockModel(
|
||||
model_id=model_id,
|
||||
max_tokens=max_tokens,
|
||||
),
|
||||
tools=[check_weather],
|
||||
system_prompt="You are a helpful assistant that can check the weather in a given location.",
|
||||
)
|
||||
|
||||
return agent
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AWSTranscribeSTTService()
|
||||
|
||||
tts = AWSPollyTTSService(
|
||||
region="us-west-2", # only specific regions support generative TTS
|
||||
voice_id="Joanna",
|
||||
params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
|
||||
)
|
||||
|
||||
# Create Strands agent processor
|
||||
try:
|
||||
agent = build_agent(model_id="us.anthropic.claude-3-5-haiku-20241022-v1:0", max_tokens=8000)
|
||||
llm = StrandsAgentsProcessor(agent=agent)
|
||||
logger.info("Successfully created Strands agent for NAB customer service coaching")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create Strands agent: {e}")
|
||||
raise ValueError(
|
||||
"Unable to create Strands processor. Please ensure you have properly "
|
||||
"installed strands-agents and configured your AWS credentials."
|
||||
)
|
||||
|
||||
# Setup context aggregators for message handling
|
||||
context = LLMContext()
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # Speech-to-text
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # Strands Agents processor
|
||||
tts, # Text-to-speech
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames(
|
||||
[
|
||||
LLMMessagesAppendFrame(
|
||||
messages=[
|
||||
{
|
||||
"role": "user",
|
||||
"content": f"Greet the user and introduce yourself.",
|
||||
}
|
||||
],
|
||||
run_llm=True,
|
||||
)
|
||||
]
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -8,24 +8,19 @@
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.aws.llm import AWSBedrockLLMService
|
||||
from pipecat.services.aws.stt import AWSTranscribeSTTService
|
||||
from pipecat.services.aws.tts import AWSPollyTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -36,25 +31,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AWSTranscribeSTTService()
|
||||
@@ -78,8 +70,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -99,7 +91,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -107,14 +98,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "user", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -122,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -1,171 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""
|
||||
A conversational AI bot using Gemini for both LLM and TTS.
|
||||
|
||||
This example demonstrates how to use Gemini's TTS capabilities with the new
|
||||
GeminiTTSService, which uses Gemini's TTS-specific models instead of Google Cloud TTS.
|
||||
|
||||
Features showcased:
|
||||
- Gemini LLM for conversation
|
||||
- Gemini TTS with natural voice control
|
||||
- Support for different voice personalities
|
||||
- Style and tone control through natural language prompts
|
||||
|
||||
Run with:
|
||||
python examples/foundational/gemini-tts.py
|
||||
|
||||
Make sure to set your environment variables:
|
||||
export GOOGLE_API_KEY=your_api_key_here
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.services.google.stt import GoogleSTTService
|
||||
from pipecat.services.google.tts import GeminiTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot with Gemini TTS")
|
||||
|
||||
stt = GoogleSTTService(
|
||||
params=GoogleSTTService.InputParams(languages=Language.EN_US),
|
||||
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
|
||||
)
|
||||
|
||||
tts = GeminiTTSService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
model="gemini-2.5-flash-preview-tts", # TTS-specific model
|
||||
voice_id="Charon",
|
||||
params=GeminiTTSService.InputParams(language=Language.EN_US),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
model="gemini-2.5-flash",
|
||||
)
|
||||
|
||||
# System message that instructs the AI on how to speak
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": """You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
|
||||
|
||||
IMPORTANT: Since you're using Gemini TTS which supports natural voice control, you can include speaking instructions in your responses. For example:
|
||||
- "Say cheerfully: Welcome to our conversation!"
|
||||
- "Read this in a calm, professional tone: Here are the details you requested."
|
||||
- "Speak in an excited whisper: I have some great news to share!"
|
||||
- "Say slowly and clearly: Let me explain this step by step."
|
||||
|
||||
Feel free to use natural language instructions to control your voice style, tone, pace, and emotion. The TTS system will interpret these instructions and adjust the speech accordingly.
|
||||
|
||||
Your output will be converted to audio, so avoid special characters in your answers. Respond to what the user said in a creative and helpful way.""",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # Gemini TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation with a styled introduction
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": "Say cheerfully and warmly: Hello! I'm your AI assistant powered by Gemini's new TTS technology. I can speak with different voices, tones, and styles. How can I help you today?",
|
||||
}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -10,16 +10,11 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
@@ -27,8 +22,8 @@ from pipecat.services.google.stt import GoogleSTTService
|
||||
from pipecat.services.google.tts import GoogleTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GoogleSTTService(
|
||||
@@ -85,8 +77,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -106,7 +98,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -114,14 +105,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -129,7 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.assemblyai.stt import AssemblyAISTTService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AssemblyAISTTService(
|
||||
@@ -78,8 +70,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -99,7 +91,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -107,14 +98,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -122,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,24 +11,19 @@ from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.filters.krisp_filter import KrispFilter
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,28 +34,25 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
audio_in_filter=KrispFilter(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
audio_in_filter=KrispFilter(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
audio_in_filter=KrispFilter(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -76,8 +68,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -97,7 +89,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -105,14 +96,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -120,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,24 +11,19 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.rime.tts import RimeHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -40,25 +35,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -81,8 +73,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -102,7 +94,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -110,14 +101,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -125,7 +116,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.rime.tts import RimeTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -75,8 +67,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -96,7 +88,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -104,14 +95,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -119,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.nim.llm import NimLLMService
|
||||
from pipecat.services.riva.stt import RivaSTTService
|
||||
from pipecat.services.riva.tts import RivaTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = RivaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
@@ -72,8 +64,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -93,7 +85,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -101,14 +92,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -116,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -12,17 +12,13 @@ from dotenv import load_dotenv
|
||||
from google.genai.types import Content, Part
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
InputAudioRawFrame,
|
||||
InterruptionFrame,
|
||||
LLMFullResponseEndFrame,
|
||||
LLMFullResponseStartFrame,
|
||||
LLMRunFrame,
|
||||
StartInterruptionFrame,
|
||||
TextFrame,
|
||||
TranscriptionFrame,
|
||||
UserStartedSpeakingFrame,
|
||||
@@ -31,8 +27,7 @@ from pipecat.frames.frames import (
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.processors.frame_processor import FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -40,8 +35,8 @@ from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.services.google.tts import GoogleTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -97,8 +92,9 @@ class UserAudioCollector(FrameProcessor):
|
||||
elif isinstance(frame, UserStoppedSpeakingFrame):
|
||||
self._user_speaking = False
|
||||
self._context.add_audio_frames_message(audio_frames=self._audio_frames)
|
||||
await self._user_context_aggregator.push_frame(LLMRunFrame())
|
||||
|
||||
await self._user_context_aggregator.push_frame(
|
||||
self._user_context_aggregator.get_context_frame()
|
||||
)
|
||||
elif isinstance(frame, InputAudioRawFrame):
|
||||
if self._user_speaking:
|
||||
self._audio_frames.append(frame)
|
||||
@@ -154,7 +150,7 @@ class TranscriptExtractor(FrameProcessor):
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
class TranscriptionContextFixup(FrameProcessor):
|
||||
class TanscriptionContextFixup(FrameProcessor):
|
||||
def __init__(self, context):
|
||||
super().__init__()
|
||||
self._context = context
|
||||
@@ -185,7 +181,9 @@ class TranscriptionContextFixup(FrameProcessor):
|
||||
|
||||
if isinstance(frame, MagicDemoTranscriptionFrame):
|
||||
self._transcript = frame.text
|
||||
elif isinstance(frame, LLMFullResponseEndFrame) or isinstance(frame, InterruptionFrame):
|
||||
elif isinstance(frame, LLMFullResponseEndFrame) or isinstance(
|
||||
frame, StartInterruptionFrame
|
||||
):
|
||||
self.swap_user_audio()
|
||||
self.add_transcript_back_to_inference_output()
|
||||
self._transcript = ""
|
||||
@@ -200,25 +198,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
llm = GoogleLLMService(
|
||||
@@ -245,11 +240,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
audio_collector = UserAudioCollector(context, context_aggregator.user())
|
||||
pull_transcript_out_of_llm_output = TranscriptExtractor(context)
|
||||
fixup_context_messages = TranscriptionContextFixup(context)
|
||||
fixup_context_messages = TanscriptionContextFixup(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -271,7 +266,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -279,14 +273,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -294,7 +288,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.fish.tts import FishAudioTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -76,8 +68,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -97,7 +89,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -105,14 +96,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -120,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,10 +10,7 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
@@ -22,8 +19,8 @@ from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.ultravox.stt import UltravoxSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -47,25 +44,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
@@ -88,7 +82,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -100,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -108,7 +101,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,24 +11,19 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -40,25 +35,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -80,8 +72,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -101,7 +93,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -109,14 +100,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -124,7 +115,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.neuphonic.tts import NeuphonicTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +33,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -75,8 +67,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -96,7 +88,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -104,14 +95,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -119,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,24 +10,19 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.fal.stt import FalSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -39,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = FalSTTService(
|
||||
@@ -78,8 +70,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -99,7 +91,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -107,14 +98,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -122,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -11,16 +11,11 @@ import sys
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
@@ -39,8 +34,7 @@ async def main():
|
||||
LocalAudioTransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -60,8 +54,8 @@ async def main():
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -84,7 +78,7 @@ async def main():
|
||||
)
|
||||
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
|
||||
@@ -11,16 +11,11 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
@@ -28,8 +23,8 @@ from pipecat.services.minimax.tts import MiniMaxHttpTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -41,25 +36,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
@@ -82,8 +74,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -103,7 +95,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -111,14 +102,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -126,7 +117,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -1,133 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.sarvam.tts import SarvamHttpTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = SarvamHttpTTSService(
|
||||
api_key=os.getenv("SARVAM_API_KEY"),
|
||||
aiohttp_session=session,
|
||||
params=SarvamHttpTTSService.InputParams(language=Language.EN),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -5,31 +5,26 @@
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame, TTSUpdateSettingsFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.sarvam.tts import SarvamTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -41,91 +36,87 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = SarvamTTSService(
|
||||
api_key=os.getenv("SARVAM_API_KEY"),
|
||||
model="bulbul:v2",
|
||||
voice_id="manisha",
|
||||
)
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
tts = SarvamTTSService(
|
||||
api_key=os.getenv("SARVAM_API_KEY"),
|
||||
aiohttp_session=session,
|
||||
params=SarvamTTSService.InputParams(language=Language.EN),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
# Optionally, you can wait for 30 seconds and then change the voice.
|
||||
# await asyncio.sleep(30)
|
||||
# await task.queue_frame(TTSUpdateSettingsFrame(settings={"voice": "anushka"}))
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
await runner.run(task)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -6,16 +6,14 @@ from typing import Tuple
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMContextFrame, TextFrame
|
||||
from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.processors.aggregators import SentenceAggregator
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.daily import configure
|
||||
from pipecat.services.azure import AzureLLMService, AzureTTSService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.fal import FalImageGenService
|
||||
from pipecat.transports.daily.transport import DailyTransport
|
||||
from pipecat.transports.services.daily import DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -81,7 +79,7 @@ async def main():
|
||||
sentence_aggregator = SentenceAggregator()
|
||||
pipeline = Pipeline([llm, sentence_aggregator, tts1], source_queue, sink_queue)
|
||||
|
||||
await source_queue.put(LLMContextFrame(LLMContext(messages)))
|
||||
await source_queue.put(LLMMessagesFrame(messages))
|
||||
await source_queue.put(EndFrame())
|
||||
await pipeline.run_pipeline()
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -72,7 +72,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
pipeline = Pipeline([transport.input(), MirrorProcessor(), transport.output()])
|
||||
@@ -80,7 +80,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -92,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -100,7 +99,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -24,8 +24,8 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport, maybe_capture_participant_camera
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -75,7 +75,7 @@ transport_params = {
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tk_root = tk.Tk()
|
||||
@@ -97,7 +97,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
async def run_tk():
|
||||
@@ -116,7 +115,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await asyncio.gather(runner.run(task), run_tk())
|
||||
|
||||
@@ -124,7 +123,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -9,16 +9,12 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.processors.filters.wake_check_filter import WakeCheckFilter
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -26,8 +22,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -38,25 +34,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -77,8 +70,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -99,7 +92,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
@@ -113,7 +105,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -121,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -10,13 +10,9 @@ import wave
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
LLMFullResponseEndFrame,
|
||||
OutputAudioRawFrame,
|
||||
TTSSpeakFrame,
|
||||
@@ -24,8 +20,10 @@ from pipecat.frames.frames import (
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.openai_llm_context import (
|
||||
OpenAILLMContext,
|
||||
OpenAILLMContextFrame,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.processors.logger import FrameLogger
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
@@ -34,8 +32,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -73,7 +71,7 @@ class InboundSoundEffectWrapper(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, LLMContextFrame):
|
||||
if isinstance(frame, OpenAILLMContextFrame):
|
||||
await self.push_frame(sounds["ding2.wav"])
|
||||
# In case anything else downstream needs it
|
||||
await self.push_frame(frame, direction)
|
||||
@@ -88,25 +86,22 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def run_bot(transport: BaseTransport):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
@@ -125,8 +120,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
out_sound = OutboundSoundEffectWrapper()
|
||||
in_sound = InboundSoundEffectWrapper()
|
||||
fl = FrameLogger("LLM Out")
|
||||
@@ -148,10 +143,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
@@ -165,7 +157,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -173,7 +165,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await run_bot(transport)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user