Compare commits
1 Commits
aleix/fram
...
hush/usage
| Author | SHA1 | Date | |
|---|---|---|---|
|
cb6e86e69f |
14
.github/workflows/build.yaml
vendored
14
.github/workflows/build.yaml
vendored
@@ -21,20 +21,20 @@ 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 3.12
|
||||
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
|
||||
- name: Build project
|
||||
run: uv build
|
||||
|
||||
|
||||
- name: Install project in editable mode
|
||||
run: uv pip install --editable .
|
||||
run: uv pip install --editable .
|
||||
14
.github/workflows/format.yaml
vendored
14
.github/workflows/format.yaml
vendored
@@ -22,22 +22,22 @@ 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
|
||||
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
|
||||
- name: Ruff formatter
|
||||
id: ruff-format
|
||||
run: uv run ruff format --diff
|
||||
|
||||
|
||||
- name: Ruff linter (all rules)
|
||||
id: ruff-check
|
||||
run: uv run ruff check
|
||||
run: uv run ruff check
|
||||
174
.github/workflows/generate-changelog.yml
vendored
174
.github/workflows/generate-changelog.yml
vendored
@@ -1,174 +0,0 @@
|
||||
name: Generate Changelog for Release
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Release version (e.g., 0.0.97)"
|
||||
required: true
|
||||
type: string
|
||||
date:
|
||||
description: "Release date (YYYY-MM-DD format, defaults to today)"
|
||||
required: false
|
||||
type: string
|
||||
default: ""
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
generate-changelog:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
with:
|
||||
enable-cache: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
uv sync --group dev
|
||||
|
||||
- name: Set release date
|
||||
id: set_date
|
||||
run: |
|
||||
if [ -z "${{ inputs.date }}" ]; then
|
||||
RELEASE_DATE=$(date +%Y-%m-%d)
|
||||
echo "Using today's date: $RELEASE_DATE"
|
||||
else
|
||||
RELEASE_DATE="${{ inputs.date }}"
|
||||
echo "Using provided date: $RELEASE_DATE"
|
||||
fi
|
||||
echo "release_date=$RELEASE_DATE" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Validate inputs
|
||||
run: |
|
||||
# Validate version format (basic check)
|
||||
if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+.*$ ]]; then
|
||||
echo "Error: Version must be in format X.Y.Z (e.g., 0.0.97)"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate date format if provided
|
||||
if [ -n "${{ inputs.date }}" ]; then
|
||||
if ! date -d "${{ inputs.date }}" >/dev/null 2>&1; then
|
||||
# Try macOS date format
|
||||
if ! date -j -f "%Y-%m-%d" "${{ inputs.date }}" >/dev/null 2>&1; then
|
||||
echo "Error: Date must be in YYYY-MM-DD format (e.g., 2025-12-04)"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
- name: Check for changelog fragments
|
||||
id: check_fragments
|
||||
run: |
|
||||
FRAGMENT_COUNT=$(find changelog -name "*.md" ! -name "_template.md.j2" | wc -l | tr -d ' ')
|
||||
echo "fragment_count=$FRAGMENT_COUNT" >> $GITHUB_OUTPUT
|
||||
|
||||
if [ "$FRAGMENT_COUNT" -eq "0" ]; then
|
||||
echo "❌ Error: No changelog fragments found in changelog/"
|
||||
echo ""
|
||||
echo "Cannot create a release without changelog entries."
|
||||
echo "Add changelog fragments to the changelog/ directory (e.g., 1234.added.md) and try again."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate fragment types
|
||||
VALID_TYPES="added changed deprecated removed fixed security other"
|
||||
INVALID_FRAGMENTS=""
|
||||
|
||||
for file in changelog/*.md; do
|
||||
# Skip template
|
||||
if [[ "$file" == "changelog/_template.md.j2" ]]; then
|
||||
continue
|
||||
fi
|
||||
|
||||
# Extract type from filename (e.g., 1234.added.md -> added)
|
||||
filename=$(basename "$file")
|
||||
# Handle both 1234.added.md and 1234.added.2.md patterns
|
||||
type=$(echo "$filename" | sed -E 's/^[0-9]+\.([a-z]+)(\.[0-9]+)?\.md$/\1/')
|
||||
|
||||
# Check if type is valid
|
||||
if ! echo "$VALID_TYPES" | grep -wq "$type"; then
|
||||
INVALID_FRAGMENTS="$INVALID_FRAGMENTS\n - $filename (type: '$type')"
|
||||
fi
|
||||
done
|
||||
|
||||
if [ -n "$INVALID_FRAGMENTS" ]; then
|
||||
echo "❌ Error: Invalid changelog fragment types found:"
|
||||
echo -e "$INVALID_FRAGMENTS"
|
||||
echo ""
|
||||
echo "Valid types are: $VALID_TYPES"
|
||||
echo "Example: 1234.added.md, 5678.fixed.md"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Found $FRAGMENT_COUNT changelog fragment(s)"
|
||||
echo "has_fragments=true" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Preview changelog
|
||||
run: |
|
||||
echo "## Preview of changelog for version ${{ inputs.version }}"
|
||||
echo ""
|
||||
uv run towncrier build --draft --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}"
|
||||
|
||||
- name: Build changelog
|
||||
run: |
|
||||
uv run towncrier build --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}" --yes
|
||||
|
||||
- name: Create Pull Request
|
||||
uses: peter-evans/create-pull-request@v7
|
||||
with:
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
commit-message: "Update changelog for version ${{ inputs.version }}"
|
||||
title: "Release ${{ inputs.version }} - Changelog Update"
|
||||
body: |
|
||||
## Changelog Update for Release ${{ inputs.version }}
|
||||
|
||||
This PR updates the CHANGELOG.md with all changes for version **${{ inputs.version }}**.
|
||||
|
||||
### Summary
|
||||
- **Version:** ${{ inputs.version }}
|
||||
- **Date:** ${{ steps.set_date.outputs.release_date }}
|
||||
- **Fragments processed:** ${{ steps.check_fragments.outputs.fragment_count }}
|
||||
|
||||
### What this PR does
|
||||
- ✅ Adds new release section to CHANGELOG.md
|
||||
- ✅ Removes processed changelog fragments
|
||||
- ✅ Ready to merge for release
|
||||
|
||||
### Next Steps
|
||||
1. Review the changelog entries below
|
||||
2. Make any necessary edits to CHANGELOG.md if needed
|
||||
3. Merge this PR
|
||||
4. Continue with your release process
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>📋 Preview of changes</summary>
|
||||
|
||||
The changelog has been updated with entries from the following fragments:
|
||||
|
||||
```bash
|
||||
${{ steps.check_fragments.outputs.fragment_count }} fragments processed
|
||||
```
|
||||
|
||||
</details>
|
||||
branch: changelog-${{ inputs.version }}
|
||||
delete-branch: true
|
||||
labels: |
|
||||
changelog
|
||||
release
|
||||
1
.github/workflows/python-compatibility.yaml
vendored
1
.github/workflows/python-compatibility.yaml
vendored
@@ -50,6 +50,7 @@ jobs:
|
||||
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
|
||||
|
||||
@@ -11,7 +11,7 @@ build:
|
||||
jobs:
|
||||
post_install:
|
||||
- pip install uv
|
||||
- UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
- UV_PROJECT_ENVIRONMENT=$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
|
||||
|
||||
sphinx:
|
||||
configuration: docs/api/conf.py
|
||||
|
||||
1287
CHANGELOG.md
1287
CHANGELOG.md
File diff suppressed because it is too large
Load Diff
@@ -79,7 +79,7 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [NvidiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/nvidia/stt.py)
|
||||
- [RivaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/riva/stt.py)
|
||||
- [FalSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/stt.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
106
CONTRIBUTING.md
106
CONTRIBUTING.md
@@ -17,122 +17,24 @@ We welcome contributions of all kinds! Your help is appreciated. Follow these st
|
||||
git checkout -b your-branch-name
|
||||
```
|
||||
4. **Make your changes**: Edit or add files as necessary.
|
||||
5. **Add a changelog entry**: Create a changelog fragment file (see [Changelog Entries](#changelog-entries) below).
|
||||
6. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
|
||||
7. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
|
||||
5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
|
||||
6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
|
||||
|
||||
```bash
|
||||
git commit -m "Description of your changes"
|
||||
```
|
||||
|
||||
8. **Push your changes**: Push your branch to your forked repository.
|
||||
7. **Push your changes**: Push your branch to your forked repository.
|
||||
|
||||
```bash
|
||||
git push origin your-branch-name
|
||||
```
|
||||
|
||||
9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
|
||||
8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
|
||||
> Important: Describe the changes you've made clearly!
|
||||
|
||||
Our maintainers will review your PR, and once everything is good, your contributions will be merged!
|
||||
|
||||
## Changelog Entries
|
||||
|
||||
Every pull request that makes a user-facing change should include a changelog entry. We use a changelog fragment system to avoid merge conflicts.
|
||||
|
||||
### Creating a Changelog Fragment
|
||||
|
||||
1. Create a new file in the `changelog/` directory with this naming pattern:
|
||||
|
||||
```
|
||||
<PR_number>.<type>.md
|
||||
```
|
||||
|
||||
2. Choose the appropriate type:
|
||||
|
||||
- `added.md` - New features
|
||||
- `changed.md` - Changes in existing functionality
|
||||
- `deprecated.md` - Soon-to-be removed features
|
||||
- `removed.md` - Removed features
|
||||
- `fixed.md` - Bug fixes
|
||||
- `security.md` - Security fixes
|
||||
- `other.md` - Other changes (documentation, dependencies, etc.)
|
||||
|
||||
3. Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
|
||||
|
||||
**Example files:**
|
||||
|
||||
`changelog/1234.added.md`:
|
||||
|
||||
```markdown
|
||||
- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
|
||||
```
|
||||
|
||||
`changelog/5678.fixed.md`:
|
||||
|
||||
```markdown
|
||||
- Fixed an issue where audio frames were dropped during high-load scenarios.
|
||||
```
|
||||
|
||||
**For entries with nested bullets:**
|
||||
|
||||
`changelog/1234.changed.md`:
|
||||
|
||||
```markdown
|
||||
- Updated service configuration:
|
||||
|
||||
- Changed default timeout to 30 seconds
|
||||
- Added retry logic for failed connections
|
||||
```
|
||||
|
||||
### Multiple Changes in One PR
|
||||
|
||||
**Different types of changes:** Create separate fragment files for each type:
|
||||
|
||||
```
|
||||
changelog/1234.added.md
|
||||
changelog/1234.fixed.md
|
||||
```
|
||||
|
||||
**Multiple changes of the same type:** Create numbered fragment files:
|
||||
|
||||
```
|
||||
changelog/1234.changed.md
|
||||
changelog/1234.changed.2.md
|
||||
```
|
||||
|
||||
**Related changes:** Use nested bullets in a single fragment:
|
||||
|
||||
```markdown
|
||||
- Updated service configuration:
|
||||
|
||||
- Changed default timeout to 30 seconds
|
||||
- Added retry logic for failed connections
|
||||
```
|
||||
|
||||
**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
|
||||
|
||||
### Preview Your Changes
|
||||
|
||||
To see what your changelog entry will look like:
|
||||
|
||||
```bash
|
||||
towncrier build --draft --version Unreleased
|
||||
```
|
||||
|
||||
This won't modify any files, just show you a preview.
|
||||
|
||||
### When to Skip Changelog Entries
|
||||
|
||||
You can skip adding a changelog entry for:
|
||||
|
||||
- Documentation-only changes
|
||||
- Internal refactoring with no user-facing impact
|
||||
- Test-only changes
|
||||
- CI/build configuration changes
|
||||
|
||||
If you're unsure whether your change needs a changelog entry, ask in your PR!
|
||||
|
||||
## Dependency Management
|
||||
|
||||
This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.
|
||||
|
||||
34
README.md
34
README.md
@@ -3,6 +3,7 @@
|
||||
</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://getmanta.ai/pipecat)
|
||||
|
||||
# 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
|
||||
|
||||
@@ -43,10 +44,6 @@ Looking to build structured conversations? Check out [Pipecat Flows](https://git
|
||||
|
||||
Want to build beautiful and engaging experiences? Checkout the [Voice UI Kit](https://github.com/pipecat-ai/voice-ui-kit), a collection of components, hooks and templates for building voice AI applications quickly.
|
||||
|
||||
### 🛠️ Create and deploy projects
|
||||
|
||||
Create a new project in under a minute with the [Pipecat CLI](https://github.com/pipecat-ai/pipecat-cli). Then use the CLI to monitor and deploy your agent to production.
|
||||
|
||||
### 🔍 Debugging
|
||||
|
||||
Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
|
||||
@@ -66,24 +63,24 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
|
||||
<br/>
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/12-describe-video.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/assets/moondream.png" width="400" /></a>
|
||||
<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>
|
||||
|
||||
## 🧩 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), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [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), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [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) |
|
||||
| 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), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [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), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [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), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), |
|
||||
| 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) |
|
||||
| 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) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
| 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) |
|
||||
| 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), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [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) |
|
||||
| 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) |
|
||||
| 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)
|
||||
|
||||
@@ -153,6 +150,7 @@ You can get started with Pipecat running on your local machine, then move your a
|
||||
--no-extra gstreamer \
|
||||
--no-extra krisp \
|
||||
--no-extra local \
|
||||
--no-extra ultravox # (ultravox not fully supported on macOS)
|
||||
```
|
||||
|
||||
3. Install the git pre-commit hooks:
|
||||
|
||||
@@ -1,42 +0,0 @@
|
||||
- Introducing user turn strategies. User turn strategies indicate when the user turn starts or stops. In conversational agents, these are often referred to as start/stop speaking or turn-taking plans or policies.
|
||||
|
||||
User turn start strategies indicate when the user starts speaking (e.g. using VAD events or when a user says one or more words).
|
||||
|
||||
User turn stop strategies indicate when the user stops speaking (e.g. using an end-of-turn detection model or by observing incoming transcriptions).
|
||||
|
||||
A list of strategies can be specified for both strategies; strategies are evaluated in order until one evaluates to true.
|
||||
|
||||
Available user turn start strategies:
|
||||
- VADUserTurnStartStrategy
|
||||
- TranscriptionUserTurnStartStrategy
|
||||
- MinWordsUserTurnStartStrategy
|
||||
- ExternalUserTurnStartStrategy
|
||||
|
||||
Available user turn stop strategies:
|
||||
- TranscriptionUserTurnStopStrategy
|
||||
- TurnAnalyzerUserTurnStopStrategy
|
||||
- ExternalUserTurnStopStrategy
|
||||
|
||||
The default strategies are:
|
||||
|
||||
- start: [VADUserTurnStartStrategy, TranscriptionUserTurnStartStrategy]
|
||||
- stop: [TranscriptionUserTurnStopStrategy]
|
||||
|
||||
Turn strategies are configured when setting up `LLMContextAggregatorPair`. For example:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams())
|
||||
)
|
||||
],
|
||||
)
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
In order to use the user turn strategies you must update to the new universal `LLMContext` and `LLMContextAggregatorPair`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ `TransportParams.turn_analyzer` is deprecated and might result in unexpected behavior, use `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `FrameProcessor.interruption_strategies` is deprecated, use `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `EmulateUserStartedSpeakingFrame` and `EmulateUserStoppedSpeakingFrame` frames are deprecated.
|
||||
@@ -1 +0,0 @@
|
||||
- Deprecated the `emulated` field in the `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames.
|
||||
@@ -1 +0,0 @@
|
||||
- The `LLMUserAggregatorParams` and `LLMAssistantAggregatorParams` classes in `pipecat.processors.aggregators.llm_response` are now deprecated. Use the new universal `LLMContext` and `LLMContextAggregatorPair` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `pipecat.audio.interruptions.MinWordsInterruptionStrategy` is deprecated. Use `pipecat.turns.user_start.MinWordsUserTurnStartStrategy` with `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `RNNoiseFilter` for real-time noise suppression using RNNoise neural network via pyrnnoise library.
|
||||
@@ -1,15 +0,0 @@
|
||||
- Updated `SpeechmaticsSTTService` to use new Python Voice SDK with improved VAD,
|
||||
Smart Turn capabilities, and brings dramatic improvements to latency without
|
||||
any impact on accuracy. Use the `turn_detection_mode` parameter to control the
|
||||
endpointing of speech, with `TurnDetectionMode.EXTERNAL` (default),
|
||||
`TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`.
|
||||
```python
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
),
|
||||
)
|
||||
```
|
||||
@@ -1,4 +0,0 @@
|
||||
- For `SpeechmaticsSTTService`, the `end_of_utterance_mode` parameter is deprecated.
|
||||
Use the new `turn_detection_mode` parameter instead, with `TurnDetectionMode.EXTERNAL`,
|
||||
`TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`. The `enable_vad`
|
||||
parameter is also deprecated and is inferred from the `turn_detection_mode`.
|
||||
@@ -1,2 +0,0 @@
|
||||
- Improved error handling in `ElevenLabsRealtimeSTTService`
|
||||
- Fixed an issue in `ElevenLabsRealtimeSTTService` causing an infinite loop that blocks the process if the websocket disconnects due to an error
|
||||
@@ -1 +0,0 @@
|
||||
- `TranscriptionFrame` and `InterimTranscriptionFrame` produced by `DailyTransport` now include the transport source (i.e., the originating audio track).
|
||||
@@ -1 +0,0 @@
|
||||
- `daily-python` updated to 0.23.0.
|
||||
@@ -1,15 +0,0 @@
|
||||
- `OpenAILLMContext` and its associated things (context aggregators, etc.) are now deprecated in favor of the universal `LLMContext` and its associated things.
|
||||
|
||||
From the developer's point of view, switching to using `LLMContext` machinery will usually be a matter of going from this:
|
||||
|
||||
```python
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
```
|
||||
|
||||
To this:
|
||||
|
||||
```
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
```
|
||||
@@ -1,8 +0,0 @@
|
||||
- Added `GrokRealtimeLLMService` for xAI's Grok Voice Agent API with real-time voice conversations:
|
||||
|
||||
- Support for real-time audio streaming with WebSocket connection
|
||||
- Built-in server-side VAD (Voice Activity Detection)
|
||||
- Multiple voice options: Ara, Rex, Sal, Eve, Leo
|
||||
- Built-in tools support: web_search, x_search, file_search
|
||||
- Custom function calling with standard Pipecat tools schema
|
||||
- Configurable audio formats (PCM at 8kHz-48kHz)
|
||||
@@ -1 +0,0 @@
|
||||
- Added an approximation of TTFB for Ultravox.
|
||||
@@ -1,5 +0,0 @@
|
||||
- Updates to Inworld TTS services:
|
||||
|
||||
- Improved `InworldTTSService`'s websocket implementation to better flush and
|
||||
close context to better handle long inputs.
|
||||
- Improved docstrings for `InworldTTSService` and `InworldHttpTTSService`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a new `AudioContextTTSService` to the TTS service base classes. The `AudioContextWordTTSService` now inherits from `AudioContextTTSService` and `WebsocketWordTTSService`.
|
||||
@@ -1,4 +0,0 @@
|
||||
- `LLMUserAggregator` now exposes the following events:
|
||||
- `on_user_turn_started`: triggered when a user turn starts
|
||||
- `on_user_turn_stopped`: triggered when a user turn ends
|
||||
- `on_user_turn_stop_timeout`: triggered when a user turn does not stop and times out
|
||||
@@ -1,29 +0,0 @@
|
||||
- Introducing user mute strategies. User mute strategies indicate when user input should be muted based on the current system state.
|
||||
|
||||
In conversational agents, user mute strategies are used to prevent user input from interrupting bot speech, tool execution, or other critical system operations.
|
||||
|
||||
A list of strategies can be specified; all strategies are evaluated for every frame so that each strategy can maintain its internal state. A user frame is muted if any of the configured strategies indicates it should be muted.
|
||||
|
||||
Available user mute strategies:
|
||||
|
||||
* `FirstSpeechUserMuteStrategy`
|
||||
* `MuteUntilFirstBotCompleteUserMuteStrategy`
|
||||
* `AlwaysUserMuteStrategy`
|
||||
* `FunctionCallUserMuteStrategy`
|
||||
|
||||
User mute strategies replace the legacy `STTMuteFilter` and provide a more flexible and composable approach to muting user input.
|
||||
|
||||
User mute strategies are configured when setting up the `LLMContextAggregatorPair`. For example:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_mute_strategies=[
|
||||
FirstSpeechUserMuteStrategy(),
|
||||
]
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
In order to use user mute strategies you should update to the new universal `LLMContext` and `LLMContextAggregatorPair`.
|
||||
@@ -1 +0,0 @@
|
||||
- `STTMuteFilter` is deprecated and will be removed in a future version. Use `LLMUserAggregator`'s new `user_mute_strategies` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a bug in `STTMuteFilter` where the user was not always muted during function calls, especially when there were multiple simultaneous calls.
|
||||
@@ -1 +0,0 @@
|
||||
- `FrameProcessor.interruptions_allowed` is now deprecated, use `LLMUserAggregator`'s new parameter `user_mute_strategies` instead.
|
||||
@@ -1,12 +0,0 @@
|
||||
- `PipelineParams.allow_interruptions` is now deprecated, use `LLMUserAggregator`'s new parameter `turn_start_strategies` instead. For example, to disable interruptions but still get user turns you can do:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
start=[TranscriptionUserTurnStartStrategy(enable_interruptions=False)],
|
||||
),
|
||||
),
|
||||
)
|
||||
```
|
||||
@@ -1 +0,0 @@
|
||||
- Added `use_ssl` parameter to `NvidiaSTTService`, `NvidiaSegmentedSTTService` and `NvidiaTTSService`.
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `DeepgramSTTService` to push user started/stopped speaking and interruption frames when `vad_enabled` is set to true. This centralizes the frames into the service, removing the need to have your application code handle Deepgram's events and push these frames.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `enable_interruptions` constructor argument to all user turn strategies. This tells the `LLMUserAggregator` to push or not push an `InterruptionFrame`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `52-live-transcription.py` foundational example demonstrating live transcription and translation from English to Spanish. In this example, the bot is not interruptible: as the user continues speaking, English transcriptions are queued, and the bot continuously translates and speaks each queued sentence in Spanish without being interrupted by new user speech.
|
||||
@@ -1 +0,0 @@
|
||||
- Frame processors can now push frames from the top of the pipeline using new methods `queue_task_frame()` and `queue_task_frames()`.
|
||||
@@ -1,16 +0,0 @@
|
||||
{% for section, _ in sections.items() %}
|
||||
{% if sections[section] %}
|
||||
{% for category, val in definitions.items() if category in sections[section]%}
|
||||
### {{ definitions[category]['name'] }}
|
||||
|
||||
{% for text, values in sections[section][category].items() %}
|
||||
{{ text }}
|
||||
(PR {{ values|join(', ') }})
|
||||
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
{% else %}
|
||||
No significant changes.
|
||||
|
||||
{% endif %}
|
||||
{% endfor %}
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
# Build docs using uv
|
||||
echo "Installing dependencies with uv..."
|
||||
uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
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
|
||||
@@ -24,4 +24,4 @@ if [ $? -eq 0 ]; then
|
||||
else
|
||||
echo "Documentation build failed!" >&2
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
@@ -61,6 +61,9 @@ autodoc_mock_imports = [
|
||||
# OpenCV - sometimes has import issues during docs build
|
||||
"cv2",
|
||||
# Heavy ML packages excluded from ReadTheDocs
|
||||
# ultravox dependencies
|
||||
"vllm",
|
||||
"vllm.engine.arg_utils",
|
||||
# local-smart-turn dependencies
|
||||
"coremltools",
|
||||
"coremltools.models",
|
||||
@@ -116,6 +119,7 @@ def import_core_modules():
|
||||
"pipecat.observers",
|
||||
"pipecat.runner",
|
||||
"pipecat.serializers",
|
||||
"pipecat.sync",
|
||||
"pipecat.transcriptions",
|
||||
"pipecat.utils",
|
||||
]
|
||||
|
||||
@@ -30,6 +30,7 @@ Quick Links
|
||||
Runner <api/pipecat.runner>
|
||||
Serializers <api/pipecat.serializers>
|
||||
Services <api/pipecat.services>
|
||||
Sync <api/pipecat.sync>
|
||||
Transcriptions <api/pipecat.transcriptions>
|
||||
Transports <api/pipecat.transports>
|
||||
Utils <api/pipecat.utils>
|
||||
Utils <api/pipecat.utils>
|
||||
190
env.example
190
env.example
@@ -4,9 +4,6 @@ AICOUSTICS_LICENSE_KEY=...
|
||||
# Anthropic
|
||||
ANTHROPIC_API_KEY=...
|
||||
|
||||
# Assembly AI
|
||||
ASSEMBLYAI_API_KEY=...
|
||||
|
||||
# Async
|
||||
ASYNCAI_API_KEY=...
|
||||
ASYNCAI_VOICE_ID=...
|
||||
@@ -24,19 +21,12 @@ AZURE_CHATGPT_API_KEY=...
|
||||
AZURE_CHATGPT_ENDPOINT=https://...
|
||||
AZURE_CHATGPT_MODEL=...
|
||||
|
||||
AZURE_REALTIME_API_KEY=...
|
||||
AZURE_REALTIME_BASE_URL=...
|
||||
|
||||
AZURE_DALLE_API_KEY=...
|
||||
AZURE_DALLE_ENDPOINT=https://...
|
||||
AZURE_DALLE_MODEL=...
|
||||
|
||||
# Cartesia
|
||||
CARTESIA_API_KEY=...
|
||||
CARTESIA_VOICE_ID=...
|
||||
|
||||
# Cerebras
|
||||
CEREBRAS_API_KEY=...
|
||||
|
||||
# Daily
|
||||
DAILY_API_KEY=...
|
||||
@@ -44,81 +34,43 @@ DAILY_SAMPLE_ROOM_URL=https://...
|
||||
|
||||
# Deepgram
|
||||
DEEPGRAM_API_KEY=...
|
||||
SAGEMAKER_ENDPOINT_NAME=...
|
||||
|
||||
# DeepSeek
|
||||
DEEPSEEK_API_KEY=...
|
||||
|
||||
# ElevenLabs
|
||||
ELEVENLABS_API_KEY=...
|
||||
ELEVENLABS_VOICE_ID=...
|
||||
|
||||
# Neuphonic
|
||||
NEUPHONIC_API_KEY=...
|
||||
|
||||
# Fal
|
||||
FAL_KEY=...
|
||||
|
||||
# Fireworks
|
||||
FIREWORKS_API_KEY=...
|
||||
|
||||
# Fish Audio
|
||||
FISH_API_KEY=...
|
||||
|
||||
# Gladia
|
||||
GLADIA_API_KEY=...
|
||||
GLADIA_REGION=...
|
||||
|
||||
# Google
|
||||
GOOGLE_API_KEY=...
|
||||
GOOGLE_VERTEX_TEST_CREDENTIALS=...
|
||||
GOOGLE_CLOUD_PROJECT_ID=...
|
||||
GOOGLE_CLOUD_LOCATION=...
|
||||
GOOGLE_TEST_CREDENTIALS=...
|
||||
|
||||
# Gradium
|
||||
GRAPDIUM_API_KEY=...
|
||||
|
||||
# Grok
|
||||
GROK_API_KEY=...
|
||||
|
||||
# Groq
|
||||
GROQ_API_KEY=...
|
||||
|
||||
# Heygen
|
||||
HEYGEN_API_KEY=...
|
||||
HEYGEN_LIVE_AVATAR_API_KEY=...
|
||||
GOOGLE_VERTEX_TEST_CREDENTIALS=...
|
||||
|
||||
# Hume
|
||||
HUME_API_KEY=...
|
||||
HUME_VOICE_ID=...
|
||||
|
||||
# Inworld
|
||||
INWORLD_API_KEY=...
|
||||
|
||||
# Krisp
|
||||
KRISP_MODEL_PATH=...
|
||||
|
||||
# Krisp Viva
|
||||
KRISP_VIVA_MODEL_PATH=...
|
||||
|
||||
# LiveKit
|
||||
LIVEKIT_API_KEY=...
|
||||
LIVEKIT_API_SECRET=...
|
||||
|
||||
# LMNT
|
||||
LMNT_API_KEY=...
|
||||
LMNT_VOICE_ID=...
|
||||
|
||||
# MiniMax
|
||||
MINIMAX_API_KEY=...
|
||||
MINIMAX_GROUP_ID=...
|
||||
# Perplexity
|
||||
PERPLEXITY_API_KEY=...
|
||||
|
||||
# Mistral
|
||||
MISTRAL_API_KEY=...
|
||||
|
||||
# Neuphonic
|
||||
NEUPHONIC_API_KEY=...
|
||||
|
||||
# NVIDIA
|
||||
NVIDIA_API_KEY=...
|
||||
# PlayHT
|
||||
PLAYHT_USER_ID=...
|
||||
PLAYHT_API_KEY=...
|
||||
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
@@ -126,76 +78,92 @@ OPENAI_API_KEY=...
|
||||
# OpenPipe
|
||||
OPENPIPE_API_KEY=...
|
||||
|
||||
# OpenRouter
|
||||
OPENROUTER_API_KEY=...
|
||||
|
||||
# Perplexity
|
||||
PERPLEXITY_API_KEY=...
|
||||
|
||||
# Picovoice Koala
|
||||
KOALA_ACCESS_KEY=...
|
||||
|
||||
# Piper
|
||||
PIPER_BASE_URL=...
|
||||
|
||||
# PlayHT
|
||||
PLAYHT_USER_ID=...
|
||||
PLAYHT_API_KEY=...
|
||||
|
||||
# Plivo
|
||||
PLIVO_AUTH_ID=...
|
||||
PLIVO_AUTH_TOKEN=...
|
||||
|
||||
# Qwen
|
||||
QWEN_API_KEY=...
|
||||
|
||||
# Rime
|
||||
RIME_API_KEY=...
|
||||
RIME_VOICE_ID=...
|
||||
|
||||
# SambaNova
|
||||
SAMBANOVA_API_KEY=...
|
||||
|
||||
# Sarvam AI
|
||||
SARVAM_API_KEY=...
|
||||
|
||||
# Sentry
|
||||
SENTRY_DSN=...
|
||||
# Tavus
|
||||
TAVUS_API_KEY=...
|
||||
TAVUS_REPLICA_ID=...
|
||||
TAVUS_PERSONA_ID=...
|
||||
|
||||
# Simli
|
||||
SIMLI_API_KEY=...
|
||||
SIMLI_FACE_ID=...
|
||||
|
||||
# Smart turn
|
||||
LOCAL_SMART_TURN_MODEL_PATH=...
|
||||
FAL_SMART_TURN_API_KEY=...
|
||||
# Krisp
|
||||
KRISP_MODEL_PATH=...
|
||||
|
||||
# Soniox
|
||||
SONIOX_API_KEY=...
|
||||
# Krisp Viva
|
||||
KRISP_VIVA_MODEL_PATH=...
|
||||
|
||||
# Speechmatics
|
||||
SPEECHMATICS_API_KEY=...
|
||||
# DeepSeek
|
||||
DEEPSEEK_API_KEY=...
|
||||
|
||||
# Tavus
|
||||
TAVUS_API_KEY=...
|
||||
TAVUS_REPLICA_ID=...
|
||||
# Groq
|
||||
GROQ_API_KEY=...
|
||||
|
||||
# Telnyx
|
||||
TELNYX_API_KEY=...
|
||||
TELNYX_ACCOUNT_SID=...
|
||||
# Grok
|
||||
GROK_API_KEY=...
|
||||
|
||||
# Inworld
|
||||
INWORLD_API_KEY=...
|
||||
|
||||
# Together.ai
|
||||
TOGETHER_API_KEY=...
|
||||
|
||||
# Cerebras
|
||||
CEREBRAS_API_KEY=...
|
||||
|
||||
# Fish Audio
|
||||
FISH_API_KEY=...
|
||||
|
||||
# Assembly AI
|
||||
ASSEMBLYAI_API_KEY=...
|
||||
|
||||
# OpenRouter
|
||||
OPENROUTER_API_KEY=...
|
||||
|
||||
# Piper
|
||||
PIPER_BASE_URL=...
|
||||
|
||||
# Smart turn
|
||||
LOCAL_SMART_TURN_MODEL_PATH=...
|
||||
FAL_SMART_TURN_API_KEY=...
|
||||
|
||||
# Twilio
|
||||
TWILIO_ACCOUNT_SID=...
|
||||
TWILIO_AUTH_TOKEN=...
|
||||
|
||||
# Ultravox Realtime
|
||||
ULTRAVOX_API_KEY=...
|
||||
# MiniMax
|
||||
MINIMAX_API_KEY=...
|
||||
MINIMAX_GROUP_ID=...
|
||||
|
||||
# Sarvam AI
|
||||
SARVAM_API_KEY=...
|
||||
|
||||
# Soniox
|
||||
SONIOX_API_KEY=
|
||||
|
||||
# Speechmatics
|
||||
SPEECHMATICS_API_KEY=...
|
||||
|
||||
# SambaNova
|
||||
SAMBANOVA_API_KEY=...
|
||||
|
||||
# Sentry
|
||||
SENTRY_DSN=...
|
||||
|
||||
# Heygen
|
||||
HEYGEN_API_KEY=...
|
||||
|
||||
# Mistral
|
||||
MISTRAL_API_KEY=...
|
||||
|
||||
# NVIDIA
|
||||
NVIDIA_API_KEY=...
|
||||
|
||||
# Qwen
|
||||
QWEN_API_KEY=...
|
||||
|
||||
# WhatsApp
|
||||
WHATSAPP_TOKEN=...
|
||||
WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
|
||||
WHATSAPP_PHONE_NUMBER_ID=...
|
||||
WHATSAPP_APP_SECRET=...
|
||||
WHATSAPP_TOKEN=
|
||||
WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=
|
||||
WHATSAPP_PHONE_NUMBER_ID=
|
||||
WHATSAPP_APP_SECRET=
|
||||
@@ -15,7 +15,7 @@ from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.nvidia.tts import NvidiaTTSService
|
||||
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
|
||||
@@ -36,7 +36,7 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
@@ -17,6 +17,7 @@ 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
|
||||
@@ -25,18 +26,13 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -65,6 +61,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -80,19 +77,12 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -12,6 +12,7 @@ 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
|
||||
@@ -20,16 +21,11 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
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 DailyParams, DailyTransport
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -50,6 +46,7 @@ async def main():
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -63,21 +60,12 @@ async def main():
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -12,6 +12,7 @@ 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
|
||||
@@ -26,17 +27,12 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -55,6 +51,7 @@ async def main():
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -72,20 +69,13 @@ async def main():
|
||||
"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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -23,6 +23,7 @@ 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
|
||||
|
||||
@@ -26,6 +26,7 @@ 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
|
||||
|
||||
@@ -9,6 +9,7 @@ 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
|
||||
@@ -23,10 +24,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -36,8 +34,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -70,16 +66,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -101,19 +100,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +10,7 @@ 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
|
||||
@@ -24,10 +25,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -36,8 +34,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -88,6 +84,7 @@ transport_params = {
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
@@ -96,6 +93,7 @@ transport_params = {
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -115,19 +113,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
image_sync_aggregator = ImageSyncAggregator(
|
||||
os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
|
||||
|
||||
@@ -9,6 +9,7 @@ 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
|
||||
@@ -17,20 +18,15 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.cartesia.stt import CartesiaSTTService
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -60,7 +59,7 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaHttpTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
@@ -72,19 +71,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -9,6 +9,7 @@ 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
|
||||
@@ -17,10 +18,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.cartesia.tts import CartesiaTTSService
|
||||
@@ -29,8 +27,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -42,16 +38,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -71,19 +70,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -6,7 +6,6 @@
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
@@ -15,21 +14,20 @@ 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 (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
|
||||
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.turns.user_turn_strategies import ExternalUserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -53,125 +51,121 @@ transport_params = {
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"""Speechmatics STT and TTS Service Example
|
||||
"""Speechmatics STT Service Example
|
||||
|
||||
This example demonstrates using Speechmatics Speech-to-Text and Text-to-Speech services
|
||||
with speaker diarization and intelligent speaker management. Key features:
|
||||
This example demonstrates using Speechmatics Speech-to-Text service with speaker diarization and intelligent speaker management. Key features:
|
||||
|
||||
1. Speaker Diarization (STT)
|
||||
1. Speaker Diarization
|
||||
- Automatically identifies and distinguishes between different speakers
|
||||
- First speaker is identified as 'S1', others get subsequent IDs
|
||||
- Uses `enable_diarization` parameter to manage speaker detection
|
||||
|
||||
2. Smart Speaker Control (STT)
|
||||
2. Smart Speaker Control
|
||||
- `focus_speakers` parameter lets you target specific speakers (e.g. ["S1"])
|
||||
- Other speakers will be wrapped in PASSIVE tags
|
||||
- Only processes speech from focused speakers
|
||||
- Words from all speakers are wrapped with XML tags for clear speaker identification
|
||||
- Other speakers' speech only sent when focused speaker is active
|
||||
|
||||
3. Voice Activity Detection (STT)
|
||||
3. Voice Activity Detection
|
||||
- Built-in VAD using `enable_vad` parameter
|
||||
- Remove `vad_analyzer` from `transport` config to use module's VAD
|
||||
- Emits speaker started/stopped events
|
||||
|
||||
4. Text-to-Speech (TTS)
|
||||
- Low latency streaming audio synthesis
|
||||
- Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
|
||||
|
||||
5. Configuration Options
|
||||
4. Configuration Options
|
||||
- `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
|
||||
- Configurable `end_of_utterance_silence_trigger` (default 0.5s)
|
||||
- Customizable speaker formatting
|
||||
- Additional diarization settings available
|
||||
|
||||
For detailed information:
|
||||
- STT: https://docs.speechmatics.com/rt-api-ref
|
||||
- TTS: https://docs.speechmatics.com/text-to-speech/quickstart
|
||||
For detailed information about operating points and configuration:
|
||||
https://docs.speechmatics.com/rt-api-ref
|
||||
"""
|
||||
|
||||
logger.info(f"Starting bot")
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
|
||||
# focus_speakers=["S1"],
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
|
||||
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
enable_vad=True,
|
||||
enable_diarization=True,
|
||||
focus_speakers=["S1"],
|
||||
end_of_utterance_silence_trigger=0.5,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
|
||||
),
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
model="eleven_turbo_v2_5",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
params=BaseOpenAILLMService.InputParams(temperature=0.75),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are a helpful British assistant called Alfred. "
|
||||
"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. "
|
||||
"Always include punctuation in your responses. "
|
||||
"Give very short replies - do not give longer replies unless strictly necessary. "
|
||||
"Respond to what the user said in a concise, funny, creative and helpful way. "
|
||||
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
|
||||
"Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
|
||||
),
|
||||
)
|
||||
},
|
||||
]
|
||||
|
||||
tts = SpeechmaticsTTSService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
voice_id="sarah",
|
||||
aiohttp_session=session,
|
||||
)
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
params=BaseOpenAILLMService.InputParams(temperature=0.75),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are a helpful British assistant called Sarah. "
|
||||
"Your goal is to demonstrate your capabilities in a succinct way. "
|
||||
"Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
|
||||
"Always include punctuation in your responses. "
|
||||
"Give very short replies - do not give longer replies unless strictly necessary. "
|
||||
"Respond to what the user said in a concise, funny, creative and helpful way. "
|
||||
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
|
||||
"Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
|
||||
),
|
||||
},
|
||||
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
|
||||
]
|
||||
)
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
|
||||
)
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
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
|
||||
]
|
||||
)
|
||||
@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": "Say a short hello to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
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_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": "Say a short hello to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
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()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
|
||||
@@ -6,10 +6,10 @@
|
||||
|
||||
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
|
||||
@@ -18,22 +18,20 @@ 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 (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,125 +43,118 @@ transport_params = {
|
||||
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):
|
||||
"""Run example using Speechmatics STT and TTS.
|
||||
"""Run example using Speechmatics STT.
|
||||
|
||||
This example demonstrates a complete Speechmatics integration with both Speech-to-Text
|
||||
and Text-to-Speech services:
|
||||
This example will use diarization within our STT service and output the words spoken by
|
||||
each individual speaker and wrap them with XML tags for the LLM to process. Note the
|
||||
instructions in the system context for the LLM. This greatly improves the conversation
|
||||
experience by allowing the LLM to understand who is speaking in a multi-party call.
|
||||
|
||||
STT Features:
|
||||
- Diarization to identify and distinguish between different speakers
|
||||
- Words spoken by each speaker are wrapped with XML tags for LLM processing
|
||||
- System context instructions help the LLM understand multi-party conversations
|
||||
- ENHANCED operating point by default for optimal accuracy
|
||||
By default, this example will use our ENHANCED operating point, which is optimized for
|
||||
high accuracy. You can change this by setting the `operating_point` parameter to a different
|
||||
value.
|
||||
|
||||
TTS Features:
|
||||
- Low latency streaming audio synthesis
|
||||
- Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
|
||||
|
||||
For more information:
|
||||
- STT: https://docs.speechmatics.com/rt-api-ref
|
||||
- TTS: https://docs.speechmatics.com/text-to-speech/quickstart
|
||||
For more information on operating points, see the Speechmatics documentation:
|
||||
https://docs.speechmatics.com/rt-api-ref
|
||||
"""
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
enable_diarization=True,
|
||||
end_of_utterance_silence_trigger=0.5,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
),
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
model="eleven_turbo_v2_5",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
params=BaseOpenAILLMService.InputParams(temperature=0.75),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are a helpful British assistant called Alfred. "
|
||||
"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. "
|
||||
"Always include punctuation in your responses. "
|
||||
"Give very short replies - do not give longer replies unless strictly necessary. "
|
||||
"Respond to what the user said in a concise, funny, creative and helpful way. "
|
||||
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
|
||||
),
|
||||
)
|
||||
},
|
||||
]
|
||||
|
||||
tts = SpeechmaticsTTSService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
voice_id="sarah",
|
||||
aiohttp_session=session,
|
||||
)
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
params=BaseOpenAILLMService.InputParams(temperature=0.75),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are a helpful British assistant called Sarah. "
|
||||
"Your goal is to demonstrate your capabilities in a succinct way. "
|
||||
"Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
|
||||
"Always include punctuation in your responses. "
|
||||
"Give very short replies - do not give longer replies unless strictly necessary. "
|
||||
"Respond to what the user said in a concise, funny, creative and helpful way. "
|
||||
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
|
||||
),
|
||||
},
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
@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": "Say a short hello to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
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_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": "Say a short hello to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
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()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.cartesia.tts import CartesiaTTSService
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -40,16 +36,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -71,19 +70,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -4,72 +4,76 @@
|
||||
# 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.frames.frames import LLMRunFrame, TTSTextFrame
|
||||
from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
|
||||
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.inworld.tts import InworldHttpTTSService
|
||||
from pipecat.services.inworld.tts import InworldTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_output import BaseOutputTransport
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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("Starting bot")
|
||||
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 = InworldHttpTTSService(
|
||||
# Inworld TTS Service - Unified streaming and non-streaming
|
||||
# Set streaming=True for real-time audio, streaming=False for complete audio generation
|
||||
streaming = True # Toggle this to switch between modes
|
||||
|
||||
tts = InworldTTSService(
|
||||
api_key=os.getenv("INWORLD_API_KEY", ""),
|
||||
aiohttp_session=session,
|
||||
voice_id="Ashley",
|
||||
model="inworld-tts-1",
|
||||
# Set to False for non-streaming mode or True for streaming mode.
|
||||
streaming=True,
|
||||
streaming=streaming, # True: real-time chunks, False: complete audio then playback
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
@@ -77,34 +81,22 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
|
||||
"content": "You are very knowledgable about dogs. 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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
rtvi = RTVIProcessor()
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
rtvi,
|
||||
stt,
|
||||
context_aggregator.user(),
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
@@ -114,27 +106,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
observers=[
|
||||
RTVIObserver(rtvi),
|
||||
DebugLogObserver(
|
||||
frame_types={
|
||||
TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
|
||||
}
|
||||
),
|
||||
],
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info("Client connected")
|
||||
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()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info("Client disconnected")
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
@@ -1,149 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
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, TTSTextFrame
|
||||
from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
|
||||
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_output import BaseOutputTransport
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = InworldTTSService(
|
||||
api_key=os.getenv("INWORLD_API_KEY", ""),
|
||||
voice_id="Ashley",
|
||||
model="inworld-tts-1",
|
||||
temperature=1.1,
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
rtvi,
|
||||
stt,
|
||||
context_aggregator.user(),
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
observers=[
|
||||
RTVIObserver(rtvi),
|
||||
DebugLogObserver(
|
||||
frame_types={
|
||||
TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
|
||||
}
|
||||
),
|
||||
],
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info("Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info("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()
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.asyncai.tts import AsyncAIHttpTTSService
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,16 +41,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -77,21 +76,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.asyncai.tts import AsyncAITTSService
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -73,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -13,16 +13,16 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -32,8 +32,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -50,7 +48,7 @@ def _create_aic_filter() -> AICFilter:
|
||||
|
||||
return AICFilter(
|
||||
license_key=license_key,
|
||||
enhancement_level=0.5,
|
||||
enhancement_level=1.0,
|
||||
)
|
||||
|
||||
|
||||
@@ -58,30 +56,27 @@ def _create_aic_filter() -> AICFilter:
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: (
|
||||
lambda aic: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
|
||||
audio_in_filter=aic,
|
||||
)
|
||||
)(_create_aic_filter()),
|
||||
"twilio": lambda: (
|
||||
lambda aic: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
|
||||
audio_in_filter=aic,
|
||||
)
|
||||
)(_create_aic_filter()),
|
||||
"webrtc": lambda: (
|
||||
lambda aic: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
|
||||
audio_in_filter=aic,
|
||||
)
|
||||
)(_create_aic_filter()),
|
||||
"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(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
@@ -100,19 +95,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -9,35 +9,28 @@ 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, TTSTextFrame
|
||||
from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_output import BaseOutputTransport
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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.
|
||||
@@ -46,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -76,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
|
||||
|
||||
@@ -99,7 +88,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS (HumeTTSService with word timestamps)
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
@@ -113,14 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
audio_out_sample_rate=HUME_SAMPLE_RATE,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
observers=[
|
||||
RTVIObserver(rtvi),
|
||||
DebugLogObserver(
|
||||
frame_types={
|
||||
TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
|
||||
}
|
||||
),
|
||||
],
|
||||
observers=[RTVIObserver(rtvi)],
|
||||
)
|
||||
|
||||
@rtvi.event_handler("on_client_ready")
|
||||
@@ -130,9 +112,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
logger.info(
|
||||
"💡 Word timestamps are enabled! Watch the console for TTSTextFrame logs showing each word with its PTS."
|
||||
)
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@@ -1,135 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.gradium.stt import GradiumSTTService
|
||||
from pipecat.services.gradium.tts import GradiumTTSService
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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)),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GradiumSTTService(api_key=os.getenv("GRADIUM_API_KEY"))
|
||||
|
||||
tts = GradiumTTSService(
|
||||
api_key=os.getenv("GRADIUM_API_KEY"),
|
||||
voice_id="YTpq7expH9539ERJ",
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
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([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()
|
||||
@@ -15,6 +15,7 @@ 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
|
||||
@@ -23,10 +24,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frameworks.langchain import LangchainProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -35,8 +33,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -58,16 +54,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -103,14 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
lc = LangchainProcessor(history_chain)
|
||||
|
||||
context = LLMContext()
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -17,7 +17,6 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContext,
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -27,7 +26,6 @@ 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.turns.user_turn_strategies import ExternalUserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -54,10 +52,7 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramFluxSTTService(
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
params=DeepgramFluxSTTService.InputParams(min_confidence=0.3),
|
||||
)
|
||||
stt = DeepgramFluxSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
|
||||
|
||||
@@ -66,15 +61,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -109,10 +101,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
@stt.event_handler("on_update")
|
||||
async def on_deepgram_flux_update(stt, transcript):
|
||||
logger.debug(f"On deeggram flux update: {transcript}")
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
@@ -1,142 +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.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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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 DeepgramHttpTTSService
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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)),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = DeepgramHttpTTSService(
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
voice="aura-2-andromeda-en",
|
||||
aiohttp_session=session,
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # 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([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()
|
||||
@@ -1,145 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.aws.llm import AWSBedrockLLMService
|
||||
from pipecat.services.deepgram.stt_sagemaker import DeepgramSageMakerSTTService
|
||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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)),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Initialize Deepgram SageMaker STT Service
|
||||
# This requires:
|
||||
# - AWS credentials configured (via environment variables or AWS CLI)
|
||||
# - A deployed SageMaker endpoint with Deepgram model
|
||||
stt = DeepgramSageMakerSTTService(
|
||||
endpoint_name=os.getenv("SAGEMAKER_ENDPOINT_NAME"),
|
||||
region=os.getenv("AWS_REGION"),
|
||||
)
|
||||
|
||||
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
|
||||
|
||||
llm = AWSBedrockLLMService(
|
||||
aws_region=os.getenv("AWS_REGION"),
|
||||
model="us.amazon.nova-pro-v1:0",
|
||||
params=AWSBedrockLLMService.InputParams(temperature=0.8),
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # 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([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()
|
||||
@@ -11,15 +11,17 @@ from deepgram import LiveOptions
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.frames.frames import (
|
||||
InterruptionFrame,
|
||||
LLMRunFrame,
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -28,7 +30,6 @@ 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.turns.user_turn_strategies import ExternalUserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -67,15 +68,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -98,6 +96,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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()])
|
||||
|
||||
@stt.event_handler("on_utterance_end")
|
||||
async def on_utterance_end(stt, *args, **kwargs):
|
||||
await task.queue_frames([UserStoppedSpeakingFrame()])
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -70,19 +69,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.elevenlabs.stt import ElevenLabsSTTService
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,16 +41,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -80,21 +79,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,20 +19,15 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.elevenlabs.stt import ElevenLabsRealtimeSTTService
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -61,7 +60,7 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
||||
@@ -73,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -73,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -75,19 +74,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -1,143 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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 AzureHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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)),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AzureSTTService(
|
||||
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
|
||||
region=os.getenv("AZURE_SPEECH_REGION"),
|
||||
)
|
||||
|
||||
tts = AzureHttpTTSService(
|
||||
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
|
||||
region=os.getenv("AZURE_SPEECH_REGION"),
|
||||
)
|
||||
|
||||
llm = AzureLLMService(
|
||||
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
|
||||
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
|
||||
model=os.getenv("AZURE_CHATGPT_MODEL"),
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # 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([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()
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.azure.llm import AzureLLMService
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -79,19 +78,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.openai.llm import OpenAILLMService
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -73,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"content": "You are very knowledgable about dogs. 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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.cartesia.tts import CartesiaTTSService
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -78,19 +77,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -76,21 +75,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.cartesia.tts import CartesiaTTSService
|
||||
@@ -32,8 +30,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,16 +41,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -82,19 +81,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"content": f"You are a helpful LLM. 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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -19,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -70,19 +68,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,8 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
|
||||
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.groq.llm import GroqLLMService
|
||||
@@ -30,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -71,18 +71,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
|
||||
@@ -8,17 +8,13 @@
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesAppendFrame
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -27,8 +23,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
# Strands agent setup
|
||||
try:
|
||||
@@ -77,9 +71,9 @@ def build_agent(model_id: str, max_tokens: int):
|
||||
@tool
|
||||
def check_weather(location: str) -> str:
|
||||
if location.lower() == "san francisco":
|
||||
return "The weather in San Francisco is sunny and 75 degrees."
|
||||
return "The weather in San Francisco is sunny and 30 degrees."
|
||||
elif location.lower() == "sydney":
|
||||
return "The weather in Sydney is cloudy and 60 degrees."
|
||||
return "The weather in Sydney is cloudy and 20 degrees."
|
||||
else:
|
||||
return "I'm not sure about the weather in that location."
|
||||
|
||||
@@ -120,14 +114,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Setup context aggregators for message handling
|
||||
context = LLMContext()
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -8,6 +8,7 @@
|
||||
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
|
||||
@@ -16,10 +17,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.aws.llm import AWSBedrockLLMService
|
||||
@@ -28,8 +26,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -41,16 +37,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -68,26 +67,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
llm = AWSBedrockLLMService(
|
||||
aws_region="us-west-2",
|
||||
model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
|
||||
params=AWSBedrockLLMService.InputParams(temperature=0.8),
|
||||
model="us.anthropic.claude-3-5-haiku-20241022-v1:0",
|
||||
params=AWSBedrockLLMService.InputParams(temperature=0.8, latency="optimized"),
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -25,6 +25,7 @@ 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
|
||||
@@ -33,10 +34,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -46,8 +44,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -62,6 +58,7 @@ transport_params = {
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
@@ -70,6 +67,7 @@ transport_params = {
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -91,25 +89,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
model="gemini-2.5-flash-image",
|
||||
# model="gemini-3-pro-image-preview", # A more powerful model, but slower
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -4,12 +4,31 @@
|
||||
# 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
|
||||
@@ -18,10 +37,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +47,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +58,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -67,13 +84,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
)
|
||||
|
||||
tts = GeminiTTSService(
|
||||
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
|
||||
model="gemini-2.5-flash-tts",
|
||||
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,
|
||||
prompt="You are a helpful AI assistant. Speak in a natural, conversational tone.",
|
||||
),
|
||||
params=GeminiTTSService.InputParams(language=Language.EN_US),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
@@ -87,34 +101,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"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: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:
|
||||
- [sigh] - Insert a sigh sound
|
||||
- [laughing] - Insert a laugh
|
||||
- [uhm] - Insert a hesitation sound
|
||||
- [whispering] - Speak the next part in a whisper
|
||||
- [shouting] - Speak the next part louder
|
||||
- [extremely fast] - Speak the next part very quickly
|
||||
- [short pause], [medium pause], [long pause] - Add pauses for dramatic effect
|
||||
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."
|
||||
|
||||
Examples:
|
||||
- "Well [sigh] that's a tricky question."
|
||||
- "[laughing] That's a great joke!"
|
||||
- "[whispering] Let me tell you a secret."
|
||||
- "The answer is... [long pause] ...42!"
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.""",
|
||||
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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -140,11 +140,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation
|
||||
# Kick off the conversation with a styled introduction
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are an AI assistant. You can help with a variety of tasks. Introduce yourself and ask the user what they would like to know.",
|
||||
"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()])
|
||||
|
||||
@@ -1,149 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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 GoogleHttpTTSService
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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)),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GoogleSTTService(
|
||||
params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
|
||||
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
|
||||
location="us",
|
||||
)
|
||||
|
||||
tts = GoogleHttpTTSService(
|
||||
voice_id="en-US-Chirp3-HD-Charon",
|
||||
params=GoogleHttpTTSService.InputParams(language=Language.EN_US),
|
||||
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
model="gemini-2.5-flash",
|
||||
# force a certain amount of thinking if you want it
|
||||
# params=GoogleLLMService.InputParams(
|
||||
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
|
||||
# ),
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User respones
|
||||
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([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()
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -62,9 +61,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GoogleSTTService(
|
||||
params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
|
||||
params=GoogleSTTService.InputParams(languages=Language.EN_US),
|
||||
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
|
||||
location="us",
|
||||
)
|
||||
|
||||
tts = GoogleTTSService(
|
||||
@@ -76,28 +74,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
model="gemini-2.5-flash",
|
||||
# force a certain amount of thinking if you want it
|
||||
# params=GoogleLLMService.InputParams(
|
||||
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
|
||||
# ),
|
||||
# turn on thinking if you want it
|
||||
# params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
|
||||
)
|
||||
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.assemblyai.stt import AssemblyAISTTService
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -75,19 +74,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -11,6 +11,7 @@ from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.filters.krisp_viva_filter import KrispVivaFilter
|
||||
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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,18 +40,21 @@ transport_params = {
|
||||
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=KrispVivaFilter(),
|
||||
),
|
||||
"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=KrispVivaFilter(),
|
||||
),
|
||||
"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=KrispVivaFilter(),
|
||||
),
|
||||
}
|
||||
@@ -73,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,18 +40,21 @@ transport_params = {
|
||||
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=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()),
|
||||
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()),
|
||||
audio_in_filter=KrispFilter(),
|
||||
),
|
||||
}
|
||||
@@ -73,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,16 +41,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -78,21 +77,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -72,19 +71,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,20 +19,15 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.nvidia.llm import NvidiaLLMService
|
||||
from pipecat.services.nvidia.stt import NvidiaSTTService
|
||||
from pipecat.services.nvidia.tts import NvidiaTTSService
|
||||
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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -60,30 +59,21 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = NvidiaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
stt = RivaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
|
||||
llm = NvidiaLLMService(
|
||||
api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct"
|
||||
)
|
||||
llm = NimLLMService(api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct")
|
||||
|
||||
tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
tts = RivaTTSService(api_key=os.getenv("NVIDIA_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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -12,6 +12,7 @@ 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
|
||||
@@ -31,10 +32,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frame_processor import FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -44,8 +42,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -57,7 +53,7 @@ You are a helpful LLM in a WebRTC call. Your goals are to be helpful and brief i
|
||||
You are expert at transcribing audio to text. You will receive a mixture of audio and text input. When
|
||||
asked to transcribe what the user said, output an exact, word-for-word transcription.
|
||||
|
||||
Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
|
||||
Your output will be converted to audio so don't include special characters in your answers.
|
||||
|
||||
Each time you answer, you should respond in three parts.
|
||||
|
||||
@@ -205,16 +201,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -225,10 +224,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
model="gemini-2.5-flash",
|
||||
# force a certain amount of thinking if you want it
|
||||
# params=GoogleLLMService.InputParams(
|
||||
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
|
||||
# ),
|
||||
# turn on thinking if you want it
|
||||
# params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
|
||||
)
|
||||
|
||||
tts = GoogleTTSService(
|
||||
@@ -249,14 +246,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
audio_collector = UserAudioCollector(context, context_aggregator.user())
|
||||
pull_transcript_out_of_llm_output = TranscriptExtractor(context)
|
||||
fixup_context_messages = TranscriptionContextFixup(context)
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -73,19 +72,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -9,35 +9,58 @@ import os
|
||||
|
||||
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 UserImageRawFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.moondream.vision import MoondreamService
|
||||
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
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# NOTE: This example requires GPU resources to run efficiently.
|
||||
# The Ultravox model is compute-intensive and performs best with GPU acceleration.
|
||||
# This can be deployed on cloud GPU providers like Cerebrium.ai for optimal performance.
|
||||
|
||||
|
||||
# Want to initialize the ultravox processor since it takes time to load the model and dont
|
||||
# want to load it every time the pipeline is run
|
||||
ultravox_processor = UltravoxSTTService(
|
||||
model_name="fixie-ai/ultravox-v0_5-llama-3_1-8b",
|
||||
hf_token=os.getenv("HF_TOKEN"),
|
||||
)
|
||||
|
||||
|
||||
# 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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -46,15 +69,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
api_key=os.environ.get("CARTESIA_API_KEY"),
|
||||
voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
|
||||
)
|
||||
|
||||
vision = MoondreamService()
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
vision, # Vision
|
||||
transport.input(), # Transport user input
|
||||
ultravox_processor,
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
]
|
||||
@@ -73,29 +95,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
|
||||
if not runner_args.body:
|
||||
script_dir = os.path.dirname(__file__)
|
||||
runner_args.body = {
|
||||
"image_path": os.path.join(script_dir, "assets", "cat.jpg"),
|
||||
"question": "Describe this image",
|
||||
}
|
||||
|
||||
image_path = runner_args.body["image_path"]
|
||||
question = runner_args.body["question"]
|
||||
|
||||
# Describe the image.
|
||||
image = Image.open(image_path)
|
||||
await task.queue_frames(
|
||||
[
|
||||
UserImageRawFrame(
|
||||
image=image.tobytes(),
|
||||
format="RGB",
|
||||
size=image.size,
|
||||
text=question,
|
||||
)
|
||||
]
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,10 +20,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -31,8 +29,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,16 +41,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -77,21 +76,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -72,19 +71,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -10,6 +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
|
||||
@@ -18,10 +19,7 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.cartesia.tts import CartesiaTTSService
|
||||
@@ -30,8 +28,6 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -44,16 +40,19 @@ transport_params = {
|
||||
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()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -75,19 +74,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -11,6 +11,7 @@ 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
|
||||
@@ -19,16 +20,13 @@ 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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
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.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -42,6 +40,7 @@ async def main():
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -57,19 +56,12 @@ async def main():
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||||
"content": "You are a helpful LLM. 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,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user