Compare commits
1 Commits
v0.0.98
...
hush/usage
| Author | SHA1 | Date | |
|---|---|---|---|
|
cb6e86e69f |
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"
|
||||
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
|
||||
|
||||
1285
CHANGELOG.md
1285
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:
|
||||
|
||||
105
CONTRIBUTING.md
105
CONTRIBUTING.md
@@ -17,121 +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
|
||||
|
||||
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), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), 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:
|
||||
|
||||
@@ -1,16 +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()]),
|
||||
@@ -77,7 +77,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -60,7 +60,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -69,7 +69,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
@@ -100,7 +100,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -113,7 +113,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -21,8 +21,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.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
|
||||
@@ -59,7 +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"),
|
||||
@@ -71,7 +71,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -70,7 +70,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -6,7 +6,6 @@
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
@@ -21,10 +20,10 @@ from pipecat.processors.aggregators.llm_response import (
|
||||
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
|
||||
@@ -52,127 +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`, and `megan`
|
||||
|
||||
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,
|
||||
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>",
|
||||
|
||||
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(aggregation_timeout=0.005),
|
||||
)
|
||||
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):
|
||||
|
||||
@@ -6,7 +6,6 @@
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
@@ -25,10 +24,10 @@ from pipecat.processors.aggregators.llm_response import (
|
||||
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
|
||||
@@ -62,106 +61,100 @@ transport_params = {
|
||||
|
||||
|
||||
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`, and `megan`
|
||||
|
||||
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,
|
||||
enable_diarization=True,
|
||||
end_of_utterance_silence_trigger=0.5,
|
||||
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(aggregation_timeout=0.005),
|
||||
)
|
||||
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):
|
||||
|
||||
@@ -70,7 +70,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
@@ -14,26 +15,26 @@ 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
|
||||
from pipecat.processors.frameworks.rtvi import 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 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
|
||||
|
||||
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,
|
||||
@@ -57,18 +58,22 @@ transport_params = {
|
||||
|
||||
|
||||
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"))
|
||||
@@ -76,25 +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)
|
||||
|
||||
rtvi = RTVIProcessor()
|
||||
|
||||
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
|
||||
]
|
||||
)
|
||||
|
||||
@@ -104,27 +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)
|
||||
|
||||
@@ -1,141 +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.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.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frameworks.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
|
||||
|
||||
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)),
|
||||
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")
|
||||
|
||||
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)
|
||||
|
||||
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()
|
||||
@@ -76,7 +76,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -72,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -15,6 +15,7 @@ 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
|
||||
@@ -47,7 +48,7 @@ def _create_aic_filter() -> AICFilter:
|
||||
|
||||
return AICFilter(
|
||||
license_key=license_key,
|
||||
enhancement_level=0.5,
|
||||
enhancement_level=1.0,
|
||||
)
|
||||
|
||||
|
||||
@@ -55,33 +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),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
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),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
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),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
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(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
@@ -100,7 +95,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -13,29 +13,24 @@ 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,
|
||||
)
|
||||
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
|
||||
|
||||
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.
|
||||
@@ -77,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
@@ -93,7 +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
|
||||
]
|
||||
@@ -107,14 +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")
|
||||
@@ -124,9 +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()])
|
||||
|
||||
@@ -1,127 +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.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.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
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
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)
|
||||
|
||||
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()
|
||||
@@ -52,10 +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")
|
||||
|
||||
@@ -64,7 +61,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
@@ -104,10 +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)
|
||||
|
||||
@@ -1,132 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.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
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
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)
|
||||
|
||||
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()
|
||||
@@ -1,137 +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.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.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
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# 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)
|
||||
|
||||
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()
|
||||
@@ -68,7 +68,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -69,7 +69,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -79,7 +79,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.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
|
||||
@@ -60,7 +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", ""),
|
||||
@@ -72,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -72,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -74,7 +74,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -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.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.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
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
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)
|
||||
|
||||
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()
|
||||
@@ -78,7 +78,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -72,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -77,7 +77,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -75,7 +75,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -81,7 +81,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -68,7 +68,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -71,7 +71,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -71,9 +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."
|
||||
|
||||
|
||||
@@ -67,14 +67,14 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -89,13 +89,12 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -4,6 +4,24 @@
|
||||
# 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
|
||||
|
||||
@@ -66,13 +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(
|
||||
@@ -86,22 +101,15 @@ 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.""",
|
||||
},
|
||||
]
|
||||
|
||||
@@ -132,11 +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()])
|
||||
|
||||
@@ -1,141 +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.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.services.google.stt import GoogleSTTService
|
||||
from pipecat.services.google.tts import GoogleHttpTTSService, GoogleTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
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)
|
||||
|
||||
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()
|
||||
@@ -61,9 +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(
|
||||
@@ -75,16 +74,14 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -74,7 +74,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -72,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -72,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -77,7 +77,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -71,7 +71,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.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
|
||||
@@ -59,18 +59,16 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
@@ -53,7 +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.
|
||||
|
||||
@@ -224,10 +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(
|
||||
|
||||
@@ -72,7 +72,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -9,36 +9,55 @@ 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()),
|
||||
@@ -50,15 +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
|
||||
]
|
||||
@@ -77,29 +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")
|
||||
@@ -76,7 +76,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -71,7 +71,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -74,7 +74,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -56,7 +56,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -78,7 +78,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -15,7 +15,6 @@ 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
|
||||
@@ -23,8 +22,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.sarvam.stt import SarvamSTTService
|
||||
from pipecat.services.sarvam.tts import SarvamHttpTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
@@ -64,10 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = SarvamSTTService(
|
||||
api_key=os.getenv("SARVAM_API_KEY"),
|
||||
model="saarika:v2.5",
|
||||
)
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = SarvamHttpTTSService(
|
||||
api_key=os.getenv("SARVAM_API_KEY"),
|
||||
@@ -80,7 +76,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
@@ -113,7 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
|
||||
@@ -24,8 +24,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.sarvam.stt import SarvamSTTService
|
||||
from pipecat.services.sarvam.tts import SarvamTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
@@ -62,10 +62,7 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = SarvamSTTService(
|
||||
api_key=os.getenv("SARVAM_API_KEY"),
|
||||
model="saarika:v2.5",
|
||||
)
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = SarvamTTSService(
|
||||
api_key=os.getenv("SARVAM_API_KEY"),
|
||||
@@ -77,7 +74,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
147
examples/foundational/08-bots-arguing.py
Normal file
147
examples/foundational/08-bots-arguing.py
Normal file
@@ -0,0 +1,147 @@
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
from typing import Tuple
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMContextFrame, TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.processors.aggregators import SentenceAggregator
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.daily import configure
|
||||
from pipecat.services.azure import AzureLLMService, AzureTTSService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.fal import FalImageGenService
|
||||
from pipecat.transports.daily.transport import DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
|
||||
logger = logging.getLogger("pipecat")
|
||||
logger.setLevel(logging.DEBUG)
|
||||
|
||||
|
||||
async def main():
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, _) = await configure(session)
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
None,
|
||||
"Respond bot",
|
||||
duration_minutes=10,
|
||||
mic_enabled=True,
|
||||
mic_sample_rate=16000,
|
||||
camera_enabled=True,
|
||||
camera_width=1024,
|
||||
camera_height=1024,
|
||||
)
|
||||
|
||||
llm = AzureLLMService(
|
||||
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
|
||||
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
|
||||
model=os.getenv("AZURE_CHATGPT_MODEL"),
|
||||
)
|
||||
tts1 = AzureTTSService(
|
||||
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
|
||||
region=os.getenv("AZURE_SPEECH_REGION"),
|
||||
)
|
||||
tts2 = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id="jBpfuIE2acCO8z3wKNLl",
|
||||
)
|
||||
dalle = FalImageGenService(
|
||||
params=FalImageGenService.InputParams(image_size="1024x1024"),
|
||||
aiohttp_session=session,
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
|
||||
bot1_messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a stern librarian. You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever compromise on the fundamental truth that a hot dog is a sandwich. Your responses should only be a few sentences long.",
|
||||
},
|
||||
]
|
||||
bot2_messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich.",
|
||||
},
|
||||
]
|
||||
|
||||
async def get_text_and_audio(messages) -> Tuple[str, bytearray]:
|
||||
"""This function streams text from the LLM and uses the TTS service to convert
|
||||
that text to speech as it's received.
|
||||
"""
|
||||
source_queue = asyncio.Queue()
|
||||
sink_queue = asyncio.Queue()
|
||||
sentence_aggregator = SentenceAggregator()
|
||||
pipeline = Pipeline([llm, sentence_aggregator, tts1], source_queue, sink_queue)
|
||||
|
||||
await source_queue.put(LLMContextFrame(LLMContext(messages)))
|
||||
await source_queue.put(EndFrame())
|
||||
await pipeline.run_pipeline()
|
||||
|
||||
message = ""
|
||||
all_audio = bytearray()
|
||||
while sink_queue.qsize():
|
||||
frame = sink_queue.get_nowait()
|
||||
if isinstance(frame, TextFrame):
|
||||
message += frame.text
|
||||
elif isinstance(frame, AudioFrame):
|
||||
all_audio.extend(frame.audio)
|
||||
|
||||
return (message, all_audio)
|
||||
|
||||
async def get_bot1_statement():
|
||||
message, audio = await get_text_and_audio(bot1_messages)
|
||||
|
||||
bot1_messages.append({"role": "assistant", "content": message})
|
||||
bot2_messages.append({"role": "user", "content": message})
|
||||
|
||||
return audio
|
||||
|
||||
async def get_bot2_statement():
|
||||
message, audio = await get_text_and_audio(bot2_messages)
|
||||
|
||||
bot2_messages.append({"role": "assistant", "content": message})
|
||||
bot1_messages.append({"role": "user", "content": message})
|
||||
|
||||
return audio
|
||||
|
||||
async def argue():
|
||||
for i in range(100):
|
||||
print(f"In iteration {i}")
|
||||
|
||||
bot1_description = "A woman conservatively dressed as a librarian in a library surrounded by books, cartoon, serious, highly detailed"
|
||||
|
||||
(audio1, image_data1) = await asyncio.gather(
|
||||
get_bot1_statement(), dalle.run_image_gen(bot1_description)
|
||||
)
|
||||
await transport.send_queue.put(
|
||||
[
|
||||
ImageFrame(image_data1[1], image_data1[2]),
|
||||
AudioFrame(audio1),
|
||||
]
|
||||
)
|
||||
|
||||
bot2_description = "A cat dressed in a hot dog costume, cartoon, bright colors, funny, highly detailed"
|
||||
|
||||
(audio2, image_data2) = await asyncio.gather(
|
||||
get_bot2_statement(), dalle.run_image_gen(bot2_description)
|
||||
)
|
||||
await transport.send_queue.put(
|
||||
[
|
||||
ImageFrame(image_data2[1], image_data2[2]),
|
||||
AudioFrame(audio2),
|
||||
]
|
||||
)
|
||||
|
||||
await asyncio.gather(transport.run(), argue())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -121,7 +121,7 @@ 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. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -1,141 +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 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 LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
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()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be 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. You are also able to describe images.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
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")
|
||||
|
||||
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"]
|
||||
|
||||
# Kick off the conversation.
|
||||
image = Image.open(image_path)
|
||||
message = await LLMContext.create_image_message(
|
||||
image=image.tobytes(),
|
||||
format="RGB",
|
||||
size=image.size,
|
||||
text=question,
|
||||
)
|
||||
messages.append(message)
|
||||
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()
|
||||
180
examples/foundational/12-describe-video.py
Normal file
180
examples/foundational/12-describe-video.py
Normal file
@@ -0,0 +1,180 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
TextFrame,
|
||||
TTSSpeakFrame,
|
||||
UserImageRawFrame,
|
||||
UserImageRequestFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.user_response import UserResponseAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
get_transport_client_id,
|
||||
maybe_capture_participant_camera,
|
||||
)
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.moondream.vision import MoondreamService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class UserImageRequester(FrameProcessor):
|
||||
"""Converts incoming text into requests for user images."""
|
||||
|
||||
def __init__(self, participant_id: Optional[str] = None):
|
||||
super().__init__()
|
||||
self._participant_id = participant_id
|
||||
|
||||
def set_participant_id(self, participant_id: str):
|
||||
self._participant_id = participant_id
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if self._participant_id and isinstance(frame, TextFrame):
|
||||
await self.push_frame(
|
||||
UserImageRequestFrame(self._participant_id, context=frame.text),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
class UserImageProcessor(FrameProcessor):
|
||||
"""Converts incoming user images into context frames."""
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, UserImageRawFrame):
|
||||
if frame.request and frame.request.context:
|
||||
context = LLMContext()
|
||||
context.add_image_frame_message(
|
||||
image=frame.image,
|
||||
text=frame.request.context,
|
||||
size=frame.size,
|
||||
format=frame.format,
|
||||
)
|
||||
frame = LLMContextFrame(context)
|
||||
await self.push_frame(frame)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# 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,
|
||||
video_in_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,
|
||||
video_in_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
user_response = UserResponseAggregator()
|
||||
|
||||
# Initialize the image requester without setting the participant ID yet
|
||||
image_requester = UserImageRequester()
|
||||
|
||||
image_processor = UserImageProcessor()
|
||||
|
||||
# If you run into weird description, try with use_cpu=True
|
||||
moondream = MoondreamService()
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
user_response,
|
||||
image_requester,
|
||||
image_processor,
|
||||
moondream,
|
||||
tts,
|
||||
transport.output(),
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
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: {client}")
|
||||
|
||||
await maybe_capture_participant_camera(transport, client)
|
||||
|
||||
# Set the participant ID in the image requester
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
image_requester.set_participant_id(client_id)
|
||||
|
||||
# Welcome message
|
||||
await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -5,23 +5,29 @@
|
||||
#
|
||||
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.adapters.schemas.function_schema import FunctionSchema
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
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, UserImageRequestFrame
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
TextFrame,
|
||||
TTSSpeakFrame,
|
||||
UserImageRawFrame,
|
||||
UserImageRequestFrame,
|
||||
)
|
||||
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.frame_processor import FrameDirection
|
||||
from pipecat.processors.aggregators.user_response import UserResponseAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
@@ -31,37 +37,53 @@ from pipecat.runner.utils import (
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def fetch_user_image(params: FunctionCallParams):
|
||||
"""Fetch the user image and push it to the LLM.
|
||||
class UserImageRequester(FrameProcessor):
|
||||
"""Converts incoming text into requests for user images."""
|
||||
|
||||
When called, this function pushes a UserImageRequestFrame upstream to the
|
||||
transport. As a result, the transport will request the user image and push a
|
||||
UserImageRawFrame downstream which will be added to the context by the LLM
|
||||
assistant aggregator.
|
||||
"""
|
||||
user_id = params.arguments["user_id"]
|
||||
question = params.arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
|
||||
def __init__(self, participant_id: Optional[str] = None):
|
||||
super().__init__()
|
||||
self._participant_id = participant_id
|
||||
|
||||
# Request a user image frame and indicate that it should be added to the
|
||||
# context.
|
||||
await params.llm.push_frame(
|
||||
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
def set_participant_id(self, participant_id: str):
|
||||
self._participant_id = participant_id
|
||||
|
||||
await params.result_callback(None)
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
# Instead of None, it's possible to also provide a tool call answer to
|
||||
# tell the LLM that we are grabbing the image to analyze.
|
||||
# await params.result_callback({"result": "Image is being captured."})
|
||||
if self._participant_id and isinstance(frame, TextFrame):
|
||||
await self.push_frame(
|
||||
UserImageRequestFrame(self._participant_id, context=frame.text),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
class UserImageProcessor(FrameProcessor):
|
||||
"""Converts incoming user images into context frames."""
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, UserImageRawFrame):
|
||||
if frame.request and frame.request.context:
|
||||
context = LLMContext()
|
||||
context.add_image_frame_message(
|
||||
image=frame.image,
|
||||
text=frame.request.context,
|
||||
size=frame.size,
|
||||
format=frame.format,
|
||||
)
|
||||
frame = LLMContextFrame(context)
|
||||
await self.push_frame(frame)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
@@ -88,53 +110,33 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
user_response = UserResponseAggregator()
|
||||
|
||||
# Initialize the image requester without setting the participant ID yet
|
||||
image_requester = UserImageRequester()
|
||||
|
||||
image_processor = UserImageProcessor()
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
# Google Gemini model for vision analysis
|
||||
google = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
# Google Gemini model for vision analysis
|
||||
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
|
||||
llm.register_function("fetch_user_image", fetch_user_image)
|
||||
|
||||
fetch_image_function = FunctionSchema(
|
||||
name="fetch_user_image",
|
||||
description="Called when the user requests a description of their camera feed",
|
||||
properties={
|
||||
"user_id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the user to grab the image from",
|
||||
},
|
||||
"question": {
|
||||
"type": "string",
|
||||
"description": "The question that the user is asking about the image",
|
||||
},
|
||||
},
|
||||
required=["user_id", "question"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[fetch_image_function])
|
||||
|
||||
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. You are able to describe images from the user camera.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
transport.input(),
|
||||
stt,
|
||||
user_response,
|
||||
image_requester,
|
||||
image_processor,
|
||||
google,
|
||||
tts,
|
||||
transport.output(),
|
||||
]
|
||||
)
|
||||
|
||||
@@ -155,15 +157,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Set the participant ID in the image requester
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
image_requester.set_participant_id(client_id)
|
||||
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
|
||||
}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
# Welcome message
|
||||
await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
@@ -1,148 +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 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 LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.aws.llm import AWSBedrockLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
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()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = AWSBedrockLLMService(
|
||||
aws_region="us-west-2",
|
||||
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
|
||||
# Note: usually, prefer providing latency="optimized" param.
|
||||
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
|
||||
# which we need for image input.
|
||||
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. You are also able to describe images.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
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")
|
||||
|
||||
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"]
|
||||
|
||||
# Kick off the conversation.
|
||||
image = Image.open(image_path)
|
||||
message = await LLMContext.create_image_message(
|
||||
image=image.tobytes(),
|
||||
format="RGB",
|
||||
size=image.size,
|
||||
text=question,
|
||||
)
|
||||
messages.append(message)
|
||||
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()
|
||||
@@ -4,9 +4,8 @@
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import io
|
||||
import os
|
||||
import re
|
||||
from typing import Optional
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
@@ -17,17 +16,24 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMRunFrame,
|
||||
MetricsFrame,
|
||||
LLMContextFrame,
|
||||
TextFrame,
|
||||
TTSSpeakFrame,
|
||||
UserImageRawFrame,
|
||||
UserImageRequestFrame,
|
||||
)
|
||||
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.user_response import UserResponseAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
get_transport_client_id,
|
||||
maybe_capture_participant_camera,
|
||||
)
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
@@ -37,41 +43,46 @@ from pipecat.transports.daily.transport import DailyParams
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
def format_metrics(metrics, indent=0):
|
||||
lines = []
|
||||
tab = "\t" * indent
|
||||
class UserImageRequester(FrameProcessor):
|
||||
"""Converts incoming text into requests for user images."""
|
||||
|
||||
for metric in metrics:
|
||||
lines.append(tab + type(metric).__name__)
|
||||
for field, value in vars(metric).items():
|
||||
if hasattr(value, "__dict__") and not isinstance(
|
||||
value, (str, int, float, bool, type(None))
|
||||
):
|
||||
lines.append(f"{tab}\t{field}={type(value).__name__}")
|
||||
for k, v in vars(value).items():
|
||||
lines.append(f"{tab}\t\t{k}={repr(v)}")
|
||||
else:
|
||||
lines.append(f"{tab}\t{field}={repr(value)}")
|
||||
def __init__(self, participant_id: Optional[str] = None):
|
||||
super().__init__()
|
||||
self._participant_id = participant_id
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
class MetricsFrameLogger(FrameProcessor):
|
||||
"""MetricsFrameLogger formats and logs all MetericsFrames"""
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
def set_participant_id(self, participant_id: str):
|
||||
self._participant_id = participant_id
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, MetricsFrame):
|
||||
logger.info(f"{frame.name}\n {format_metrics(frame.data)}")
|
||||
if self._participant_id and isinstance(frame, TextFrame):
|
||||
await self.push_frame(
|
||||
UserImageRequestFrame(self._participant_id, context=frame.text),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
# ALWAYS push all frames
|
||||
|
||||
class UserImageProcessor(FrameProcessor):
|
||||
"""Converts incoming user images into context frames."""
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, UserImageRawFrame):
|
||||
if frame.request and frame.request.context:
|
||||
context = LLMContext()
|
||||
context.add_image_frame_message(
|
||||
image=frame.image,
|
||||
text=frame.request.context,
|
||||
size=frame.size,
|
||||
format=frame.format,
|
||||
)
|
||||
frame = LLMContextFrame(context)
|
||||
await self.push_frame(frame)
|
||||
else:
|
||||
# SUPER IMPORTANT: always push every frame!
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
@@ -82,13 +93,14 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_in_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,
|
||||
video_out_enabled=True,
|
||||
video_in_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
@@ -98,37 +110,33 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
user_response = UserResponseAggregator()
|
||||
|
||||
# Initialize the image requester without setting the participant ID yet
|
||||
image_requester = UserImageRequester()
|
||||
|
||||
image_processor = UserImageProcessor()
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
# OpenAI GPT-4o for vision analysis
|
||||
openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be 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)
|
||||
|
||||
metrics_frame_processor = MetricsFrameLogger()
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
context_aggregator.user(),
|
||||
llm,
|
||||
user_response,
|
||||
image_requester,
|
||||
image_processor,
|
||||
openai,
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
metrics_frame_processor, # pretty print metrics frames
|
||||
]
|
||||
)
|
||||
|
||||
@@ -144,9 +152,15 @@ 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: {client}")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
await maybe_capture_participant_camera(transport, client)
|
||||
|
||||
# Set the participant ID in the image requester
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
image_requester.set_participant_id(client_id)
|
||||
|
||||
# Welcome message
|
||||
await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
@@ -1,141 +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 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 LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
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()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_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. You are also able to describe images.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
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")
|
||||
|
||||
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"]
|
||||
|
||||
# Kick off the conversation.
|
||||
image = Image.open(image_path)
|
||||
message = await LLMContext.create_image_message(
|
||||
image=image.tobytes(),
|
||||
format="RGB",
|
||||
size=image.size,
|
||||
text=question,
|
||||
)
|
||||
messages.append(message)
|
||||
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()
|
||||
@@ -4,25 +4,36 @@
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
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 LLMRunFrame
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
TextFrame,
|
||||
TTSSpeakFrame,
|
||||
UserImageRawFrame,
|
||||
UserImageRequestFrame,
|
||||
)
|
||||
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.user_response import UserResponseAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
get_transport_client_id,
|
||||
maybe_capture_participant_camera,
|
||||
)
|
||||
from pipecat.services.anthropic.llm import AnthropicLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
@@ -32,6 +43,49 @@ from pipecat.transports.daily.transport import DailyParams
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class UserImageRequester(FrameProcessor):
|
||||
"""Converts incoming text into requests for user images."""
|
||||
|
||||
def __init__(self, participant_id: Optional[str] = None):
|
||||
super().__init__()
|
||||
self._participant_id = participant_id
|
||||
|
||||
def set_participant_id(self, participant_id: str):
|
||||
self._participant_id = participant_id
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if self._participant_id and isinstance(frame, TextFrame):
|
||||
await self.push_frame(
|
||||
UserImageRequestFrame(self._participant_id, context=frame.text),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
class UserImageProcessor(FrameProcessor):
|
||||
"""Converts incoming user images into context frames."""
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, UserImageRawFrame):
|
||||
if frame.request and frame.request.context:
|
||||
context = LLMContext()
|
||||
context.add_image_frame_message(
|
||||
image=frame.image,
|
||||
text=frame.request.context,
|
||||
size=frame.size,
|
||||
format=frame.format,
|
||||
)
|
||||
frame = LLMContextFrame(context)
|
||||
await self.push_frame(frame)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
@@ -39,12 +93,14 @@ transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_in_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,
|
||||
video_in_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
@@ -54,34 +110,33 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
user_response = UserResponseAggregator()
|
||||
|
||||
# Initialize the image requester without setting the participant ID yet
|
||||
image_requester = UserImageRequester()
|
||||
|
||||
image_processor = UserImageProcessor()
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
# Anthropic for vision analysis
|
||||
anthropic = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_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. You are also able to describe images.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
transport.input(),
|
||||
stt,
|
||||
user_response,
|
||||
image_requester,
|
||||
image_processor,
|
||||
anthropic,
|
||||
tts,
|
||||
transport.output(),
|
||||
]
|
||||
)
|
||||
|
||||
@@ -96,28 +151,16 @@ 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(f"Client connected: {client}")
|
||||
|
||||
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",
|
||||
}
|
||||
await maybe_capture_participant_camera(transport, client)
|
||||
|
||||
image_path = runner_args.body["image_path"]
|
||||
question = runner_args.body["question"]
|
||||
# Set the participant ID in the image requester
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
image_requester.set_participant_id(client_id)
|
||||
|
||||
# Kick off the conversation.
|
||||
image = Image.open(image_path)
|
||||
message = await LLMContext.create_image_message(
|
||||
image=image.tobytes(),
|
||||
format="RGB",
|
||||
size=image.size,
|
||||
text=question,
|
||||
)
|
||||
messages.append(message)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
# Welcome message
|
||||
await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
@@ -5,23 +5,29 @@
|
||||
#
|
||||
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.adapters.schemas.function_schema import FunctionSchema
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
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, UserImageRequestFrame
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
TextFrame,
|
||||
TTSSpeakFrame,
|
||||
UserImageRawFrame,
|
||||
UserImageRequestFrame,
|
||||
)
|
||||
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.frame_processor import FrameDirection
|
||||
from pipecat.processors.aggregators.user_response import UserResponseAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
@@ -31,37 +37,54 @@ from pipecat.runner.utils import (
|
||||
from pipecat.services.aws.llm import AWSBedrockLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def fetch_user_image(params: FunctionCallParams):
|
||||
"""Fetch the user image and push it to the LLM.
|
||||
class UserImageRequester(FrameProcessor):
|
||||
"""Converts incoming text into requests for user images."""
|
||||
|
||||
When called, this function pushes a UserImageRequestFrame upstream to the
|
||||
transport. As a result, the transport will request the user image and push a
|
||||
UserImageRawFrame downstream which will be added to the context by the LLM
|
||||
assistant aggregator.
|
||||
"""
|
||||
user_id = params.arguments["user_id"]
|
||||
question = params.arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
|
||||
def __init__(self, participant_id: Optional[str] = None):
|
||||
super().__init__()
|
||||
self._participant_id = participant_id
|
||||
|
||||
# Request a user image frame and indicate that it should be added to the
|
||||
# context.
|
||||
await params.llm.push_frame(
|
||||
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
def set_participant_id(self, participant_id: str):
|
||||
self._participant_id = participant_id
|
||||
|
||||
await params.result_callback(None)
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
# Instead of None, it's possible to also provide a tool call answer to
|
||||
# tell the LLM that we are grabbing the image to analyze.
|
||||
# await params.result_callback({"result": "Image is being captured."})
|
||||
if self._participant_id and isinstance(frame, TextFrame):
|
||||
await self.push_frame(
|
||||
UserImageRequestFrame(self._participant_id, context=frame.text),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
class UserImageProcessor(FrameProcessor):
|
||||
"""Converts incoming user images into context frames."""
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, UserImageRawFrame):
|
||||
if frame.request and frame.request.context:
|
||||
# Note: AWS Bedrock does not yet support the universal LLMContext
|
||||
context = LLMContext()
|
||||
context.add_image_frame_message(
|
||||
image=frame.image,
|
||||
text=frame.request.context,
|
||||
size=frame.size,
|
||||
format=frame.format,
|
||||
)
|
||||
frame = LLMContextFrame(context)
|
||||
await self.push_frame(frame)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
@@ -88,15 +111,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
user_response = UserResponseAggregator()
|
||||
|
||||
# Initialize the image requester without setting the participant ID yet
|
||||
image_requester = UserImageRequester()
|
||||
|
||||
image_processor = UserImageProcessor()
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
# AWS for vision analysis
|
||||
llm = AWSBedrockLLMService(
|
||||
aws = AWSBedrockLLMService(
|
||||
aws_region="us-west-2",
|
||||
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
|
||||
# Note: usually, prefer providing latency="optimized" param.
|
||||
@@ -104,44 +129,22 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
# which we need for image input.
|
||||
params=AWSBedrockLLMService.InputParams(temperature=0.8),
|
||||
)
|
||||
llm.register_function("fetch_user_image", fetch_user_image)
|
||||
|
||||
fetch_image_function = FunctionSchema(
|
||||
name="fetch_user_image",
|
||||
description="Called when the user requests a description of their camera feed",
|
||||
properties={
|
||||
"user_id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the user to grab the image from",
|
||||
},
|
||||
"question": {
|
||||
"type": "string",
|
||||
"description": "The question that the user is asking about the image",
|
||||
},
|
||||
},
|
||||
required=["user_id", "question"],
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[fetch_image_function])
|
||||
|
||||
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. You are able to describe images from the user camera.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
transport.input(),
|
||||
stt,
|
||||
user_response,
|
||||
image_requester,
|
||||
image_processor,
|
||||
aws,
|
||||
tts,
|
||||
transport.output(),
|
||||
]
|
||||
)
|
||||
|
||||
@@ -162,15 +165,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Set the participant ID in the image requester
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
image_requester.set_participant_id(client_id)
|
||||
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
|
||||
}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
# Welcome message
|
||||
await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
@@ -48,7 +48,10 @@ 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 = CartesiaSTTService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
base_url=os.getenv("CARTESIA_BASE_URL"),
|
||||
)
|
||||
|
||||
tl = TranscriptionLogger()
|
||||
|
||||
|
||||
@@ -120,7 +120,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -4,6 +4,8 @@
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
@@ -15,13 +17,12 @@ 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, UserImageRequestFrame
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frame_processor import FrameDirection
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
@@ -38,30 +39,34 @@ from pipecat.transports.daily.transport import DailyParams
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def fetch_user_image(params: FunctionCallParams):
|
||||
"""Fetch the user image and push it to the LLM.
|
||||
# Global variable to store the client ID
|
||||
client_id = ""
|
||||
|
||||
When called, this function pushes a UserImageRequestFrame upstream to the
|
||||
transport. As a result, the transport will request the user image and push a
|
||||
UserImageRawFrame downstream which will be added to the context by the LLM
|
||||
assistant aggregator.
|
||||
"""
|
||||
user_id = params.arguments["user_id"]
|
||||
|
||||
async def get_weather(params: FunctionCallParams):
|
||||
location = params.arguments["location"]
|
||||
await params.result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
|
||||
|
||||
|
||||
async def get_image(params: FunctionCallParams):
|
||||
question = params.arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
|
||||
logger.debug(f"Requesting image with user_id={client_id}, question={question}")
|
||||
|
||||
# Request a user image frame and indicate that it should be added to the
|
||||
# context.
|
||||
await params.llm.push_frame(
|
||||
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
|
||||
FrameDirection.UPSTREAM,
|
||||
# Request the image frame
|
||||
await params.llm.request_image_frame(
|
||||
user_id=client_id,
|
||||
function_name=params.function_name,
|
||||
tool_call_id=params.tool_call_id,
|
||||
text_content=question,
|
||||
)
|
||||
|
||||
await params.result_callback(None)
|
||||
# Wait a short time for the frame to be processed
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
# Instead of None, it's possible to also provide a tool call answer to
|
||||
# tell the LLM that we are grabbing the image to analyze.
|
||||
# await params.result_callback({"result": "Image is being captured."})
|
||||
# Return a result to complete the function call
|
||||
await params.result_callback(
|
||||
f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
|
||||
)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
@@ -95,32 +100,70 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
# Anthropic for vision analysis
|
||||
llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
|
||||
llm.register_function("fetch_user_image", fetch_user_image)
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
model="claude-3-7-sonnet-latest",
|
||||
params=AnthropicLLMService.InputParams(enable_prompt_caching=True),
|
||||
)
|
||||
llm.register_function("get_weather", get_weather)
|
||||
llm.register_function("get_image", get_image)
|
||||
|
||||
fetch_image_function = FunctionSchema(
|
||||
name="fetch_user_image",
|
||||
description="Called when the user requests a description of their camera feed",
|
||||
weather_function = FunctionSchema(
|
||||
name="get_weather",
|
||||
description="Get the current weather",
|
||||
properties={
|
||||
"user_id": {
|
||||
"location": {
|
||||
"type": "string",
|
||||
"description": "The ID of the user to grab the image from",
|
||||
},
|
||||
"question": {
|
||||
"type": "string",
|
||||
"description": "The question that the user is asking about the image",
|
||||
"description": "The city and state, e.g. San Francisco, CA",
|
||||
},
|
||||
},
|
||||
required=["user_id", "question"],
|
||||
required=["location"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[fetch_image_function])
|
||||
get_image_function = FunctionSchema(
|
||||
name="get_image",
|
||||
description="Get an image from the video stream.",
|
||||
properties={
|
||||
"question": {
|
||||
"type": "string",
|
||||
"description": "The question that the user is asking about the image.",
|
||||
}
|
||||
},
|
||||
required=["question"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
|
||||
|
||||
system_prompt = """\
|
||||
You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
|
||||
|
||||
Your response will be turned into speech so use only simple words and punctuation.
|
||||
|
||||
You have access to two tools: get_weather and get_image.
|
||||
|
||||
You can respond to questions about the weather using the get_weather tool.
|
||||
|
||||
You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
|
||||
indicate you should use the get_image tool are:
|
||||
- What do you see?
|
||||
- What's in the video?
|
||||
- Can you describe the video?
|
||||
- Tell me about what you see.
|
||||
- Tell me something interesting about what you see.
|
||||
- What's happening in the video?
|
||||
|
||||
If you need to use a tool, simply use the tool. Do not tell the user the tool you are using. Be brief and concise.
|
||||
"""
|
||||
|
||||
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. You are able to describe images from the user camera.",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": system_prompt,
|
||||
}
|
||||
],
|
||||
},
|
||||
{"role": "user", "content": "Start the conversation by introducing yourself."},
|
||||
]
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
@@ -130,11 +173,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
context_aggregator.user(), # User speech to text
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
context_aggregator.assistant(), # Assistant spoken responses and tool context
|
||||
]
|
||||
)
|
||||
|
||||
@@ -153,16 +196,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
await maybe_capture_participant_camera(transport, client)
|
||||
|
||||
# Set the participant ID in the image requester
|
||||
global client_id
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
|
||||
}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
@@ -106,7 +106,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -1,224 +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.adapters.schemas.function_schema import FunctionSchema
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMFullResponseEndFrame,
|
||||
LLMFullResponseStartFrame,
|
||||
LLMRunFrame,
|
||||
TextFrame,
|
||||
UserImageRequestFrame,
|
||||
)
|
||||
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
get_transport_client_id,
|
||||
maybe_capture_participant_camera,
|
||||
)
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.moondream.vision import MoondreamService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def fetch_user_image(params: FunctionCallParams):
|
||||
"""Fetch the user image.
|
||||
|
||||
When called, this function pushes a UserImageRequestFrame upstream to the
|
||||
transport. As a result, the transport will request the user image and push a
|
||||
UserImageRawFrame downstream.
|
||||
"""
|
||||
user_id = params.arguments["user_id"]
|
||||
question = params.arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
|
||||
|
||||
# Request a user image frame. In this case, we don't want the requested
|
||||
# image to be added to the context because we will process it with
|
||||
# Moondream.
|
||||
await params.llm.push_frame(
|
||||
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=False),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
|
||||
await params.result_callback(None)
|
||||
|
||||
# Instead of None, it's possible to also provide a tool call answer to
|
||||
# tell the LLM that we are grabbing the image to analyze.
|
||||
# await params.result_callback({"result": "Image is being captured."})
|
||||
|
||||
|
||||
class MoondreamTextFrameWrapper(FrameProcessor):
|
||||
"""Wraps Moondream-provided TextFrames with LLM response start/end frames.
|
||||
|
||||
This processor detects TextFrames and automatically wraps them with
|
||||
LLMFullResponseStartFrame and LLMFullResponseEndFrame to provide proper
|
||||
response boundaries for downstream processors.
|
||||
"""
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
# If we receive a TextFrame, wrap it with response start/end frames
|
||||
if isinstance(frame, TextFrame):
|
||||
await self.push_frame(LLMFullResponseStartFrame(), direction)
|
||||
await self.push_frame(frame, direction)
|
||||
await self.push_frame(LLMFullResponseEndFrame(), direction)
|
||||
else:
|
||||
# For all other frames, just pass them through
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# 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,
|
||||
video_in_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,
|
||||
video_in_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm.register_function("fetch_user_image", fetch_user_image)
|
||||
|
||||
fetch_image_function = FunctionSchema(
|
||||
name="fetch_user_image",
|
||||
description="Called when the user requests a description of their camera feed",
|
||||
properties={
|
||||
"user_id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the user to grab the image from",
|
||||
},
|
||||
"question": {
|
||||
"type": "string",
|
||||
"description": "The question that the user is asking about the image",
|
||||
},
|
||||
},
|
||||
required=["user_id", "question"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[fetch_image_function])
|
||||
|
||||
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. You are able to describe images from the user camera.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
# If you run into weird description, try with use_cpu=True
|
||||
moondream = MoondreamService()
|
||||
|
||||
# Wrap TextFrames with LLM response start/end frames, which makes Moondream
|
||||
# output be treated like LLM responses for the purpose of context
|
||||
# aggregation. Without this, the assistant context aggregator would ignore
|
||||
# Moondream output (if the TTS service is disabled).
|
||||
moondream_text_wrapper = MoondreamTextFrameWrapper()
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
ParallelPipeline(
|
||||
[llm], # LLM
|
||||
[moondream, moondream_text_wrapper],
|
||||
),
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
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: {client}")
|
||||
|
||||
await maybe_capture_participant_camera(transport, client)
|
||||
|
||||
# Set the participant ID in the image requester
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
|
||||
}
|
||||
)
|
||||
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()
|
||||
@@ -1,186 +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.adapters.schemas.function_schema import FunctionSchema
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
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, UserImageRequestFrame
|
||||
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.frame_processor import FrameDirection
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
get_transport_client_id,
|
||||
maybe_capture_participant_camera,
|
||||
)
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def fetch_user_image(params: FunctionCallParams):
|
||||
"""Fetch the user image and push it to the LLM.
|
||||
|
||||
When called, this function pushes a UserImageRequestFrame upstream to the
|
||||
transport. As a result, the transport will request the user image and push a
|
||||
UserImageRawFrame downstream which will be added to the context by the LLM
|
||||
assistant aggregator.
|
||||
"""
|
||||
user_id = params.arguments["user_id"]
|
||||
question = params.arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
|
||||
|
||||
# Request a user image frame and indicate that it should be added to the
|
||||
# context.
|
||||
await params.llm.push_frame(
|
||||
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
|
||||
FrameDirection.UPSTREAM,
|
||||
)
|
||||
|
||||
await params.result_callback(None)
|
||||
|
||||
# Instead of None, it's possible to also provide a tool call answer to
|
||||
# tell the LLM that we are grabbing the image to analyze.
|
||||
# await params.result_callback({"result": "Image is being captured."})
|
||||
|
||||
|
||||
# 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,
|
||||
video_in_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,
|
||||
video_in_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm.register_function("fetch_user_image", fetch_user_image)
|
||||
|
||||
fetch_image_function = FunctionSchema(
|
||||
name="fetch_user_image",
|
||||
description="Called when the user requests a description of their camera feed",
|
||||
properties={
|
||||
"user_id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the user to grab the image from",
|
||||
},
|
||||
"question": {
|
||||
"type": "string",
|
||||
"description": "The question that the user is asking about the image",
|
||||
},
|
||||
},
|
||||
required=["user_id", "question"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[fetch_image_function])
|
||||
|
||||
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. You are able to describe images from the user camera.",
|
||||
},
|
||||
]
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
|
||||
await maybe_capture_participant_camera(transport, client)
|
||||
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
|
||||
}
|
||||
)
|
||||
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()
|
||||
@@ -4,8 +4,9 @@
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import time
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
@@ -16,31 +17,56 @@ 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, TTSSpeakFrame
|
||||
from pipecat.frames.frames import LLMRunFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.runner.utils import (
|
||||
create_transport,
|
||||
get_transport_client_id,
|
||||
maybe_capture_participant_camera,
|
||||
)
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openpipe.llm import OpenPipeLLMService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||||
await params.result_callback({"conditions": "nice", "temperature": "75"})
|
||||
# Global variable to store the client ID
|
||||
client_id = ""
|
||||
|
||||
|
||||
async def fetch_restaurant_recommendation(params: FunctionCallParams):
|
||||
await params.result_callback({"name": "The Golden Dragon"})
|
||||
async def get_weather(params: FunctionCallParams):
|
||||
location = params.arguments["location"]
|
||||
await params.result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
|
||||
|
||||
|
||||
async def get_image(params: FunctionCallParams):
|
||||
question = params.arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={client_id}, question={question}")
|
||||
|
||||
# Request the image frame
|
||||
await params.llm.request_image_frame(
|
||||
user_id=client_id,
|
||||
function_name=params.function_name,
|
||||
tool_call_id=params.tool_call_id,
|
||||
text_content=question,
|
||||
)
|
||||
|
||||
# Wait a short time for the frame to be processed
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
# Return a result to complete the function call
|
||||
await params.result_callback(
|
||||
f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
|
||||
)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
@@ -50,18 +76,14 @@ 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,
|
||||
video_in_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,
|
||||
video_in_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
@@ -78,24 +100,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
timestamp = int(time.time())
|
||||
llm = OpenPipeLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
|
||||
tags={"conversation_id": f"pipecat-{timestamp}"},
|
||||
)
|
||||
|
||||
# You can also register a function_name of None to get all functions
|
||||
# sent to the same callback with an additional function_name parameter.
|
||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
|
||||
|
||||
@llm.event_handler("on_function_calls_started")
|
||||
async def on_function_calls_started(service, function_calls):
|
||||
await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm.register_function("get_weather", get_weather)
|
||||
llm.register_function("get_image", get_image)
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_current_weather",
|
||||
name="get_weather",
|
||||
description="Get the current weather",
|
||||
properties={
|
||||
"location": {
|
||||
@@ -108,26 +118,41 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"description": "The temperature unit to use. Infer this from the user's location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
)
|
||||
restaurant_function = FunctionSchema(
|
||||
name="get_restaurant_recommendation",
|
||||
description="Get a restaurant recommendation",
|
||||
properties={
|
||||
"location": {
|
||||
"type": "string",
|
||||
"description": "The city and state, e.g. San Francisco, CA",
|
||||
},
|
||||
},
|
||||
required=["location"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
|
||||
|
||||
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.",
|
||||
get_image_function = FunctionSchema(
|
||||
name="get_image",
|
||||
description="Get an image from the video stream.",
|
||||
properties={
|
||||
"question": {
|
||||
"type": "string",
|
||||
"description": "The question that the user is asking about the image.",
|
||||
}
|
||||
},
|
||||
required=["question"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
|
||||
|
||||
system_prompt = """\
|
||||
You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
|
||||
|
||||
Your response will be turned into speech so use only simple words and punctuation.
|
||||
|
||||
You have access to two tools: get_weather and get_image.
|
||||
|
||||
You can respond to questions about the weather using the get_weather tool.
|
||||
|
||||
You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
|
||||
indicate you should use the get_image tool are:
|
||||
- What do you see?
|
||||
- What's in the video?
|
||||
- Can you describe the video?
|
||||
- Tell me about what you see.
|
||||
- Tell me something interesting about what you see.
|
||||
- What's happening in the video?
|
||||
"""
|
||||
messages = [
|
||||
{"role": "system", "content": system_prompt},
|
||||
]
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
@@ -157,6 +182,12 @@ 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")
|
||||
|
||||
await maybe_capture_participant_camera(transport, client)
|
||||
|
||||
global client_id
|
||||
client_id = get_transport_client_id(transport, client)
|
||||
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@@ -104,7 +104,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -99,7 +99,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -107,7 +107,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
llm = FireworksLLMService(
|
||||
api_key=os.getenv("FIREWORKS_API_KEY"),
|
||||
model="accounts/fireworks/models/gpt-oss-20b",
|
||||
model="accounts/fireworks/models/llama-v3p1-405b-instruct",
|
||||
)
|
||||
# You can also register a function_name of None to get all functions
|
||||
# sent to the same callback with an additional function_name parameter.
|
||||
@@ -110,7 +110,7 @@ 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. Start by saying hello.",
|
||||
"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. Start by saying hello.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -27,7 +27,7 @@ from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.nvidia.llm import NvidiaLLMService
|
||||
from pipecat.services.nim.llm import NimLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
@@ -75,12 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
# text_filters=[MarkdownTextFilter()],
|
||||
)
|
||||
|
||||
llm = NvidiaLLMService(
|
||||
api_key=os.getenv("NVIDIA_API_KEY"),
|
||||
model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
|
||||
# Recommended when turning thinking off
|
||||
params=NvidiaLLMService.InputParams(temperature=0.0),
|
||||
)
|
||||
llm = NimLLMService(api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.3-70b-instruct")
|
||||
# You can also register a function_name of None to get all functions
|
||||
# sent to the same callback with an additional function_name parameter.
|
||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||
@@ -107,12 +102,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[weather_function])
|
||||
messages = [
|
||||
# Disable thinking by sending this message first
|
||||
# Check the model for the corresponding "no thinking" message
|
||||
{"role": "system", "content": "/no_think"},
|
||||
{
|
||||
"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.",
|
||||
},
|
||||
]
|
||||
|
||||
@@ -107,7 +107,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"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, but try to be brief.",
|
||||
"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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -105,7 +105,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -79,8 +79,8 @@ 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"),
|
||||
)
|
||||
|
||||
# You can also register a function_name of None to get all functions
|
||||
@@ -120,7 +120,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -110,7 +110,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -106,7 +106,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -122,7 +122,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -128,7 +128,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@@ -116,7 +116,7 @@ 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.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user