Add quickstart demos

This commit is contained in:
Mark Backman
2025-07-30 22:11:40 -04:00
parent aa85fffa57
commit 226b516948
29 changed files with 3718 additions and 4 deletions

164
examples/phone-bot-twilio/.gitignore vendored Normal file
View File

@@ -0,0 +1,164 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
runpod.toml
# Examples
templates/streams.xml

View File

@@ -0,0 +1,116 @@
# Phone Bot Twilio
Learn how to connect your Pipecat bot to a phone number so users can call and have voice conversations. This example shows the complete setup for telephone-based AI interactions using Twilio's telephony services. At the end, you'll be able to talk to your bot on the phone.
## Prerequisites
- Python 3.10+
- [ngrok](https://ngrok.com/docs/getting-started/) (for tunneling)
- [Twilio Account](https://www.twilio.com/login) and [phone number](https://help.twilio.com/articles/223135247-How-to-Search-for-and-Buy-a-Twilio-Phone-Number-from-Console)
- AI Service API keys for: [Deepgram](https://console.deepgram.com/signup), [OpenAI](https://auth.openai.com/create-account), and [Cartesia](https://play.cartesia.ai/sign-up)
## Setup
This example requires running both a server and ngrok tunnel in **two separate terminal windows**.
### Terminal 1: Start ngrok and Configure Twilio
1. Start ngrok:
In a new terminal, start ngrok to tunnel the local server:
```bash
ngrok http 7860
```
> Want a fixed ngrok URL? Use the `--subdomain` flag:
> `ngrok http --subdomain=your_ngrok_name 7860`
2. Update the Twilio Webhook:
- Go to your Twilio phone number's configuration page
- Under "Voice Configuration", in the "A call comes in" section:
- Select "Webhook" from the dropdown
- Enter your ngrok URL: `https://your-ngrok-url.ngrok.io`
- Ensure "HTTP POST" is selected
- Click Save at the bottom of the page
3. Configure streams.xml:
- Copy the template file to create your local version:
```bash
cp templates/streams.xml.template templates/streams.xml
```
- In `templates/streams.xml`, replace `<your_server_url>` with your ngrok URL (without `https://`)
- The final URL should look like: `wss://abc123.ngrok.io/ws`
### Terminal 2: Server Setup
1. Set up a virtual environment
From the `examples/phone-bot-twilio` directory, run:
```bash
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
```
> Using `uv`? Create your venv using: `uv venv && source .venv/bin/activate`.
2. Install dependencies
```bash
pip install -r requirements.txt
```
> Using `uv`? Install requirements using: `uv pip install -r requirements.txt`.
3. Configure environment variables
Create a `.env` file:
```bash
cp env.example .env
```
Then, add your API keys:
```
DEEPGRAM_API_KEY=your_deepgram_api_key
OPENAI_API_KEY=your_openai_api_key
CARTESIA_API_KEY=your_cartesia_api_key
```
> Optional: Add your `TWILIO_ACCOUNT_SID` and `TWILIO_AUTH_TOKEN` to enable auto-hangup.
4. Run the Application
```bash
python server.py
```
### Test Your Phone Bot
**Call your Twilio phone number** to start talking with your AI bot! 🚀
> 💡 **Tip**: Check your server terminal for debug logs showing Pipecat's internal workings.
## Troubleshooting
- **Call doesn't connect**: Verify your ngrok URL is correctly set in both Twilio webhook and `streams.xml`
- **No audio or bot doesn't respond**: Check that all API keys are correctly set in your `.env` file
- **Webhook errors**: Ensure your server is running and ngrok tunnel is active before making calls
- **ngrok tunnel issues**: Free ngrok URLs change each restart - remember to update both Twilio and `streams.xml`
## Understanding the Call Flow
1. **Incoming Call**: User dials your Twilio number
2. **Webhook**: Twilio sends call data to your ngrok URL
3. **WebSocket**: Your server establishes real-time audio connection via Websocket and exchanges Media Streams with Twilio
4. **Processing**: Audio flows through your Pipecat Pipeline
5. **Response**: Synthesized speech streams back to caller
## Next Steps
- **Deploy to production**: Replace ngrok with a proper server deployment
- **Explore other telephony providers**: Try [Telnyx](https://github.com/pipecat-ai/pipecat-examples/tree/main/telnyx-chatbot) or [Plivo](https://github.com/pipecat-ai/pipecat-examples/tree/main/plivo-chatbot) examples
- **Advanced telephony features**: Check out [pipecat-examples](https://github.com/pipecat-ai/pipecat-examples) for call recording, transfer, and more
- **Join Discord**: Connect with other developers on [Discord](https://discord.gg/pipecat)

View File

@@ -0,0 +1,144 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
"""Pipecat Twilio Phone Example.
The example runs a simple voice AI bot that you can connect to using a
phone via Twilio.
Required AI services:
- Deepgram (Speech-to-Text)
- OpenAI (LLM)
- Cartesia (Text-to-Speech)
The example connects between client and server using a Twilio websocket
connection.
Run the bot using::
python bot.py -t twilio -x your_ngrok.ngrok.io
"""
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import parse_telephony_websocket
from pipecat.serializers.twilio import TwilioFrameSerializer
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
from pipecat.transports.network.fastapi_websocket import (
FastAPIWebsocketParams,
FastAPIWebsocketTransport,
)
load_dotenv(override=True)
async def run_bot(transport: BaseTransport):
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 friendly AI assistant. Respond naturally and keep your answers conversational.",
},
]
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
pipeline = Pipeline(
[
transport.input(), # Transport user input
rtvi, # RTVI processor
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,
),
observers=[RTVIObserver(rtvi)],
)
@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 hello and briefly introduce yourself."})
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
async def bot(runner_args: RunnerArguments):
"""Main bot entry point for the bot starter."""
transport_type, call_data = await parse_telephony_websocket(runner_args.websocket)
logger.info(f"Auto-detected transport: {transport_type}")
serializer = TwilioFrameSerializer(
stream_sid=call_data["stream_id"],
call_sid=call_data["call_id"],
account_sid=os.getenv("TWILIO_ACCOUNT_SID", ""),
auth_token=os.getenv("TWILIO_AUTH_TOKEN", ""),
)
transport = FastAPIWebsocketTransport(
websocket=runner_args.websocket,
params=FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
add_wav_header=False,
vad_analyzer=SileroVADAnalyzer(),
serializer=serializer,
),
)
await run_bot(transport)
if __name__ == "__main__":
from pipecat.runner.run import main
main()

View File

@@ -0,0 +1,3 @@
OPENAI_API_KEY=
DEEPGRAM_API_KEY=
CARTESIA_API_KEY=

View File

@@ -0,0 +1 @@
pipecat-ai[cartesia,openai,silero,deepgram,websocket,runner]

View File

@@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<Response>
<Connect>
<Stream url="wss://<your_server_url>/ws"></Stream>
</Connect>
<Pause length="40"/>
</Response>