wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update with latest starter

Browse Source
This commit is contained in:
Mark Backman
2025-03-14 20:37:55 -04:00
parent 24220f38f0
commit d3cd1a6c59
3 changed files with 101 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
examples/deployment/pipecat-cloud-example/README.md
View File

@@ -4,6 +4,8 @@
A template voice agent for [Pipecat Cloud](https://www.daily.co/products/pipecat-cloud/) that demonstrates building and deploying a conversational AI agent. A template voice agent for [Pipecat Cloud](https://www.daily.co/products/pipecat-cloud/) that demonstrates building and deploying a conversational AI agent.
> **For a detailed step-by-step guide, see our [Quickstart Documentation](https://docs.pipecat.daily.co/quickstart).**
## Prerequisites ## Prerequisites
- Python 3.10+ - Python 3.10+
@@ -14,25 +16,9 @@ A template voice agent for [Pipecat Cloud](https://www.daily.co/products/pipecat
> **Note**: If you haven't installed Docker yet, follow the official installation guides for your platform ([Linux](https://docs.docker.com/engine/install/), [Mac](https://docs.docker.com/desktop/setup/install/mac-install/), [Windows](https://docs.docker.com/desktop/setup/install/windows-install/)). For Docker Hub, [create a free account](https://hub.docker.com/signup) and log in via terminal with `docker login`. > **Note**: If you haven't installed Docker yet, follow the official installation guides for your platform ([Linux](https://docs.docker.com/engine/install/), [Mac](https://docs.docker.com/desktop/setup/install/mac-install/), [Windows](https://docs.docker.com/desktop/setup/install/windows-install/)). For Docker Hub, [create a free account](https://hub.docker.com/signup) and log in via terminal with `docker login`.
## Getting Started ## Get Started
### 1. Set up Python environment ### 1. Get the starter project
We recommend using a virtual environment to manage your Python dependencies.
```bash
# Create a virtual environment
python -m venv venv
# Activate it
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
pip install pipecatcloud
```
### 2. Get the starter project
Clone the starter project from GitHub: Clone the starter project from GitHub:
@@ -41,11 +27,19 @@ git clone https://github.com/daily-co/pipecat-cloud-starter
cd pipecat-cloud-starter cd pipecat-cloud-starter
``` ```
or use the Pipecat Cloud CLI to initialize a new project: ### 2. Set up your Python environment
We recommend using a virtual environment to manage your Python dependencies.
```bash ```bash
mkdir pipecat-cloud-starter && cd pipecat-cloud-starter # Create a virtual environment
pcc init python -m venv .venv
# Activate it
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install the Pipecat Cloud CLI
pip install pipecatcloud
``` ```
### 3. Authenticate with Pipecat Cloud ### 3. Authenticate with Pipecat Cloud
@@ -66,13 +60,24 @@ This starter requires the following API keys:
You can test your agent locally before deploying to Pipecat Cloud: You can test your agent locally before deploying to Pipecat Cloud:
- `DAILY_API_KEY` value can be found at [https://pipecat.daily.co](https://pipecat.daily.co) Under the `Settings` menu of your agent, in the `Daily` tab.
```bash ```bash
# Set environment variables with your API keys # Set environment variables with your API keys
export CARTESIA_API_KEY="your_cartesia_key" export CARTESIA_API_KEY="your_cartesia_key"
export DAILY_API_KEY="your_daily_key" export DAILY_API_KEY="your_daily_key"
export OPENAI_API_KEY="your_openai_key" export OPENAI_API_KEY="your_openai_key"
```
> Your `DAILY_API_KEY` can be found at [https://pipecat.daily.co](https://pipecat.daily.co) under the `Settings` in the `Daily (WebRTC)` tab.
First install requirements:
```bash
pip install -r requirements.txt
```
Then, launch the bot.py script locally:
```bash
LOCAL_RUN=1 python bot.py LOCAL_RUN=1 python bot.py
``` ```
@@ -118,7 +123,7 @@ pcc secrets set my-first-agent-secrets \
### 3. Deploy to Pipecat Cloud ### 3. Deploy to Pipecat Cloud
```bash ```bash
pcc deploy my-first-agent your-username/my-first-agent:0.1 pcc deploy my-first-agent your-username/my-first-agent:0.1 --secrets my-first-agent-secrets
``` ```
> **Note (Optional)**: For a more maintainable approach, you can use the included `pcc-deploy.toml` file: > **Note (Optional)**: For a more maintainable approach, you can use the included `pcc-deploy.toml` file:
@@ -137,7 +142,7 @@ pcc deploy my-first-agent your-username/my-first-agent:0.1
> **Note**: If your repository is private, you'll need to add credentials: > **Note**: If your repository is private, you'll need to add credentials:
> >
> ```bash > ```bash
> # Create pull secret (you'll be prompted for credentials) > # Create pull secret (you’ll be prompted for credentials)
> pcc secrets image-pull-secret pull-secret https://index.docker.io/v1/ > pcc secrets image-pull-secret pull-secret https://index.docker.io/v1/
> >
> # Deploy with credentials > # Deploy with credentials

144
examples/deployment/pipecat-cloud-example/bot.py
View File

@@ -9,6 +9,7 @@ import os
import aiohttp import aiohttp
from dotenv import load_dotenv from dotenv import load_dotenv
from loguru import logger from loguru import logger
from pipecatcloud.agent import DailySessionArguments
from pipecat.audio.vad.silero import SileroVADAnalyzer from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame from pipecat.frames.frames import LLMMessagesFrame
@@ -35,110 +36,103 @@ if LOCAL_RUN:
load_dotenv(override=True) load_dotenv(override=True)
async def main(room_url: str, token: str, session_logger=None): async def main(room_url: str, token: str):
"""Main pipeline setup and execution function. """Main pipeline setup and execution function.
Args: Args:
room_url: The Daily room URL room_url: The Daily room URL
token: The Daily room token token: The Daily room token
session_logger: Optional logger instance
""" """
log = session_logger or logger logger.debug("Starting bot in room: {}", room_url)
log.debug("Starting bot in room: {}", room_url) transport = DailyTransport(
room_url,
token,
"bot",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
async with aiohttp.ClientSession() as session: tts = CartesiaTTSService(
transport = DailyTransport( api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
room_url, )
token,
"bot",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
tts = CartesiaTTSService( llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o") messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
messages = [ context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
logger.info("First participant joined: {}", participant["id"])
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{ {
"role": "system", "role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.", "content": "Please start with 'Hello World' and introduce yourself to the user.",
}, }
]
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
) )
await task.queue_frames([LLMMessagesFrame(messages)])
task = PipelineTask( @transport.event_handler("on_participant_left")
pipeline, async def on_participant_left(transport, participant, reason):
params=PipelineParams( logger.info("Participant left: {}", participant)
allow_interruptions=True, await task.cancel()
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)
@transport.event_handler("on_first_participant_joined") runner = PipelineRunner()
async def on_first_participant_joined(transport, participant):
log.info("First participant joined: {}", participant["id"])
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{
"role": "system",
"content": "Please start with 'Hello World' and introduce yourself to the user.",
}
)
await task.queue_frames([LLMMessagesFrame(messages)])
@transport.event_handler("on_participant_left") await runner.run(task)
async def on_participant_left(transport, participant, reason):
log.info("Participant left: {}", participant)
await task.cancel()
runner = PipelineRunner()
await runner.run(task)
async def bot(config, room_url: str, token: str, session_id=None, session_logger=None): async def bot(args: DailySessionArguments):
"""Main bot entry point compatible with the FastAPI route handler. """Main bot entry point compatible with the FastAPI route handler.
Args: Args:
config: The configuration object from the request body
room_url: The Daily room URL room_url: The Daily room URL
token: The Daily room token token: The Daily room token
body: The configuration object from the request body
session_id: The session ID for logging session_id: The session ID for logging
session_logger: The session-specific logger
""" """
log = session_logger or logger logger.info(f"Bot process initialized {args.room_url} {args.token}")
log.info(f"Bot process initialized {room_url} {token}")
log.info(f"Bot config {config}")
try: try:
await main(room_url, token, session_logger) await main(args.room_url, args.token)
log.info("Bot process completed") logger.info("Bot process completed")
except Exception as e: except Exception as e:
log.exception(f"Error in bot process: {str(e)}") logger.exception(f"Error in bot process: {str(e)}")
raise raise

1
examples/deployment/pipecat-cloud-example/requirements.txt
View File

@@ -1,2 +1,3 @@
pipecatcloud
pipecat-ai[cartesia,daily,openai,silero]>=0.0.58 pipecat-ai[cartesia,daily,openai,silero]>=0.0.58
python-dotenv~=1.0.1 python-dotenv~=1.0.1