Updating foundation examples to use SmallWebRTCTransport and pipecat-ai-small-webrtc-prebuilt (#1534)
Co-authored-by: Filipi Fuchter <filipi@daily.co>
This commit is contained in:
Mark Backman
@@ -6,12 +6,9 @@
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from runner import configure
|
||||
|
||||
from pipecat.adapters.schemas.function_schema import FunctionSchema
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
@@ -22,14 +19,16 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.services.anthropic.llm import AnthropicLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
|
||||
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
video_participant_id = None
|
||||
# Global variable to store the peer connection ID
|
||||
webrtc_peer_id = None
|
||||
|
||||
|
||||
async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
|
||||
@@ -39,72 +38,83 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu
|
||||
|
||||
async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
|
||||
question = arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={webrtc_peer_id}, question={question}")
|
||||
|
||||
# Request the image frame
|
||||
await llm.request_image_frame(
|
||||
user_id=video_participant_id,
|
||||
user_id=webrtc_peer_id,
|
||||
function_name=function_name,
|
||||
tool_call_id=tool_call_id,
|
||||
text_content=question,
|
||||
)
|
||||
|
||||
# Wait a short time for the frame to be processed
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
async def main():
|
||||
global llm
|
||||
# Return a result to complete the function call
|
||||
await result_callback(
|
||||
f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
|
||||
)
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, token) = await configure(session)
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
async def run_bot(webrtc_connection: SmallWebRTCConnection):
|
||||
global webrtc_peer_id
|
||||
webrtc_peer_id = webrtc_connection.pc_id
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
model="claude-3-7-sonnet-latest",
|
||||
enable_prompt_caching_beta=True,
|
||||
)
|
||||
llm.register_function("get_weather", get_weather)
|
||||
llm.register_function("get_image", get_image)
|
||||
transport = SmallWebRTCTransport(
|
||||
webrtc_connection=webrtc_connection,
|
||||
params=TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
camera_in_enabled=True, # Make sure camera input is enabled
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
vad_audio_passthrough=True,
|
||||
),
|
||||
)
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_weather",
|
||||
description="Get the current weather",
|
||||
properties={
|
||||
"location": {
|
||||
"type": "string",
|
||||
"description": "The city and state, e.g. San Francisco, CA",
|
||||
},
|
||||
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 = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
model="claude-3-7-sonnet-latest",
|
||||
enable_prompt_caching_beta=True,
|
||||
)
|
||||
llm.register_function("get_weather", get_weather)
|
||||
llm.register_function("get_image", get_image)
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_weather",
|
||||
description="Get the current weather",
|
||||
properties={
|
||||
"location": {
|
||||
"type": "string",
|
||||
"description": "The city and state, e.g. San Francisco, CA",
|
||||
},
|
||||
required=["location"],
|
||||
)
|
||||
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])
|
||||
},
|
||||
required=["location"],
|
||||
)
|
||||
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])
|
||||
|
||||
# todo: test with very short initial user message
|
||||
|
||||
system_prompt = """\
|
||||
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.
|
||||
@@ -115,63 +125,73 @@ 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?
|
||||
- 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": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": system_prompt,
|
||||
}
|
||||
],
|
||||
},
|
||||
{"role": "user", "content": "Start the conversation by introducing yourself."},
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": system_prompt,
|
||||
}
|
||||
],
|
||||
},
|
||||
{"role": "user", "content": "Start the conversation by introducing yourself."},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User speech to text
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses and tool context
|
||||
]
|
||||
)
|
||||
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
context_aggregator.user(), # User speech to text
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses and tool context
|
||||
]
|
||||
)
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected: {client}")
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
),
|
||||
)
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
global video_participant_id
|
||||
video_participant_id = participant["id"]
|
||||
await transport.capture_participant_transcription(video_participant_id)
|
||||
await transport.capture_participant_video(video_participant_id, framerate=0)
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
@transport.event_handler("on_client_closed")
|
||||
async def on_client_closed(transport, client):
|
||||
logger.info(f"Client closed connection")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner()
|
||||
await runner.run(task)
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
from run import main
|
||||
|
||||
main()
|
||||
|
||||
Reference in New Issue
Block a user