Files
pipecat/examples/foundational/14r-function-calling-mcp-client.py
2025-04-10 15:21:29 -05:00

111 lines
3.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
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
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.services.cartesia.tts import CartesiaTTSService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.services.mcp_run.mcp_run import MCPRun
from pipecat.services.anthropic.llm import AnthropicLLMService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.openai.llm import OpenAILLMService
load_dotenv(override=True)
logger.remove()
logger.add(sys.stderr, level="DEBUG")
async def main():
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Bot with MCP tools",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
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")
# llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
# llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
mcp_run = MCPRun(llm)
tools = mcp_run.register_mcp_tools(llm)
system = """
You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities
in a succinct way. You have access to various tools provided by mcp.run that you can use to help users.
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. Don't overexplain what you are doing.
Just respond with short sentences when you are carrying out tool calls.
"""
messages = [{"role": "system","content": system}]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
context_aggregator.user(), # User spoken responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses and tool context
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=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.
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())