d3021b4590
Example files like openai.py shadow installed packages when Python adds the script directory to sys.path. Prepend the parent folder name to each example file (e.g. openai.py -> function-calling-openai.py). Also split thinking-and-mcp/ into separate mcp/ and thinking/ directories.
249 lines
8.3 KiB
Python
249 lines
8.3 KiB
Python
#
|
|
# Copyright (c) 2024-2026, 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.vad.silero import SileroVADAnalyzer
|
|
from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame, 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,
|
|
LLMUserAggregatorParams,
|
|
)
|
|
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.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 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 fetch_restaurant_recommendation(params: FunctionCallParams):
|
|
await params.result_callback({"name": "The Golden Dragon"})
|
|
|
|
|
|
async def get_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. The result_callback will be invoked once the image is
|
|
retrieved and processed.
|
|
"""
|
|
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. Also associate it to the function call. Pass the result_callback
|
|
# so it can be invoked when the image is actually retrieved.
|
|
await params.llm.push_frame(
|
|
UserImageRequestFrame(
|
|
user_id=user_id,
|
|
text=question,
|
|
append_to_context=True,
|
|
function_name=params.function_name,
|
|
tool_call_id=params.tool_call_id,
|
|
result_callback=params.result_callback,
|
|
),
|
|
FrameDirection.UPSTREAM,
|
|
)
|
|
|
|
|
|
# We use lambdas to defer transport parameter creation until the transport
|
|
# type is selected at runtime.
|
|
transport_params = {
|
|
"daily": lambda: DailyParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
video_in_enabled=True,
|
|
),
|
|
"webrtc": lambda: TransportParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
video_in_enabled=True,
|
|
),
|
|
}
|
|
|
|
|
|
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"),
|
|
settings=CartesiaTTSService.Settings(
|
|
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
|
),
|
|
)
|
|
|
|
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 three tools: get_weather, get_restaurant_recommendation, 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?
|
|
"""
|
|
|
|
llm = GoogleLLMService(
|
|
api_key=os.getenv("GOOGLE_API_KEY"),
|
|
settings=GoogleLLMService.Settings(
|
|
system_instruction=system_prompt,
|
|
),
|
|
)
|
|
llm.register_function("get_weather", get_weather)
|
|
llm.register_function("get_image", get_image)
|
|
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."))
|
|
|
|
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",
|
|
},
|
|
"format": {
|
|
"type": "string",
|
|
"enum": ["celsius", "fahrenheit"],
|
|
"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"],
|
|
)
|
|
get_image_function = FunctionSchema(
|
|
name="get_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=[weather_function, get_image_function, restaurant_function])
|
|
|
|
context = LLMContext(tools=tools)
|
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
context,
|
|
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
|
)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
stt,
|
|
user_aggregator,
|
|
llm,
|
|
tts,
|
|
transport.output(),
|
|
assistant_aggregator,
|
|
]
|
|
)
|
|
|
|
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: {client}")
|
|
|
|
await maybe_capture_participant_camera(transport, client)
|
|
|
|
client_id = get_transport_client_id(transport, client)
|
|
|
|
# Kick off the conversation.
|
|
context.add_message(
|
|
{
|
|
"role": "developer",
|
|
"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()
|