250 lines
8.7 KiB
Python
250 lines
8.7 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import argparse
|
||
import glob
|
||
import json
|
||
import os
|
||
from datetime import datetime
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||
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.anthropic.llm import AnthropicLLMService
|
||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.llm_service import FunctionCallParams
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||
from pipecat.transports.services.daily import DailyParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||
tts = None
|
||
|
||
|
||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||
temperature = 75 if params.arguments["format"] == "fahrenheit" else 24
|
||
await params.result_callback(
|
||
{
|
||
"conditions": "nice",
|
||
"temperature": temperature,
|
||
"format": params.arguments["format"],
|
||
"timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
|
||
}
|
||
)
|
||
|
||
|
||
async def get_saved_conversation_filenames(params: FunctionCallParams):
|
||
# Construct the full pattern including the BASE_FILENAME
|
||
full_pattern = f"{BASE_FILENAME}*.json"
|
||
|
||
# Use glob to find all matching files
|
||
matching_files = glob.glob(full_pattern)
|
||
logger.debug(f"matching files: {matching_files}")
|
||
|
||
await params.result_callback({"filenames": matching_files})
|
||
|
||
|
||
async def save_conversation(params: FunctionCallParams):
|
||
timestamp = datetime.now().strftime("%Y-%m-%d_%H:%M:%S")
|
||
filename = f"{BASE_FILENAME}{timestamp}.json"
|
||
logger.debug(
|
||
f"writing conversation to {filename}\n{json.dumps(params.context.messages, indent=4)}"
|
||
)
|
||
try:
|
||
with open(filename, "w") as file:
|
||
# todo: extract 'system' into the first message in the list
|
||
messages = params.context.get_messages_for_persistent_storage()
|
||
# remove the last message, which is the instruction we just gave to save the conversation
|
||
messages.pop()
|
||
json.dump(messages, file, indent=2)
|
||
await params.result_callback({"success": True})
|
||
except Exception as e:
|
||
await params.result_callback({"success": False, "error": str(e)})
|
||
|
||
|
||
async def load_conversation(params: FunctionCallParams):
|
||
global tts
|
||
filename = params.arguments["filename"]
|
||
logger.debug(f"loading conversation from {filename}")
|
||
try:
|
||
with open(filename, "r") as file:
|
||
params.context.set_messages(json.load(file))
|
||
logger.debug(
|
||
f"loaded conversation from {filename}\n{json.dumps(params.context.messages, indent=4)}"
|
||
)
|
||
await tts.say("Ok, I've loaded that conversation.")
|
||
except Exception as e:
|
||
await params.result_callback({"success": False, "error": str(e)})
|
||
|
||
|
||
# Test message munging ...
|
||
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 succinct, creative and helpful way. Prefer responses that are one sentence long unless you are asked for a longer or more detailed response.",
|
||
},
|
||
{"role": "user", "content": "Start the call by saying the word 'hello'. Say only that word."},
|
||
# {"role": "user", "content": ""},
|
||
# {"role": "assistant", "content": []},
|
||
# {"role": "user", "content": "Tell me"},
|
||
# {"role": "user", "content": "a joke"},
|
||
]
|
||
tools = [
|
||
{
|
||
"name": "get_current_weather",
|
||
"description": "Get the current weather",
|
||
"input_schema": {
|
||
"type": "object",
|
||
"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 users location.",
|
||
},
|
||
},
|
||
"required": ["location", "format"],
|
||
},
|
||
},
|
||
{
|
||
"name": "save_conversation",
|
||
"description": "Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||
"input_schema": {
|
||
"type": "object",
|
||
"properties": {},
|
||
"required": [],
|
||
},
|
||
},
|
||
{
|
||
"name": "get_saved_conversation_filenames",
|
||
"description": "Get a list of saved conversation histories. Returns a list of filenames. Each filename includes a date and timestamp. Each file is conversation history that can be loaded into this session.",
|
||
"input_schema": {
|
||
"type": "object",
|
||
"properties": {},
|
||
"required": [],
|
||
},
|
||
},
|
||
{
|
||
"name": "load_conversation",
|
||
"description": "Load a conversation history. Use this function to load a conversation history into the current session.",
|
||
"input_schema": {
|
||
"type": "object",
|
||
"properties": {
|
||
"filename": {
|
||
"type": "string",
|
||
"description": "The filename of the conversation history to load.",
|
||
}
|
||
},
|
||
"required": ["filename"],
|
||
},
|
||
},
|
||
]
|
||
|
||
|
||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||
# instantiated. The function will be called when the desired transport gets
|
||
# selected.
|
||
transport_params = {
|
||
"daily": lambda: DailyParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),
|
||
),
|
||
"twilio": lambda: FastAPIWebsocketParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),
|
||
),
|
||
}
|
||
|
||
|
||
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
|
||
logger.info(f"Starting bot")
|
||
|
||
global tts
|
||
|
||
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-3-5-sonnet-latest"
|
||
)
|
||
|
||
# you can either register a single function for all function calls, or specific functions
|
||
# llm.register_function(None, fetch_weather_from_api)
|
||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||
llm.register_function("save_conversation", save_conversation)
|
||
llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
|
||
llm.register_function("load_conversation", load_conversation)
|
||
|
||
context = OpenAILLMContext(messages, tools)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
stt, # STT
|
||
context_aggregator.user(),
|
||
llm, # LLM
|
||
tts,
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(),
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
# Kick off the conversation.
|
||
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=handle_sigint)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from pipecat.examples.run import main
|
||
|
||
main(run_example, transport_params=transport_params)
|