Reorganize examples into topic-based subfolders
Move 304 examples from a flat numbered directory into 14 descriptive subfolders: getting-started, services (speech + function-calling), transcription, vision, realtime, persistent-context, context-summarization, update-settings (stt/tts/llm), turn-management, thinking-and-mcp, transports, video-avatar, video-processing, and features. Strip numbered prefixes from filenames (e.g. 07c-interruptible-deepgram.py becomes services/speech/deepgram.py) since the folder context makes them redundant. Keep numbered prefixes only in getting-started/ where ordering matters. Update eval script paths and README to match the new structure.
This commit is contained in:
Mark Backman
254
examples/persistent-context/anthropic.py
Normal file
254
examples/persistent-context/anthropic.py
Normal file
@@ -0,0 +1,254 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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
|
||||
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.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
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.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# 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):
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
await params.llm.queue_frame(TTSSpeakFrame("Ok, I've loaded that conversation."))
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
|
||||
system_instruction = "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. 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."
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_current_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 users location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
)
|
||||
|
||||
save_conversation_function = FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
get_filenames_function = FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
load_conversation_function = FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
)
|
||||
|
||||
tools = ToolsSchema(
|
||||
standard_tools=[
|
||||
weather_function,
|
||||
save_conversation_function,
|
||||
get_filenames_function,
|
||||
load_conversation_function,
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# 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,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_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
|
||||
),
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
settings=AnthropicLLMService.Settings(
|
||||
system_instruction=system_instruction,
|
||||
),
|
||||
)
|
||||
|
||||
# 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 = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
user_aggregator,
|
||||
llm, # LLM
|
||||
tts,
|
||||
transport.output(), # Transport bot 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")
|
||||
# Kick off the conversation.
|
||||
context.add_message(
|
||||
{
|
||||
"role": "developer",
|
||||
"content": "Start the call by saying the word 'hello'. Say only that word.",
|
||||
}
|
||||
)
|
||||
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()
|
||||
295
examples/persistent-context/aws-nova-sonic.py
Normal file
295
examples/persistent-context/aws-nova-sonic.py
Normal file
@@ -0,0 +1,295 @@
|
||||
#
|
||||
# Copyright (c) 2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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
|
||||
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.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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 get_saved_conversation_filenames(
|
||||
# function_name, tool_call_id, args, llm, context, result_callback
|
||||
# ):
|
||||
# pattern = re.compile(re.escape(BASE_FILENAME) + "\\d{8}_\\d{6}\\.json$")
|
||||
# matching_files = []
|
||||
|
||||
# for filename in os.listdir("."):
|
||||
# if pattern.match(filename):
|
||||
# matching_files.append(filename)
|
||||
|
||||
# await 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"
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# remove the last few messages. in reverse order, they are:
|
||||
# - the in progress save tool call
|
||||
# - the invocation of the save tool call
|
||||
# - the user ask to save (which may encompass one or more messages)
|
||||
# the simplest thing to do is to pop messages until the last one is an assistant
|
||||
# response
|
||||
while messages and not (
|
||||
messages[-1].get("role") == "assistant" and "content" in messages[-1]
|
||||
):
|
||||
messages.pop()
|
||||
if messages: # we never expect this to be empty
|
||||
logger.debug(
|
||||
f"writing conversation to {filename}\n{json.dumps(messages, indent=4)}"
|
||||
)
|
||||
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):
|
||||
async def _reset():
|
||||
filename = params.arguments["filename"]
|
||||
logger.debug(f"loading conversation from {filename}")
|
||||
try:
|
||||
with open(filename, "r") as file:
|
||||
messages = json.load(file)
|
||||
# HACK: if using the older Nova Sonic (pre-2) model, you need a special way of
|
||||
# triggering the first assistant response. The call to trigger_assistant_response(),
|
||||
# commented out below, is part of this.
|
||||
# messages.append(
|
||||
# {
|
||||
# "role": "developer",
|
||||
# "content": f"{AWSNovaSonicLLMService.AWAIT_TRIGGER_ASSISTANT_RESPONSE_INSTRUCTION}",
|
||||
# }
|
||||
# )
|
||||
# If the last message isn't from the user, add a message asking for a recap
|
||||
if messages and messages[-1].get("role") != "user":
|
||||
messages.append(
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Can you catch me up on what we were talking about?",
|
||||
}
|
||||
)
|
||||
params.context.set_messages(messages)
|
||||
await params.llm.reset_conversation()
|
||||
# await params.llm.trigger_assistant_response()
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
asyncio.create_task(_reset())
|
||||
|
||||
|
||||
get_current_weather_tool = FunctionSchema(
|
||||
name="get_current_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"],
|
||||
)
|
||||
|
||||
save_conversation_tool = FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
get_saved_conversation_filenames_tool = FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
load_conversation_tool = FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
)
|
||||
|
||||
tools = ToolsSchema(
|
||||
standard_tools=[
|
||||
get_current_weather_tool,
|
||||
save_conversation_tool,
|
||||
get_saved_conversation_filenames_tool,
|
||||
load_conversation_tool,
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# 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,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Specify initial system instruction.
|
||||
system_instruction = (
|
||||
"You are a friendly assistant. The user and you will engage in a spoken dialog exchanging "
|
||||
"the transcripts of a natural real-time conversation. Keep your responses short, generally "
|
||||
"two or three sentences for chatty scenarios. "
|
||||
# HACK: if using the older Nova Sonic (pre-2) model, note that you need to inject a special
|
||||
# bit of text into this instruction to allow the first assistant response to be
|
||||
# programmatically triggered (which happens in the on_client_connected handler)
|
||||
# f"{AWSNovaSonicLLMService.AWAIT_TRIGGER_ASSISTANT_RESPONSE_INSTRUCTION}"
|
||||
)
|
||||
|
||||
llm = AWSNovaSonicLLMService(
|
||||
secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
|
||||
access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
|
||||
region=os.getenv("AWS_REGION"), # as of 2025-05-06, us-east-1 is the only supported region
|
||||
settings=AWSNovaSonicLLMService.Settings(
|
||||
voice="tiffany", # matthew, tiffany, amy
|
||||
system_instruction=system_instruction,
|
||||
),
|
||||
# you could choose to pass tools here rather than via context
|
||||
# tools=tools
|
||||
)
|
||||
|
||||
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 = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
user_aggregator,
|
||||
llm, # LLM
|
||||
transport.output(), # Transport bot 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")
|
||||
# Kick off the conversation.
|
||||
context.add_message(
|
||||
{"role": "developer", "content": "Please introduce yourself to the user."}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
# HACK: if using the older Nova Sonic (pre-2) model, you need this special way of
|
||||
# triggering the first assistant response. Note that this trigger requires a special
|
||||
# corresponding bit of text in the system instruction.
|
||||
# await llm.trigger_assistant_response()
|
||||
|
||||
@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()
|
||||
331
examples/persistent-context/gemini.py
Normal file
331
examples/persistent-context/gemini.py
Normal file
@@ -0,0 +1,331 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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, 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)
|
||||
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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_image(params: FunctionCallParams):
|
||||
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,
|
||||
)
|
||||
|
||||
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# remove the last message (the instruction to save the context)
|
||||
messages.pop()
|
||||
json.dump(messages, file, indent=2)
|
||||
await params.result_callback({"success": True})
|
||||
except Exception as e:
|
||||
logger.debug(f"error saving conversation: {e}")
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
|
||||
async def load_conversation(params: FunctionCallParams):
|
||||
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))
|
||||
await params.result_callback(
|
||||
{
|
||||
"success": True,
|
||||
"message": "The most recent conversation has been loaded. Awaiting further instructions.",
|
||||
}
|
||||
)
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
|
||||
system_instruction = """You are a helpful assistant in a voice conversation. Your goal is to demonstrate your
|
||||
capabilities in a succinct way. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Keep responses concise. Respond to what the user said in a creative
|
||||
can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative
|
||||
and helpful way.
|
||||
|
||||
You have several tools you can use to help you.
|
||||
|
||||
You can respond to questions about the weather using the get_weather tool.
|
||||
|
||||
You can save the current conversation using the save_conversation tool. This tool allows you to save
|
||||
the current conversation to external storage. If the user asks you to save the conversation, use this
|
||||
save_conversation too.
|
||||
|
||||
You can load a saved conversation using the load_conversation tool. This tool allows you to load a
|
||||
conversation from external storage. You can get a list of conversations that have been saved using the
|
||||
get_saved_conversation_filenames 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?
|
||||
"""
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_current_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 users location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
)
|
||||
|
||||
save_conversation_function = FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={
|
||||
"user_request_text": {
|
||||
"type": "string",
|
||||
"description": "The text of the user's request to save the conversation.",
|
||||
}
|
||||
},
|
||||
required=["user_request_text"],
|
||||
)
|
||||
|
||||
get_filenames_function = FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
load_conversation_function = FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
)
|
||||
|
||||
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,
|
||||
save_conversation_function,
|
||||
get_filenames_function,
|
||||
load_conversation_function,
|
||||
get_image_function,
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# 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
|
||||
),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
system_instruction=system_instruction,
|
||||
)
|
||||
|
||||
# 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)
|
||||
llm.register_function("get_image", get_image)
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
user_aggregator,
|
||||
llm, # LLM
|
||||
tts,
|
||||
transport.output(), # Transport bot 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")
|
||||
|
||||
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()
|
||||
248
examples/persistent-context/grok-realtime.py
Normal file
248
examples/persistent-context/grok-realtime.py
Normal file
@@ -0,0 +1,248 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""Grok Realtime persistent context example.
|
||||
|
||||
This example demonstrates how to save and load conversation history with
|
||||
Grok's Realtime Voice Agent API. It allows:
|
||||
- Saving the current conversation to a JSON file
|
||||
- Loading a previous conversation from disk
|
||||
- Listing all saved conversation files
|
||||
|
||||
This is useful for building voice agents that remember past conversations.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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.frames.frames import LLMRunFrame
|
||||
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,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.xai.realtime.events import SessionProperties, TurnDetection
|
||||
from pipecat.services.xai.realtime.llm import GrokRealtimeLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_grok_conversation_"
|
||||
|
||||
|
||||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||||
"""Mock weather function for demonstration."""
|
||||
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):
|
||||
"""Get a list of saved conversation history files."""
|
||||
full_pattern = f"{BASE_FILENAME}*.json"
|
||||
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):
|
||||
"""Save the current conversation to a JSON file."""
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# Remove the last message (the save instruction)
|
||||
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):
|
||||
"""Load a conversation history from a JSON file."""
|
||||
|
||||
async def _reset():
|
||||
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))
|
||||
await params.llm.reset_conversation()
|
||||
# Manually create a response since we've reset the conversation
|
||||
await params.llm._create_response()
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
asyncio.create_task(_reset())
|
||||
|
||||
|
||||
# Define the tools schema
|
||||
tools = ToolsSchema(
|
||||
standard_tools=[
|
||||
FunctionSchema(
|
||||
name="get_current_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 users location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
),
|
||||
FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={},
|
||||
required=[],
|
||||
),
|
||||
FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
),
|
||||
FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
),
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# Transport configuration - no local VAD needed since Grok has server-side VAD
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting Grok Realtime persistent context bot")
|
||||
|
||||
session_properties = SessionProperties(
|
||||
voice="Ara",
|
||||
turn_detection=TurnDetection(type="server_vad"),
|
||||
instructions="""You are a helpful and friendly AI assistant powered by Grok.
|
||||
|
||||
Your voice and personality should be warm and engaging, with a lively and playful tone.
|
||||
|
||||
You are participating in a voice conversation. Keep your responses concise, short, and to the point
|
||||
unless specifically asked to elaborate on a topic.
|
||||
|
||||
You have access to tools for:
|
||||
- Getting weather information
|
||||
- Saving the current conversation to disk
|
||||
- Loading previous conversations from disk
|
||||
- Listing saved conversation files
|
||||
|
||||
When the user asks to save or load a conversation, use the appropriate tool.
|
||||
Remember, your responses should be short - just one or two sentences usually.""",
|
||||
)
|
||||
|
||||
llm = GrokRealtimeLLMService(
|
||||
api_key=os.getenv("XAI_API_KEY"),
|
||||
session_properties=session_properties,
|
||||
)
|
||||
|
||||
# Register function handlers
|
||||
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 = LLMContext([{"role": "developer", "content": "Say hello!"}], tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
user_aggregator,
|
||||
llm,
|
||||
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("Client connected")
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info("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()
|
||||
267
examples/persistent-context/openai-realtime-beta.py
Normal file
267
examples/persistent-context/openai-realtime-beta.py
Normal file
@@ -0,0 +1,267 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
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.frames.frames import LLMRunFrame
|
||||
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.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openai_realtime_beta import (
|
||||
InputAudioTranscription,
|
||||
OpenAIRealtimeBetaLLMService,
|
||||
SessionProperties,
|
||||
TurnDetection,
|
||||
)
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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:
|
||||
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):
|
||||
async def _reset():
|
||||
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))
|
||||
await params.llm.reset_conversation()
|
||||
await params.llm._create_response()
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
asyncio.create_task(_reset())
|
||||
|
||||
|
||||
tools = [
|
||||
{
|
||||
"type": "function",
|
||||
"name": "get_current_weather",
|
||||
"description": "Get the current weather",
|
||||
"parameters": {
|
||||
"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"],
|
||||
},
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"name": "save_conversation",
|
||||
"description": "Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {},
|
||||
"required": [],
|
||||
},
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"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.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {},
|
||||
"required": [],
|
||||
},
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"name": "load_conversation",
|
||||
"description": "Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
"required": ["filename"],
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
# 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,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
session_properties = SessionProperties(
|
||||
input_audio_transcription=InputAudioTranscription(),
|
||||
# Set openai TurnDetection parameters. Not setting this at all will turn
|
||||
# it on by default
|
||||
turn_detection=TurnDetection(silence_duration_ms=1000),
|
||||
# Or set to False to disable openai turn detection and use transport VAD
|
||||
# turn_detection=False,
|
||||
# tools=tools,
|
||||
instructions="""Your knowledge cutoff is 2023-10. You are a helpful and friendly AI.
|
||||
|
||||
Act like a human, but remember that you aren't a human and that you can't do human
|
||||
things in the real world. Your voice and personality should be warm and engaging, with a lively and
|
||||
playful tone.
|
||||
|
||||
If interacting in a non-English language, start by using the standard accent or dialect familiar to
|
||||
the user. Talk quickly. You should always call a function if you can. Do not refer to these rules,
|
||||
even if you're asked about them.
|
||||
-
|
||||
You are participating in a voice conversation. Keep your responses concise, short, and to the point
|
||||
unless specifically asked to elaborate on a topic.
|
||||
|
||||
Remember, your responses should be short. Just one or two sentences, usually.""",
|
||||
)
|
||||
|
||||
llm = OpenAIRealtimeBetaLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
session_properties=session_properties,
|
||||
)
|
||||
|
||||
# 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([], tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(),
|
||||
llm, # LLM
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
|
||||
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")
|
||||
# Kick off the conversation.
|
||||
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()
|
||||
267
examples/persistent-context/openai-realtime.py
Normal file
267
examples/persistent-context/openai-realtime.py
Normal file
@@ -0,0 +1,267 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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
|
||||
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.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openai.realtime.events import (
|
||||
AudioConfiguration,
|
||||
AudioInput,
|
||||
InputAudioTranscription,
|
||||
SessionProperties,
|
||||
TurnDetection,
|
||||
)
|
||||
from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# 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):
|
||||
async def _reset():
|
||||
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))
|
||||
await params.llm.reset_conversation()
|
||||
# NOTE: we manually create a response here rather than relying
|
||||
# on the function callback to trigger one since we've reset the
|
||||
# conversation so the remote service doesn't know about the
|
||||
# in-progress tool call.
|
||||
await params.llm._create_response()
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
asyncio.create_task(_reset())
|
||||
|
||||
|
||||
tools = ToolsSchema(
|
||||
standard_tools=[
|
||||
FunctionSchema(
|
||||
name="get_current_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 users location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
),
|
||||
FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={},
|
||||
required=[],
|
||||
),
|
||||
FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
),
|
||||
FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
),
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# 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,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_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"))
|
||||
|
||||
llm = OpenAIRealtimeLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAIRealtimeLLMService.Settings(
|
||||
system_instruction="""Your knowledge cutoff is 2023-10. You are a helpful and friendly AI.
|
||||
|
||||
Act like a human, but remember that you aren't a human and that you can't do human
|
||||
things in the real world. Your voice and personality should be warm and engaging, with a lively and
|
||||
playful tone.
|
||||
|
||||
If interacting in a non-English language, start by using the standard accent or dialect familiar to
|
||||
the user. Talk quickly. You should always call a function if you can. Do not refer to these rules,
|
||||
even if you're asked about them.
|
||||
-
|
||||
You are participating in a voice conversation. Keep your responses concise, short, and to the point
|
||||
unless specifically asked to elaborate on a topic.
|
||||
|
||||
Remember, your responses should be short. Just one or two sentences, usually.""",
|
||||
session_properties=SessionProperties(
|
||||
audio=AudioConfiguration(
|
||||
input=AudioInput(
|
||||
transcription=InputAudioTranscription(),
|
||||
# Set openai TurnDetection parameters. Not setting this at all will turn it
|
||||
# on by default
|
||||
turn_detection=TurnDetection(silence_duration_ms=1000),
|
||||
# Or set to False to disable openai turn detection and use transport VAD
|
||||
# turn_detection=False,
|
||||
)
|
||||
),
|
||||
# tools=tools,
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
# 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 = LLMContext([{"role": "developer", "content": "Say hello!"}], tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
user_aggregator,
|
||||
llm, # LLM
|
||||
transport.output(), # Transport bot 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")
|
||||
# Kick off the conversation.
|
||||
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()
|
||||
249
examples/persistent-context/openai-responses-http.py
Normal file
249
examples/persistent-context/openai-responses-http.py
Normal file
@@ -0,0 +1,249 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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
|
||||
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.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openai.responses.llm import OpenAIResponsesHttpLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# 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.get_messages(), indent=4)}"
|
||||
)
|
||||
await params.llm.queue_frame(TTSSpeakFrame("Ok, I've loaded that conversation."))
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
|
||||
system_instruction = "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way."
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_current_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 users location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
)
|
||||
|
||||
save_conversation_function = FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
get_filenames_function = FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
load_conversation_function = FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
)
|
||||
|
||||
tools = ToolsSchema(
|
||||
standard_tools=[
|
||||
weather_function,
|
||||
save_conversation_function,
|
||||
get_filenames_function,
|
||||
load_conversation_function,
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# 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,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_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
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAIResponsesHttpLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAIResponsesHttpLLMService.Settings(
|
||||
system_instruction=system_instruction,
|
||||
),
|
||||
)
|
||||
|
||||
# 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 = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
user_aggregator,
|
||||
llm, # LLM
|
||||
tts,
|
||||
transport.output(), # Transport bot 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")
|
||||
# Kick off the conversation.
|
||||
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()
|
||||
249
examples/persistent-context/openai-responses.py
Normal file
249
examples/persistent-context/openai-responses.py
Normal file
@@ -0,0 +1,249 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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
|
||||
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.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openai.responses.llm import OpenAIResponsesLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# 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.get_messages(), indent=4)}"
|
||||
)
|
||||
await params.llm.queue_frame(TTSSpeakFrame("Ok, I've loaded that conversation."))
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
|
||||
system_instruction = "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way."
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_current_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 users location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
)
|
||||
|
||||
save_conversation_function = FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
get_filenames_function = FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
load_conversation_function = FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
)
|
||||
|
||||
tools = ToolsSchema(
|
||||
standard_tools=[
|
||||
weather_function,
|
||||
save_conversation_function,
|
||||
get_filenames_function,
|
||||
load_conversation_function,
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# 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,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_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
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAIResponsesLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAIResponsesLLMService.Settings(
|
||||
system_instruction=system_instruction,
|
||||
),
|
||||
)
|
||||
|
||||
# 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 = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
user_aggregator,
|
||||
llm, # LLM
|
||||
tts,
|
||||
transport.output(), # Transport bot 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")
|
||||
# Kick off the conversation.
|
||||
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()
|
||||
247
examples/persistent-context/openai.py
Normal file
247
examples/persistent-context/openai.py
Normal file
@@ -0,0 +1,247 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
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
|
||||
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.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
|
||||
|
||||
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.get_messages(), indent=4)}"
|
||||
)
|
||||
try:
|
||||
with open(filename, "w") as file:
|
||||
messages = params.context.get_messages()
|
||||
# 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.get_messages(), indent=4)}"
|
||||
)
|
||||
await params.llm.queue_frame(TTSSpeakFrame("Ok, I've loaded that conversation."))
|
||||
except Exception as e:
|
||||
await params.result_callback({"success": False, "error": str(e)})
|
||||
|
||||
|
||||
system_instruction = "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way."
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_current_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 users location.",
|
||||
},
|
||||
},
|
||||
required=["location", "format"],
|
||||
)
|
||||
|
||||
save_conversation_function = FunctionSchema(
|
||||
name="save_conversation",
|
||||
description="Save the current conversation. Use this function to persist the current conversation to external storage.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
get_filenames_function = FunctionSchema(
|
||||
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.",
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
load_conversation_function = FunctionSchema(
|
||||
name="load_conversation",
|
||||
description="Load a conversation history. Use this function to load a conversation history into the current session.",
|
||||
properties={
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The filename of the conversation history to load.",
|
||||
}
|
||||
},
|
||||
required=["filename"],
|
||||
)
|
||||
|
||||
tools = ToolsSchema(
|
||||
standard_tools=[
|
||||
weather_function,
|
||||
save_conversation_function,
|
||||
get_filenames_function,
|
||||
load_conversation_function,
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
# 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,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_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
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
system_instruction=system_instruction,
|
||||
)
|
||||
|
||||
# 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 = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
user_aggregator,
|
||||
llm, # LLM
|
||||
tts,
|
||||
transport.output(), # Transport bot 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")
|
||||
# Kick off the conversation.
|
||||
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()
|
||||
Reference in New Issue
Block a user