feat(ultravox): support cancel_on_interruption=False via placeholder + final-as-text
Replaces the prior "log a warning and skip" approach with actual handling of async-tool messages on Ultravox. The catch with Ultravox is that its API freezes the conversation between client_tool_invocation and the matching client_tool_result — there's no "keep talking while the tool runs" channel like NON_BLOCKING on Gemini or function_call_output-without-blocking on OpenAI Realtime. So: - When the model invokes an async-registered function (cancel_on_inter ruption=False), the service immediately ships a placeholder client_tool_result that tells the model "the actual result isn't ready yet; a follow-up will arrive shortly; keep the conversation going". This unfreezes the conversation. The placeholder is sent from _handle_tool_invocation, since the started async-tool message doesn't reach the context-frame path until later. - When the real tool finishes, the final async-tool message lands in the context. _handle_context now forward-iterates and routes async-tool messages: started is a no-op (placeholder already sent), intermediate is logged-as-error and dropped (matching the other realtime services), and final is injected as user-side text via user_text_message with bracketed framing — the only mechanism Ultravox offers for adding non-tool input mid-conversation. Hoists the registry-lookup helper to LLMService as _function_is_async(name) so future services can use the same pattern without re-implementing it. Adds an async-tool example file for Ultravox modeled on the existing ones for the other realtime services.
This commit is contained in:
Paul Kompfner
186
examples/realtime/realtime-ultravox-async-tool.py
Normal file
186
examples/realtime/realtime-ultravox-async-tool.py
Normal file
@@ -0,0 +1,186 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""Example: async function call with the Ultravox Realtime LLM service.
|
||||
|
||||
The ``get_current_weather`` tool is registered with
|
||||
``cancel_on_interruption=False`` and simulates a slow API call (10s sleep).
|
||||
|
||||
Ultravox's API freezes the conversation between ``client_tool_invocation``
|
||||
and the matching ``client_tool_result``, so the service ships a placeholder
|
||||
``client_tool_result`` immediately when an async-registered function is
|
||||
invoked (to unfreeze the conversation). When the real tool finishes, the
|
||||
actual result is injected as user-side text so the model picks it up.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import datetime
|
||||
import os
|
||||
import random
|
||||
|
||||
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.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.llm_service import FunctionCallParams
|
||||
from pipecat.services.ultravox.llm import OneShotInputParams, UltravoxRealtimeLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import SpeechTimeoutUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||||
# Simulate a long-running API call so we can demonstrate that the
|
||||
# conversation continues while the tool is in flight.
|
||||
await asyncio.sleep(10)
|
||||
temperature = (
|
||||
random.randint(60, 85)
|
||||
if params.arguments["format"] == "fahrenheit"
|
||||
else random.randint(15, 30)
|
||||
)
|
||||
await params.result_callback(
|
||||
{
|
||||
"conditions": "nice",
|
||||
"temperature": temperature,
|
||||
"location": params.arguments["location"],
|
||||
"format": params.arguments["format"],
|
||||
"timestamp": datetime.datetime.now().strftime("%Y%m%d_%H%M%S"),
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
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"],
|
||||
)
|
||||
|
||||
|
||||
system_prompt = (
|
||||
"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. When the user asks for the weather, call get_current_weather. "
|
||||
"While you wait for the result, keep chatting with the user. When the "
|
||||
"result arrives, share it with the user naturally."
|
||||
)
|
||||
|
||||
|
||||
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")
|
||||
|
||||
llm = UltravoxRealtimeLLMService(
|
||||
params=OneShotInputParams(
|
||||
api_key=os.environ["ULTRAVOX_API_KEY"],
|
||||
system_prompt=system_prompt,
|
||||
temperature=0.3,
|
||||
max_duration=datetime.timedelta(minutes=3),
|
||||
),
|
||||
one_shot_selected_tools=ToolsSchema(standard_tools=[weather_function]),
|
||||
)
|
||||
|
||||
llm.register_function(
|
||||
"get_current_weather",
|
||||
fetch_weather_from_api,
|
||||
cancel_on_interruption=False,
|
||||
)
|
||||
|
||||
context = LLMContext([])
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[SpeechTimeoutUserTurnStopStrategy()],
|
||||
),
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
|
||||
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(f"Client connected")
|
||||
|
||||
@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