feat: support new async-tool mechanism in AWS Nova Sonic
Add support to AWSNovaSonicLLMService for the new "async tool call" mechanism activated by `cancel_on_interruption=False`, which includes: - delivering results asynchronously - delivering result streams - cancelling running async tools Note that the introduction of the new mechanism had actually caused a regression in AWS Nova Sonic, which previously supported `cancel_on_interruption=False` with the old mechanism (simply avoiding discarding tool calls on interruptions). Support for the other major realtime services (`GeminiLiveLLMService`, `OpenAIRealtimeLLMService`) will follow in a separate PR — Gemini Live in particular needs more work before it can support long-running tool calls reliably.
This commit is contained in:
Paul Kompfner
182
examples/realtime/realtime-aws-nova-sonic-async-stream-tool.py
Normal file
182
examples/realtime/realtime-aws-nova-sonic-async-stream-tool.py
Normal file
@@ -0,0 +1,182 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""Example: streaming async function call with the AWS Nova Sonic LLM service.
|
||||
|
||||
The ``track_current_location`` tool simulates a GPS tracker reporting the
|
||||
device's position during a road trip from San Francisco to San Diego. It
|
||||
sends two intermediate updates (via ``params.result_callback`` with
|
||||
``is_final=False``) as the vehicle passes through cities along the way, then
|
||||
delivers the final destination.
|
||||
|
||||
The placeholder is sent as a formal Nova Sonic ``toolResult``; each
|
||||
intermediate result is forwarded as a cross-modal user-role text input event
|
||||
so the model can fold each update into its next turn.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.adapters.schemas.function_schema import FunctionSchema
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import FunctionCallResultProperties, 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)
|
||||
|
||||
|
||||
async def track_current_location(params: FunctionCallParams):
|
||||
"""Simulate a GPS tracker reporting position during a road trip."""
|
||||
gps = {"lat": 37.7310, "lng": -122.4527}
|
||||
await params.result_callback(
|
||||
{"gps": gps, "city": "San Francisco"},
|
||||
properties=FunctionCallResultProperties(is_final=False),
|
||||
)
|
||||
|
||||
await asyncio.sleep(10)
|
||||
gps = {"lat": 33.96003, "lng": -118.40639}
|
||||
await params.result_callback(
|
||||
{"gps": gps, "city": "Los Angeles"},
|
||||
properties=FunctionCallResultProperties(is_final=False),
|
||||
)
|
||||
|
||||
await asyncio.sleep(10)
|
||||
gps = {"lat": 32.743569, "lng": -117.20466}
|
||||
await params.result_callback({"gps": gps, "city": "San Diego"})
|
||||
|
||||
|
||||
location_function = FunctionSchema(
|
||||
name="track_current_location",
|
||||
description=(
|
||||
"Start tracking the user's current GPS location, reporting position "
|
||||
"updates until the user reaches their destination. "
|
||||
"Once this tracker is started, it doesn't need to be started again for subsequent updates; "
|
||||
"just call this function once to kick it off and the updates will come in automatically."
|
||||
),
|
||||
properties={},
|
||||
required=[],
|
||||
)
|
||||
|
||||
tools = ToolsSchema(standard_tools=[location_function])
|
||||
|
||||
|
||||
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")
|
||||
|
||||
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. You have access to a function that starts tracking the user's "
|
||||
"location and provides regular updates on it. Narrate each position "
|
||||
"update to the user as it arrives (city only, no coordinates). "
|
||||
"When you receive the final location, tell the user the destination has "
|
||||
"been reached."
|
||||
)
|
||||
|
||||
llm = AWSNovaSonicLLMService(
|
||||
secret_access_key=os.environ["AWS_SECRET_ACCESS_KEY"],
|
||||
access_key_id=os.environ["AWS_ACCESS_KEY_ID"],
|
||||
region=os.environ["AWS_REGION"],
|
||||
session_token=os.getenv("AWS_SESSION_TOKEN"),
|
||||
settings=AWSNovaSonicLLMService.Settings(
|
||||
voice="tiffany",
|
||||
system_instruction=system_instruction,
|
||||
),
|
||||
)
|
||||
|
||||
llm.register_function(
|
||||
"track_current_location",
|
||||
track_current_location,
|
||||
cancel_on_interruption=False,
|
||||
)
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(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")
|
||||
context.add_message(
|
||||
{"role": "developer", "content": "Please introduce yourself to the user."}
|
||||
)
|
||||
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()
|
||||
183
examples/realtime/realtime-aws-nova-sonic-async-tool.py
Normal file
183
examples/realtime/realtime-aws-nova-sonic-async-tool.py
Normal file
@@ -0,0 +1,183 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""Example: async function call with the AWS Nova Sonic LLM service.
|
||||
|
||||
The ``get_current_weather`` tool is registered with
|
||||
``cancel_on_interruption=False`` and simulates a slow API call (20s sleep).
|
||||
While the call is in flight the conversation continues; the result arrives
|
||||
later via the async-tool mechanism and is forwarded to Nova Sonic so the
|
||||
model can integrate it naturally into its next turn.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import random
|
||||
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)
|
||||
|
||||
|
||||
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(20)
|
||||
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.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"],
|
||||
)
|
||||
|
||||
tools = ToolsSchema(standard_tools=[weather_function])
|
||||
|
||||
|
||||
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")
|
||||
|
||||
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. 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."
|
||||
)
|
||||
|
||||
llm = AWSNovaSonicLLMService(
|
||||
secret_access_key=os.environ["AWS_SECRET_ACCESS_KEY"],
|
||||
access_key_id=os.environ["AWS_ACCESS_KEY_ID"],
|
||||
region=os.environ["AWS_REGION"],
|
||||
session_token=os.getenv("AWS_SESSION_TOKEN"),
|
||||
settings=AWSNovaSonicLLMService.Settings(
|
||||
voice="tiffany",
|
||||
system_instruction=system_instruction,
|
||||
),
|
||||
)
|
||||
|
||||
llm.register_function(
|
||||
"get_current_weather",
|
||||
fetch_weather_from_api,
|
||||
cancel_on_interruption=False,
|
||||
)
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(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")
|
||||
context.add_message(
|
||||
{"role": "developer", "content": "Please introduce yourself to the user."}
|
||||
)
|
||||
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()
|
||||
@@ -5,7 +5,6 @@
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import random
|
||||
from datetime import datetime
|
||||
@@ -46,11 +45,6 @@ async def fetch_weather_from_api(params: FunctionCallParams):
|
||||
if params.arguments["format"] == "fahrenheit"
|
||||
else random.randint(15, 30)
|
||||
)
|
||||
# Simulate a long network delay.
|
||||
# You can continue chatting while waiting for this to complete.
|
||||
# With Nova 2 Sonic (the default model), the assistant will respond
|
||||
# appropriately once the function call is complete.
|
||||
await asyncio.sleep(5)
|
||||
await params.result_callback(
|
||||
{
|
||||
"conditions": "nice",
|
||||
@@ -150,9 +144,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
# Register function for function calls
|
||||
# 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, cancel_on_interruption=False
|
||||
)
|
||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||
|
||||
# Set up context and context management.
|
||||
context = LLMContext(tools=tools)
|
||||
|
||||
Reference in New Issue
Block a user