diff --git a/examples/function-calling/function-calling-anthropic-delayed.py b/examples/function-calling/function-calling-anthropic-delayed.py new file mode 100644 index 000000000..09cafab8e --- /dev/null +++ b/examples/function-calling/function-calling-anthropic-delayed.py @@ -0,0 +1,174 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +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 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.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) + + +async def fetch_weather_from_api(params: FunctionCallParams): + # Simulate a long-running API call, so we can test async function calls. + await asyncio.sleep(20) + await params.result_callback({"conditions": "nice", "temperature": "75"}) + + +async def fetch_restaurant_recommendation(params: FunctionCallParams): + await params.result_callback({"name": "The Golden Dragon"}) + + +# 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="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.", + ), + ) + + # You can also register a function_name of None to get all functions + # sent to the same callback with an additional function_name parameter. + llm.register_function( + "get_current_weather", + fetch_weather_from_api, + cancel_on_interruption=False, + timeout_secs=30, + ) + llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation) + + 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", + }, + }, + required=["location"], + ) + restaurant_function = FunctionSchema( + name="get_restaurant_recommendation", + description="Get a restaurant recommendation", + properties={ + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + }, + required=["location"], + ) + tools = ToolsSchema(standard_tools=[weather_function, restaurant_function]) + + context = LLMContext(tools=tools) + user_aggregator, assistant_aggregator = LLMContextAggregatorPair( + context, + user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()), + ) + + pipeline = Pipeline( + [ + transport.input(), # Transport user input + stt, + user_aggregator, # User spoken responses + llm, # LLM + tts, # TTS + transport.output(), # Transport bot output + assistant_aggregator, # Assistant spoken responses and tool context + ] + ) + + 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()]) + + @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() diff --git a/examples/function-calling/function-calling-anthropic.py b/examples/function-calling/function-calling-anthropic.py index 09cafab8e..b8bb4eac6 100644 --- a/examples/function-calling/function-calling-anthropic.py +++ b/examples/function-calling/function-calling-anthropic.py @@ -4,7 +4,7 @@ # SPDX-License-Identifier: BSD 2-Clause License # -import asyncio + import os from dotenv import load_dotenv @@ -35,10 +35,9 @@ 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 test async function calls. - await asyncio.sleep(20) - await params.result_callback({"conditions": "nice", "temperature": "75"}) +async def get_weather(params: FunctionCallParams): + location = params.arguments["location"] + await params.result_callback(f"The weather in {location} is currently 72 degrees and sunny.") async def fetch_restaurant_recommendation(params: FunctionCallParams): @@ -81,19 +80,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): 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.", ), ) - - # You can also register a function_name of None to get all functions - # sent to the same callback with an additional function_name parameter. - llm.register_function( - "get_current_weather", - fetch_weather_from_api, - cancel_on_interruption=False, - timeout_secs=30, - ) + llm.register_function("get_weather", get_weather) llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation) weather_function = FunctionSchema( - name="get_current_weather", + name="get_weather", description="Get the current weather", properties={ "location": { diff --git a/examples/function-calling/function-calling-openai-delayed.py b/examples/function-calling/function-calling-openai-delayed.py new file mode 100644 index 000000000..b5c5b83ac --- /dev/null +++ b/examples/function-calling/function-calling-openai-delayed.py @@ -0,0 +1,189 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +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 ( + 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.llm_service import FunctionCallParams +from pipecat.services.openai.llm import OpenAILLMService +from pipecat.services.openai.stt import OpenAISTTService +from pipecat.services.openai.tts import OpenAITTSService +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 test async function calls. + await asyncio.sleep(20) + await params.result_callback({"conditions": "nice", "temperature": "75"}) + + +async def fetch_restaurant_recommendation(params: FunctionCallParams): + await params.result_callback({"name": "The Golden Dragon"}) + + +# 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 = OpenAISTTService( + api_key=os.getenv("OPENAI_API_KEY"), + settings=OpenAISTTService.Settings( + model="gpt-4o-transcribe", + prompt="Expect words related weather, such as temperature and conditions. And restaurant names.", + ), + ) + + tts = OpenAITTSService( + api_key=os.getenv("OPENAI_API_KEY"), + settings=OpenAITTSService.Settings( + voice="ballad", + ), + instructions="Please speak clearly and at a moderate pace.", + ) + + llm = OpenAILLMService( + api_key=os.getenv("OPENAI_API_KEY"), + settings=OpenAILLMService.Settings( + 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.", + ), + ) + + # You can also register a function_name of None to get all functions + # sent to the same callback with an additional function_name parameter. + llm.register_function( + "get_current_weather", + fetch_weather_from_api, + cancel_on_interruption=False, + timeout_secs=30, + ) + llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation) + + @llm.event_handler("on_function_calls_started") + async def on_function_calls_started(service, function_calls): + await tts.queue_frame(TTSSpeakFrame("Let me check on that.")) + + weather_function = FunctionSchema( + name="get_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"], + ) + restaurant_function = FunctionSchema( + name="get_restaurant_recommendation", + description="Get a restaurant recommendation", + properties={ + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + }, + required=["location"], + ) + tools = ToolsSchema(standard_tools=[weather_function, restaurant_function]) + + context = LLMContext(tools=tools) + user_aggregator, assistant_aggregator = LLMContextAggregatorPair( + context, + user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()), + ) + + pipeline = Pipeline( + [ + transport.input(), + stt, + user_aggregator, + llm, + tts, + transport.output(), + assistant_aggregator, + ] + ) + + task = PipelineTask( + pipeline, + params=PipelineParams( + enable_metrics=True, + enable_usage_metrics=True, + ), + ) + + @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() diff --git a/examples/function-calling/function-calling-openai.py b/examples/function-calling/function-calling-openai.py index b5c5b83ac..2b59d7072 100644 --- a/examples/function-calling/function-calling-openai.py +++ b/examples/function-calling/function-calling-openai.py @@ -4,7 +4,6 @@ # SPDX-License-Identifier: BSD 2-Clause License # -import asyncio import os from dotenv import load_dotenv @@ -13,10 +12,7 @@ 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.frames.frames import LLMRunFrame, TTSSpeakFrame from pipecat.pipeline.pipeline import Pipeline from pipecat.pipeline.runner import PipelineRunner from pipecat.pipeline.task import PipelineParams, PipelineTask @@ -39,8 +35,6 @@ load_dotenv(override=True) async def fetch_weather_from_api(params: FunctionCallParams): - # Simulate a long-running API call, so we can test async function calls. - await asyncio.sleep(20) await params.result_callback({"conditions": "nice", "temperature": "75"}) @@ -94,12 +88,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): # You can also register a function_name of None to get all functions # sent to the same callback with an additional function_name parameter. - llm.register_function( - "get_current_weather", - fetch_weather_from_api, - cancel_on_interruption=False, - timeout_secs=30, - ) + llm.register_function("get_current_weather", fetch_weather_from_api) llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation) @llm.event_handler("on_function_calls_started")