diff --git a/examples/function-calling/gemini-openai-format.py b/examples/function-calling/gemini-openai-format.py deleted file mode 100644 index e3b06c0d6..000000000 --- a/examples/function-calling/gemini-openai-format.py +++ /dev/null @@ -1,162 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - - -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_response_universal import ( - LLMContextAggregatorPair, - LLMUserAggregatorParams, -) -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.elevenlabs.tts import ElevenLabsTTSService -from pipecat.services.google.openai.llm import GoogleLLMOpenAIBetaService -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): - await params.result_callback({"conditions": "nice", "temperature": "75"}) - - -# 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 = ElevenLabsTTSService( - api_key=os.getenv("ELEVENLABS_API_KEY", ""), - settings=ElevenLabsTTSService.Settings( - voice=os.getenv("ELEVENLABS_VOICE_ID", ""), - ), - ) - - llm = GoogleLLMOpenAIBetaService( - api_key=os.getenv("GOOGLE_API_KEY"), - settings=GoogleLLMOpenAIBetaService.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 aslo 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) - - @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"], - ) - tools = ToolsSchema(standard_tools=[weather_function]) - messages = [ - { - "role": "developer", - "content": "Start a conversation with 'Hey there' to get the current weather.", - }, - ] - - context = OpenAILLMContext(messages, 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, - ), - 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() diff --git a/examples/persistent-context/openai-realtime-beta.py b/examples/persistent-context/openai-realtime-beta.py deleted file mode 100644 index 4b05db618..000000000 --- a/examples/persistent-context/openai-realtime-beta.py +++ /dev/null @@ -1,267 +0,0 @@ -# -# 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() diff --git a/examples/realtime/azure-beta.py b/examples/realtime/azure-beta.py deleted file mode 100644 index 4e9b7bcb1..000000000 --- a/examples/realtime/azure-beta.py +++ /dev/null @@ -1,214 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - - -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.openai_llm_context import OpenAILLMContext -from pipecat.runner.types import RunnerArguments -from pipecat.runner.utils import create_transport -from pipecat.services.llm_service import FunctionCallParams -from pipecat.services.openai_realtime_beta import ( - AzureRealtimeBetaLLMService, - InputAudioTranscription, - SessionProperties, -) -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): - 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 fetch_restaurant_recommendation(params: FunctionCallParams): - await params.result_callback({"name": "The Golden Dragon"}) - - -# Define weather function using standardized schema -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"], -) - -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"], -) - -# Create tools schema -tools = ToolsSchema(standard_tools=[weather_function, restaurant_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, - 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") - - session_properties = SessionProperties( - input_audio_transcription=InputAudioTranscription(model="whisper-1"), - # 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="""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. - -You have access to the following tools: -- get_current_weather: Get the current weather for a given location. -- get_restaurant_recommendation: Get a restaurant recommendation for a given location. - -Remember, your responses should be short. Just one or two sentences, usually. Respond in English.""", - ) - - llm = AzureRealtimeBetaLLMService( - api_key=os.getenv("AZURE_REALTIME_API_KEY"), - base_url=os.getenv("AZURE_REALTIME_BASE_URL"), - 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("get_restaurant_recommendation", fetch_restaurant_recommendation) - - # Create a standard OpenAI LLM context object using the normal messages format. The - # OpenAIRealtimeBetaLLMService will convert this internally to messages that the - # openai WebSocket API can understand. - context = OpenAILLMContext( - [{"role": "developer", "content": "Say hello!"}], - # [{"role": "developer", "content": [{"type": "text", "text": "Say hello!"}]}], - # [ - # { - # "role": "developer", - # "content": [ - # {"type": "text", "text": "Say"}, - # {"type": "text", "text": "yo what's up!"}, - # ], - # } - # ], - tools, - ) - - context_aggregator = llm.create_context_aggregator(context) - - pipeline = Pipeline( - [ - transport.input(), # Transport user input - 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() diff --git a/examples/realtime/openai-beta-text.py b/examples/realtime/openai-beta-text.py deleted file mode 100644 index 31f5d0560..000000000 --- a/examples/realtime/openai-beta-text.py +++ /dev/null @@ -1,215 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - - -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.openai_llm_context import OpenAILLMContext -from pipecat.runner.types import RunnerArguments -from pipecat.runner.utils import create_transport -from pipecat.services.cartesia.tts import CartesiaTTSService -from pipecat.services.llm_service import FunctionCallParams -from pipecat.services.openai_realtime_beta import ( - InputAudioNoiseReduction, - InputAudioTranscription, - OpenAIRealtimeBetaLLMService, - SemanticTurnDetection, - SessionProperties, -) -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): - 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 fetch_restaurant_recommendation(params: FunctionCallParams): - await params.result_callback({"name": "The Golden Dragon"}) - - -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"], -) - -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"], -) - -# Create tools schema -tools = ToolsSchema(standard_tools=[weather_function, restaurant_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, - 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") - - session_properties = SessionProperties( - input_audio_transcription=InputAudioTranscription(), - modalities=["text"], - # Set openai TurnDetection parameters. Not setting this at all will turn it - # on by default - turn_detection=SemanticTurnDetection(), - # Or set to False to disable openai turn detection and use transport VAD - # turn_detection=False, - input_audio_noise_reduction=InputAudioNoiseReduction(type="near_field"), - # tools=tools, - instructions="""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. - -You have access to the following tools: -- get_current_weather: Get the current weather for a given location. -- get_restaurant_recommendation: Get a restaurant recommendation for a given location. - -Remember, your responses should be short. Just one or two sentences, usually. Respond in English.""", - ) - - llm = OpenAIRealtimeBetaLLMService( - api_key=os.getenv("OPENAI_API_KEY"), - session_properties=session_properties, - ) - - tts = CartesiaTTSService( - api_key=os.getenv("CARTESIA_API_KEY"), - settings=CartesiaTTSService.Settings( - voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady - ), - ) - - # 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("get_restaurant_recommendation", fetch_restaurant_recommendation) - - # Create a standard OpenAI LLM context object using the normal messages format. The - # OpenAIRealtimeBetaLLMService will convert this internally to messages that the - # openai WebSocket API can understand. - context = OpenAILLMContext( - [{"role": "developer", "content": "Say hello!"}], - tools, - ) - - context_aggregator = llm.create_context_aggregator(context) - - pipeline = Pipeline( - [ - transport.input(), # Transport user input - context_aggregator.user(), - llm, # LLM - tts, # TTS - 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() diff --git a/examples/realtime/openai-beta.py b/examples/realtime/openai-beta.py deleted file mode 100644 index 4d1714fe3..000000000 --- a/examples/realtime/openai-beta.py +++ /dev/null @@ -1,219 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - - -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, TranscriptionMessage -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.processors.transcript_processor import TranscriptProcessor -from pipecat.runner.types import RunnerArguments -from pipecat.runner.utils import create_transport -from pipecat.services.llm_service import FunctionCallParams -from pipecat.services.openai_realtime_beta import ( - InputAudioNoiseReduction, - InputAudioTranscription, - OpenAIRealtimeBetaLLMService, - SemanticTurnDetection, - SessionProperties, -) -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): - 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 fetch_restaurant_recommendation(params: FunctionCallParams): - await params.result_callback({"name": "The Golden Dragon"}) - - -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"], -) - -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"], -) - -# Create tools schema -tools = ToolsSchema(standard_tools=[weather_function, restaurant_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, - 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") - - session_properties = SessionProperties( - input_audio_transcription=InputAudioTranscription(), - # Set openai TurnDetection parameters. Not setting this at all will turn it - # on by default - turn_detection=SemanticTurnDetection(), - # Or set to False to disable openai turn detection and use transport VAD - # turn_detection=False, - input_audio_noise_reduction=InputAudioNoiseReduction(type="near_field"), - # tools=tools, - instructions="""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. - -You have access to the following tools: -- get_current_weather: Get the current weather for a given location. -- get_restaurant_recommendation: Get a restaurant recommendation for a given location. - -Remember, your responses should be short. Just one or two sentences, usually. Respond in English.""", - ) - - 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("get_restaurant_recommendation", fetch_restaurant_recommendation) - - transcript = TranscriptProcessor() - - # Create a standard OpenAI LLM context object using the normal messages format. The - # OpenAIRealtimeBetaLLMService will convert this internally to messages that the - # openai WebSocket API can understand. - context = OpenAILLMContext( - [{"role": "developer", "content": "Say hello!"}], - tools, - ) - - context_aggregator = llm.create_context_aggregator(context) - - pipeline = Pipeline( - [ - transport.input(), # Transport user input - context_aggregator.user(), - llm, # LLM - transcript.user(), # Placed after the LLM, as LLM pushes TranscriptionFrames downstream - transport.output(), # Transport bot output - transcript.assistant(), # After the transcript output, to time with the audio 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() - - # Register event handler for transcript updates - @transcript.event_handler("on_transcript_update") - async def on_transcript_update(processor, frame): - for msg in frame.messages: - if isinstance(msg, TranscriptionMessage): - timestamp = f"[{msg.timestamp}] " if msg.timestamp else "" - line = f"{timestamp}{msg.role}: {msg.content}" - logger.info(f"Transcript: {line}") - - 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/src/pipecat/services/ai_services.py b/src/pipecat/services/ai_services.py deleted file mode 100644 index 5f7b6d893..000000000 --- a/src/pipecat/services/ai_services.py +++ /dev/null @@ -1,33 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Deprecated AI services module. - -This module is deprecated. Import services directly from their respective modules: -- pipecat.services.ai_service -- pipecat.services.image_service -- pipecat.services.llm_service -- pipecat.services.stt_service -- pipecat.services.tts_service -- pipecat.services.vision_service -""" - -import sys - -from pipecat.services import DeprecatedModuleProxy - -from .ai_service import * -from .image_service import * -from .llm_service import * -from .stt_service import * -from .tts_service import * -from .vision_service import * - -sys.modules[__name__] = DeprecatedModuleProxy( - globals(), - "ai_services", - "[ai_service,image_service,llm_service,stt_service,tts_service,vision_service]", -) diff --git a/src/pipecat/services/aws_nova_sonic/__init__.py b/src/pipecat/services/aws_nova_sonic/__init__.py deleted file mode 100644 index a198094cb..000000000 --- a/src/pipecat/services/aws_nova_sonic/__init__.py +++ /dev/null @@ -1,24 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -import warnings - -from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService, Params - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.aws_nova_sonic are deprecated. " - "Please use the equivalent types from " - "pipecat.services.aws.nova_sonic.llm instead.", - DeprecationWarning, - stacklevel=2, - ) - -__all__ = [ - "AWSNovaSonicLLMService", - "Params", -] diff --git a/src/pipecat/services/aws_nova_sonic/aws.py b/src/pipecat/services/aws_nova_sonic/aws.py deleted file mode 100644 index b69323b8d..000000000 --- a/src/pipecat/services/aws_nova_sonic/aws.py +++ /dev/null @@ -1,25 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""AWS Nova Sonic LLM service implementation for Pipecat AI framework. - -This module provides a speech-to-speech LLM service using AWS Nova Sonic, which supports -bidirectional audio streaming, text generation, and function calling capabilities. -""" - -import warnings - -from pipecat.services.aws.nova_sonic.llm import * - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.aws_nova_sonic.aws are deprecated. " - "Please use the equivalent types from " - "pipecat.services.aws.nova_sonic.llm instead.", - DeprecationWarning, - stacklevel=2, - ) diff --git a/src/pipecat/services/aws_nova_sonic/context.py b/src/pipecat/services/aws_nova_sonic/context.py deleted file mode 100644 index 01f152b16..000000000 --- a/src/pipecat/services/aws_nova_sonic/context.py +++ /dev/null @@ -1,21 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Context management for AWS Nova Sonic LLM service. - -This module provides specialized context aggregators and message handling for AWS Nova Sonic, -including conversation history management and role-specific message processing. - -.. deprecated:: 0.0.91 - AWS Nova Sonic no longer uses types from this module under the hood. - It now uses `LLMContext` and `LLMContextAggregatorPair`. - Using the new patterns should allow you to not need types from this module. - - See deprecation warning in pipecat.services.aws.nova_sonic.context for more - details. -""" - -from pipecat.services.aws.nova_sonic.context import * diff --git a/src/pipecat/services/aws_nova_sonic/frames.py b/src/pipecat/services/aws_nova_sonic/frames.py deleted file mode 100644 index 7ac81215c..000000000 --- a/src/pipecat/services/aws_nova_sonic/frames.py +++ /dev/null @@ -1,21 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Custom frames for AWS Nova Sonic LLM service.""" - -import warnings - -from pipecat.services.aws.nova_sonic.frames import * - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.aws_nova_sonic.frames are deprecated. " - "Please use the equivalent types from " - "pipecat.services.aws.nova_sonic.frames instead.", - DeprecationWarning, - stacklevel=2, - ) diff --git a/src/pipecat/services/deepgram/stt_sagemaker.py b/src/pipecat/services/deepgram/stt_sagemaker.py deleted file mode 100644 index 08cd0c5d3..000000000 --- a/src/pipecat/services/deepgram/stt_sagemaker.py +++ /dev/null @@ -1,18 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Deprecated: use ``pipecat.services.deepgram.sagemaker.stt`` instead.""" - -import warnings - -warnings.warn( - "Module `pipecat.services.deepgram.stt_sagemaker` is deprecated, " - "use `pipecat.services.deepgram.sagemaker.stt` instead.", - DeprecationWarning, - stacklevel=2, -) - -from pipecat.services.deepgram.sagemaker.stt import * # noqa: E402, F401, F403 diff --git a/src/pipecat/services/deepgram/tts_sagemaker.py b/src/pipecat/services/deepgram/tts_sagemaker.py deleted file mode 100644 index 61ca2bceb..000000000 --- a/src/pipecat/services/deepgram/tts_sagemaker.py +++ /dev/null @@ -1,18 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Deprecated: use ``pipecat.services.deepgram.sagemaker.tts`` instead.""" - -import warnings - -warnings.warn( - "Module `pipecat.services.deepgram.tts_sagemaker` is deprecated, " - "use `pipecat.services.deepgram.sagemaker.tts` instead.", - DeprecationWarning, - stacklevel=2, -) - -from pipecat.services.deepgram.sagemaker.tts import * # noqa: E402, F401, F403 diff --git a/src/pipecat/services/gemini_multimodal_live/__init__.py b/src/pipecat/services/gemini_multimodal_live/__init__.py deleted file mode 100644 index ac4524606..000000000 --- a/src/pipecat/services/gemini_multimodal_live/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -from .file_api import GeminiFileAPI -from .gemini import GeminiMultimodalLiveLLMService - -__all__ = [ - "GeminiFileAPI", - "GeminiMultimodalLiveLLMService", -] diff --git a/src/pipecat/services/gemini_multimodal_live/events.py b/src/pipecat/services/gemini_multimodal_live/events.py deleted file mode 100644 index a560a0b02..000000000 --- a/src/pipecat/services/gemini_multimodal_live/events.py +++ /dev/null @@ -1,44 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Event models and utilities for Google Gemini Multimodal Live API. - -.. deprecated:: 0.0.90 - Importing StartSensitivity and EndSensitivity from this module is deprecated. - Import them directly from google.genai.types instead. -""" - -import warnings - -from loguru import logger - -try: - from google.genai.types import ( - EndSensitivity as _EndSensitivity, - ) - from google.genai.types import ( - StartSensitivity as _StartSensitivity, - ) -except ModuleNotFoundError as e: - logger.error(f"Exception: {e}") - logger.error("In order to use Google AI, you need to `pip install pipecat-ai[google]`.") - raise Exception(f"Missing module: {e}") - -# These aliases are just here for backward compatibility, since we used to -# define public-facing StartSensitivity and EndSensitivity enums in this -# module. -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Importing StartSensitivity and EndSensitivity from " - "pipecat.services.gemini_multimodal_live.events is deprecated. " - "Please import them directly from google.genai.types instead.", - DeprecationWarning, - stacklevel=2, - ) - -StartSensitivity = _StartSensitivity -EndSensitivity = _EndSensitivity diff --git a/src/pipecat/services/gemini_multimodal_live/file_api.py b/src/pipecat/services/gemini_multimodal_live/file_api.py deleted file mode 100644 index 02df16ded..000000000 --- a/src/pipecat/services/gemini_multimodal_live/file_api.py +++ /dev/null @@ -1,39 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Gemini File API client for uploading and managing files. - -This module provides a client for Google's Gemini File API, enabling file -uploads, metadata retrieval, listing, and deletion. Files uploaded through -this API can be referenced in Gemini generative model calls. - -.. deprecated:: 0.0.90 - Importing GeminiFileAPI from this module is deprecated. - Import it from pipecat.services.google.gemini_live.file_api instead. -""" - -import warnings - -from loguru import logger - -try: - from pipecat.services.google.gemini_live.file_api import GeminiFileAPI as _GeminiFileAPI -except ModuleNotFoundError as e: - logger.error(f"Exception: {e}") - logger.error("In order to use Google AI, you need to `pip install pipecat-ai[google]`.") - raise Exception(f"Missing module: {e}") - -# These aliases are just here for backward compatibility, since we used to -# define public-facing StartSensitivity and EndSensitivity enums in this -# module. -warnings.warn( - "Importing GeminiFileAPI from " - "pipecat.services.gemini_multimodal_live.file_api is deprecated. " - "Please import it from pipecat.services.google.gemini_live.file_api instead.", - DeprecationWarning, - stacklevel=2, -) -GeminiFileAPI = _GeminiFileAPI diff --git a/src/pipecat/services/gemini_multimodal_live/gemini.py b/src/pipecat/services/gemini_multimodal_live/gemini.py deleted file mode 100644 index 6f01e5a23..000000000 --- a/src/pipecat/services/gemini_multimodal_live/gemini.py +++ /dev/null @@ -1,57 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Google Gemini Live API service implementation. - -This module provides real-time conversational AI capabilities using Google's -Gemini Live API, supporting both text and audio modalities with -voice transcription, streaming responses, and tool usage. - -.. deprecated:: 0.0.90 - This module is deprecated. Please use the equivalent types from - pipecat.services.google.gemini_live.llm instead. Note that the new type names - do not include 'Multimodal'. -""" - -import warnings - -from pipecat.services.google.gemini_live.llm import ( - ContextWindowCompressionParams as _ContextWindowCompressionParams, -) -from pipecat.services.google.gemini_live.llm import ( - GeminiLiveAssistantContextAggregator, - GeminiLiveContext, - GeminiLiveContextAggregatorPair, - GeminiLiveLLMService, - GeminiLiveUserContextAggregator, - GeminiModalities, -) -from pipecat.services.google.gemini_live.llm import GeminiMediaResolution as _GeminiMediaResolution -from pipecat.services.google.gemini_live.llm import GeminiVADParams as _GeminiVADParams -from pipecat.services.google.gemini_live.llm import InputParams as _InputParams - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.gemini_multimodal_live.gemini are deprecated. " - "Please use the equivalent types from " - "pipecat.services.google.gemini_live.llm instead. Note that the new type " - "names do not include 'Multimodal' " - "(e.g. `GeminiMultimodalLiveLLMService` is now `GeminiLiveLLMService`).", - DeprecationWarning, - stacklevel=2, - ) - -GeminiMultimodalLiveContext = GeminiLiveContext -GeminiMultimodalLiveUserContextAggregator = GeminiLiveUserContextAggregator -GeminiMultimodalLiveAssistantContextAggregator = GeminiLiveAssistantContextAggregator -GeminiMultimodalLiveContextAggregatorPair = GeminiLiveContextAggregatorPair -GeminiMultimodalModalities = GeminiModalities -GeminiMediaResolution = _GeminiMediaResolution -GeminiVADParams = _GeminiVADParams -ContextWindowCompressionParams = _ContextWindowCompressionParams -InputParams = _InputParams -GeminiMultimodalLiveLLMService = GeminiLiveLLMService diff --git a/src/pipecat/services/google/__init__.py b/src/pipecat/services/google/__init__.py index 32b12e367..95812a536 100644 --- a/src/pipecat/services/google/__init__.py +++ b/src/pipecat/services/google/__init__.py @@ -12,12 +12,11 @@ from .frames import * from .gemini_live import * from .image import * from .llm import * -from .openai import * from .rtvi import * from .stt import * from .tts import * from .vertex import * sys.modules[__name__] = DeprecatedModuleProxy( - globals(), "google", "google.[frames,image,llm,openai,vertex,rtvi,stt,tts]" + globals(), "google", "google.[frames,image,llm,vertex,rtvi,stt,tts]" ) diff --git a/src/pipecat/services/google/gemini_live/llm_vertex.py b/src/pipecat/services/google/gemini_live/llm_vertex.py deleted file mode 100644 index 038d72e57..000000000 --- a/src/pipecat/services/google/gemini_live/llm_vertex.py +++ /dev/null @@ -1,18 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Deprecated: use ``pipecat.services.google.gemini_live.vertex.llm`` instead.""" - -import warnings - -warnings.warn( - "Module `pipecat.services.google.gemini_live.llm_vertex` is deprecated, " - "use `pipecat.services.google.gemini_live.vertex.llm` instead.", - DeprecationWarning, - stacklevel=2, -) - -from pipecat.services.google.gemini_live.vertex.llm import * # noqa: E402, F401, F403 diff --git a/src/pipecat/services/google/google.py b/src/pipecat/services/google/google.py deleted file mode 100644 index b2fc88b23..000000000 --- a/src/pipecat/services/google/google.py +++ /dev/null @@ -1,24 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Google services module for Pipecat.""" - -import sys - -from pipecat.services import DeprecatedModuleProxy - -from .frames import * -from .image import * -from .llm import * -from .openai import * -from .rtvi import * -from .stt import * -from .tts import * -from .vertex import * - -sys.modules[__name__] = DeprecatedModuleProxy( - globals(), "google", "google.[frames,image,llm,openai,vertex,rtvi,stt,tts]" -) diff --git a/src/pipecat/services/google/llm_openai.py b/src/pipecat/services/google/llm_openai.py deleted file mode 100644 index f9d182e78..000000000 --- a/src/pipecat/services/google/llm_openai.py +++ /dev/null @@ -1,18 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Deprecated: use ``pipecat.services.google.openai.llm`` instead.""" - -import warnings - -warnings.warn( - "Module `pipecat.services.google.llm_openai` is deprecated, " - "use `pipecat.services.google.openai.llm` instead.", - DeprecationWarning, - stacklevel=2, -) - -from pipecat.services.google.openai.llm import * # noqa: E402, F401, F403 diff --git a/src/pipecat/services/google/llm_vertex.py b/src/pipecat/services/google/llm_vertex.py deleted file mode 100644 index 54d338ad7..000000000 --- a/src/pipecat/services/google/llm_vertex.py +++ /dev/null @@ -1,18 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Deprecated: use ``pipecat.services.google.vertex.llm`` instead.""" - -import warnings - -warnings.warn( - "Module `pipecat.services.google.llm_vertex` is deprecated, " - "use `pipecat.services.google.vertex.llm` instead.", - DeprecationWarning, - stacklevel=2, -) - -from pipecat.services.google.vertex.llm import * # noqa: E402, F401, F403 diff --git a/src/pipecat/services/google/openai/__init__.py b/src/pipecat/services/google/openai/__init__.py deleted file mode 100644 index c4d243b97..000000000 --- a/src/pipecat/services/google/openai/__init__.py +++ /dev/null @@ -1,5 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# diff --git a/src/pipecat/services/google/openai/llm.py b/src/pipecat/services/google/openai/llm.py deleted file mode 100644 index 08a7bcd1b..000000000 --- a/src/pipecat/services/google/openai/llm.py +++ /dev/null @@ -1,217 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Google LLM service using OpenAI-compatible API format. - -This module provides integration with Google's AI LLM models using the OpenAI -API format through Google's Gemini API OpenAI compatibility layer. -""" - -import json -import os -from dataclasses import dataclass -from typing import Optional - -from openai import AsyncStream -from openai.types.chat import ChatCompletionChunk - -from pipecat.services.llm_service import FunctionCallFromLLM - -# Suppress gRPC fork warnings -os.environ["GRPC_ENABLE_FORK_SUPPORT"] = "false" - -from loguru import logger - -from pipecat.frames.frames import LLMTextFrame -from pipecat.metrics.metrics import LLMTokenUsage -from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext -from pipecat.services.openai.base_llm import BaseOpenAILLMService -from pipecat.services.openai.llm import OpenAILLMService - - -@dataclass -class GoogleOpenAILLMSettings(BaseOpenAILLMService.Settings): - """Settings for GoogleLLMOpenAIBetaService.""" - - pass - - -class GoogleLLMOpenAIBetaService(OpenAILLMService): - """Google LLM service using OpenAI-compatible API format. - - This service provides access to Google's AI LLM models (like Gemini) through - the OpenAI API format. It handles streaming responses, function calls, and - tool usage while maintaining compatibility with OpenAI's interface. - - Note: This service includes a workaround for a Google API bug where function - call indices may be incorrectly set to None, resulting in empty function names. - - .. deprecated:: 0.0.82 - GoogleLLMOpenAIBetaService is deprecated and will be removed in a future version. - Use GoogleLLMService instead for better integration with Google's native API. - - Reference: - https://ai.google.dev/gemini-api/docs/openai - """ - - Settings = GoogleOpenAILLMSettings - _settings: Settings - - def __init__( - self, - *, - api_key: str, - base_url: str = "https://generativelanguage.googleapis.com/v1beta/openai/", - model: Optional[str] = None, - settings: Optional[Settings] = None, - **kwargs, - ): - """Initialize the Google LLM service. - - Args: - api_key: Google API key for authentication. - base_url: Base URL for Google's OpenAI-compatible API. - model: Google model name to use (e.g., "gemini-2.0-flash"). - - .. deprecated:: 0.0.105 - Use ``settings=GoogleLLMOpenAIBetaService.Settings(model=...)`` instead. - - settings: Runtime-updatable settings. When provided alongside deprecated - parameters, ``settings`` values take precedence. - **kwargs: Additional arguments passed to the parent OpenAILLMService. - """ - import warnings - - with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "GoogleLLMOpenAIBetaService is deprecated and will be removed in a future version. " - "Use GoogleLLMService instead for better integration with Google's native API.", - DeprecationWarning, - stacklevel=2, - ) - - # 1. Initialize default_settings with hardcoded defaults - default_settings = self.Settings(model="gemini-2.0-flash") - - # 2. Apply direct init arg overrides (deprecated) - if model is not None: - self._warn_init_param_moved_to_settings("model", "model") - default_settings.model = model - - # 3. (No step 3, as there's no params object to apply) - - # 4. Apply settings delta (canonical API, always wins) - if settings is not None: - default_settings.apply_update(settings) - - super().__init__(api_key=api_key, base_url=base_url, settings=default_settings, **kwargs) - - async def _process_context(self, context: OpenAILLMContext): - functions_list = [] - arguments_list = [] - tool_id_list = [] - func_idx = 0 - function_name = "" - arguments = "" - tool_call_id = "" - - await self.start_ttfb_metrics() - - chunk_stream: AsyncStream[ - ChatCompletionChunk - ] = await self._stream_chat_completions_specific_context(context) - - # Use context manager to ensure stream is closed on cancellation/exception. - # Without this, CancelledError during iteration leaves the underlying socket open. - async with chunk_stream: - async for chunk in chunk_stream: - if chunk.usage: - tokens = LLMTokenUsage( - prompt_tokens=chunk.usage.prompt_tokens or 0, - completion_tokens=chunk.usage.completion_tokens or 0, - total_tokens=chunk.usage.total_tokens or 0, - ) - await self.start_llm_usage_metrics(tokens) - - if chunk.choices is None or len(chunk.choices) == 0: - continue - - await self.stop_ttfb_metrics() - - if not chunk.choices[0].delta: - continue - - if chunk.choices[0].delta.tool_calls: - # We're streaming the LLM response to enable the fastest response times. - # For text, we just yield each chunk as we receive it and count on consumers - # to do whatever coalescing they need (eg. to pass full sentences to TTS) - # - # If the LLM is a function call, we'll do some coalescing here. - # If the response contains a function name, we'll yield a frame to tell consumers - # that they can start preparing to call the function with that name. - # We accumulate all the arguments for the rest of the streamed response, then when - # the response is done, we package up all the arguments and the function name and - # yield a frame containing the function name and the arguments. - logger.debug(f"Tool call: {chunk.choices[0].delta.tool_calls}") - tool_call = chunk.choices[0].delta.tool_calls[0] - if tool_call.index != func_idx: - functions_list.append(function_name) - arguments_list.append(arguments) - tool_id_list.append(tool_call_id) - function_name = "" - arguments = "" - tool_call_id = "" - func_idx += 1 - if tool_call.function and tool_call.function.name: - function_name += tool_call.function.name - tool_call_id = tool_call.id - if tool_call.function and tool_call.function.arguments: - # Keep iterating through the response to collect all the argument fragments - arguments += tool_call.function.arguments - elif chunk.choices[0].delta.content: - await self.push_frame(LLMTextFrame(chunk.choices[0].delta.content)) - - # if we got a function name and arguments, check to see if it's a function with - # a registered handler. If so, run the registered callback, save the result to - # the context, and re-prompt to get a chat answer. If we don't have a registered - # handler, raise an exception. - if function_name and arguments: - # added to the list as last function name and arguments not added to the list - functions_list.append(function_name) - arguments_list.append(arguments) - tool_id_list.append(tool_call_id) - - logger.debug( - f"Function list: {functions_list}, Arguments list: {arguments_list}, Tool ID list: {tool_id_list}" - ) - - function_calls = [] - for function_name, arguments, tool_id in zip( - functions_list, arguments_list, tool_id_list - ): - if function_name == "": - # TODO: Remove the _process_context method once Google resolves the bug - # where the index is incorrectly set to None instead of returning the actual index, - # which currently results in an empty function name(''). - continue - - try: - arguments = json.loads(arguments) - except json.JSONDecodeError: - logger.warning(f"{self}: Failed to parse function call arguments: {arguments}") - continue - - function_calls.append( - FunctionCallFromLLM( - context=context, - tool_call_id=tool_id, - function_name=function_name, - arguments=arguments, - ) - ) - - await self.run_function_calls(function_calls) diff --git a/src/pipecat/services/grok/llm.py b/src/pipecat/services/grok/llm.py index e81db5458..cddaa7d4f 100644 --- a/src/pipecat/services/grok/llm.py +++ b/src/pipecat/services/grok/llm.py @@ -6,7 +6,7 @@ """Grok LLM service implementation. -.. deprecated:: +.. deprecated:: 0.0.108 This module is deprecated. Please use GrokLLMService from pipecat.services.xai.llm instead. """ diff --git a/src/pipecat/services/grok/realtime/events.py b/src/pipecat/services/grok/realtime/events.py index 546308e26..554ab0068 100644 --- a/src/pipecat/services/grok/realtime/events.py +++ b/src/pipecat/services/grok/realtime/events.py @@ -6,7 +6,7 @@ """Grok Realtime event models. -.. deprecated:: +.. deprecated:: 0.0.108 This module is deprecated. Please use pipecat.services.xai.realtime.events instead. """ diff --git a/src/pipecat/services/grok/realtime/llm.py b/src/pipecat/services/grok/realtime/llm.py index 5d35e158f..5373ae757 100644 --- a/src/pipecat/services/grok/realtime/llm.py +++ b/src/pipecat/services/grok/realtime/llm.py @@ -6,7 +6,7 @@ """Grok Realtime LLM service. -.. deprecated:: +.. deprecated:: 0.0.108 This module is deprecated. Please use GrokRealtimeLLMService from pipecat.services.xai.realtime.llm instead. """ diff --git a/src/pipecat/services/nim/__init__.py b/src/pipecat/services/nim/__init__.py deleted file mode 100644 index a885e6fa3..000000000 --- a/src/pipecat/services/nim/__init__.py +++ /dev/null @@ -1,13 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -import sys - -from pipecat.services import DeprecatedModuleProxy - -from .llm import * - -sys.modules[__name__] = DeprecatedModuleProxy(globals(), "nim", "nim.llm") diff --git a/src/pipecat/services/nim/llm.py b/src/pipecat/services/nim/llm.py deleted file mode 100644 index 360073c4e..000000000 --- a/src/pipecat/services/nim/llm.py +++ /dev/null @@ -1,30 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""NVIDIA NIM API service implementation. - -This module provides a service for interacting with NVIDIA's NIM (NVIDIA Inference -Microservice) API while maintaining compatibility with the OpenAI-style interface. - -.. deprecated:: 0.0.96 - This module is deprecated. Please NvidiaLLMService from - pipecat.services.nvidia.llm instead. -""" - -import warnings - -from pipecat.services.nvidia.llm import NvidiaLLMService - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "NimLLMService from pipecat.services.nim.llm is deprecated. " - "Please use NvidiaLLMService from pipecat.services.nvidia.llm instead.", - DeprecationWarning, - stacklevel=2, - ) - -NimLLMService = NvidiaLLMService diff --git a/src/pipecat/services/openai_realtime/__init__.py b/src/pipecat/services/openai_realtime/__init__.py deleted file mode 100644 index 90729ef31..000000000 --- a/src/pipecat/services/openai_realtime/__init__.py +++ /dev/null @@ -1,37 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -import warnings - -from pipecat.services.azure.realtime.llm import AzureRealtimeLLMService -from pipecat.services.openai.realtime.events import ( - InputAudioNoiseReduction, - InputAudioTranscription, - SemanticTurnDetection, - SessionProperties, - TurnDetection, -) -from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.openai_realtime are deprecated. " - "Please use the equivalent types from " - "pipecat.services.openai.realtime instead.", - DeprecationWarning, - stacklevel=2, - ) - -__all__ = [ - "AzureRealtimeLLMService", - "InputAudioNoiseReduction", - "InputAudioTranscription", - "SemanticTurnDetection", - "SessionProperties", - "TurnDetection", - "OpenAIRealtimeLLMService", -] diff --git a/src/pipecat/services/openai_realtime/azure.py b/src/pipecat/services/openai_realtime/azure.py deleted file mode 100644 index 76a2739bb..000000000 --- a/src/pipecat/services/openai_realtime/azure.py +++ /dev/null @@ -1,21 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Azure OpenAI Realtime LLM service implementation.""" - -import warnings - -from pipecat.services.azure.realtime.llm import * - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.openai_realtime.azure are deprecated. " - "Please use the equivalent types from " - "pipecat.services.azure.realtime.llm instead.", - DeprecationWarning, - stacklevel=2, - ) diff --git a/src/pipecat/services/openai_realtime/context.py b/src/pipecat/services/openai_realtime/context.py deleted file mode 100644 index 75dd6c216..000000000 --- a/src/pipecat/services/openai_realtime/context.py +++ /dev/null @@ -1,18 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""OpenAI Realtime LLM context and aggregator implementations. - -.. deprecated:: 0.0.91 - OpenAI Realtime no longer uses types from this module under the hood. - It now uses `LLMContext` and `LLMContextAggregatorPair`. - Using the new patterns should allow you to not need types from this module. - - See deprecation warning in pipecat.services.openai.realtime.context for - more details. -""" - -from pipecat.services.openai.realtime.context import * diff --git a/src/pipecat/services/openai_realtime/events.py b/src/pipecat/services/openai_realtime/events.py deleted file mode 100644 index bbbbca271..000000000 --- a/src/pipecat/services/openai_realtime/events.py +++ /dev/null @@ -1,21 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Event models and data structures for OpenAI Realtime API communication.""" - -import warnings - -from pipecat.services.openai.realtime.events import * - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.openai_realtime.events are deprecated. " - "Please use the equivalent types from " - "pipecat.services.openai.realtime.events instead.", - DeprecationWarning, - stacklevel=2, - ) diff --git a/src/pipecat/services/openai_realtime/frames.py b/src/pipecat/services/openai_realtime/frames.py deleted file mode 100644 index c2db1eb70..000000000 --- a/src/pipecat/services/openai_realtime/frames.py +++ /dev/null @@ -1,21 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Custom frame types for OpenAI Realtime API integration.""" - -import warnings - -from pipecat.services.openai.realtime.frames import * - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "Types in pipecat.services.openai_realtime.frames are deprecated. " - "Please use the equivalent types from " - "pipecat.services.openai.realtime.frames instead.", - DeprecationWarning, - stacklevel=2, - ) diff --git a/src/pipecat/services/openai_realtime_beta/__init__.py b/src/pipecat/services/openai_realtime_beta/__init__.py deleted file mode 100644 index b7c976bb6..000000000 --- a/src/pipecat/services/openai_realtime_beta/__init__.py +++ /dev/null @@ -1,19 +0,0 @@ -from .azure import AzureRealtimeBetaLLMService -from .events import ( - InputAudioNoiseReduction, - InputAudioTranscription, - SemanticTurnDetection, - SessionProperties, - TurnDetection, -) -from .openai import OpenAIRealtimeBetaLLMService - -__all__ = [ - "AzureRealtimeBetaLLMService", - "InputAudioNoiseReduction", - "InputAudioTranscription", - "SemanticTurnDetection", - "SessionProperties", - "TurnDetection", - "OpenAIRealtimeBetaLLMService", -] diff --git a/src/pipecat/services/openai_realtime_beta/azure.py b/src/pipecat/services/openai_realtime_beta/azure.py deleted file mode 100644 index b590f2c29..000000000 --- a/src/pipecat/services/openai_realtime_beta/azure.py +++ /dev/null @@ -1,94 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Azure OpenAI Realtime Beta LLM service implementation.""" - -import warnings -from dataclasses import dataclass - -from loguru import logger - -from .openai import OpenAIRealtimeBetaLLMService - -try: - from websockets.asyncio.client import connect as websocket_connect -except ModuleNotFoundError as e: - logger.error(f"Exception: {e}") - logger.error( - "In order to use OpenAI, you need to `pip install pipecat-ai[openai]`. Also, set `OPENAI_API_KEY` environment variable." - ) - raise Exception(f"Missing module: {e}") - - -@dataclass -class AzureRealtimeBetaLLMSettings(OpenAIRealtimeBetaLLMService.Settings): - """Settings for AzureRealtimeBetaLLMService.""" - - pass - - -class AzureRealtimeBetaLLMService(OpenAIRealtimeBetaLLMService): - """Azure OpenAI Realtime Beta LLM service with Azure-specific authentication. - - .. deprecated:: 0.0.84 - `AzureRealtimeBetaLLMService` is deprecated, use `AzureRealtimeLLMService` instead. - This class will be removed in version 1.0.0. - - Extends the OpenAI Realtime service to work with Azure OpenAI endpoints, - using Azure's authentication headers and endpoint format. Provides the same - real-time audio and text communication capabilities as the base OpenAI service. - """ - - Settings = AzureRealtimeBetaLLMSettings - _settings: Settings - - def __init__( - self, - *, - api_key: str, - base_url: str, - **kwargs, - ): - """Initialize Azure Realtime Beta LLM service. - - Args: - api_key: The API key for the Azure OpenAI service. - base_url: The full Azure WebSocket endpoint URL including api-version and deployment. - Example: "wss://my-project.openai.azure.com/openai/realtime?api-version=2024-10-01-preview&deployment=my-realtime-deployment" - **kwargs: Additional arguments passed to parent OpenAIRealtimeBetaLLMService. - """ - super().__init__(base_url=base_url, api_key=api_key, **kwargs) - - with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "AzureRealtimeBetaLLMService is deprecated and will be removed in version 1.0.0. " - "Use AzureRealtimeLLMService instead.", - DeprecationWarning, - stacklevel=2, - ) - - self.api_key = api_key - self.base_url = base_url - - async def _connect(self): - try: - if self._websocket: - # Here we assume that if we have a websocket, we are connected. We - # handle disconnections in the send/recv code paths. - return - - logger.info(f"Connecting to {self.base_url}") - self._websocket = await websocket_connect( - uri=self.base_url, - additional_headers={ - "api-key": self.api_key, - }, - ) - self._receive_task = self.create_task(self._receive_task_handler()) - except Exception as e: - await self.push_error(error_msg=f"Error connecting: {e}", exception=e) - self._websocket = None diff --git a/src/pipecat/services/openai_realtime_beta/context.py b/src/pipecat/services/openai_realtime_beta/context.py deleted file mode 100644 index a1bbd6c92..000000000 --- a/src/pipecat/services/openai_realtime_beta/context.py +++ /dev/null @@ -1,272 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""OpenAI Realtime LLM context and aggregator implementations.""" - -import copy -import json - -from loguru import logger - -from pipecat.frames.frames import ( - Frame, - FunctionCallResultFrame, - InterimTranscriptionFrame, - LLMMessagesUpdateFrame, - LLMSetToolsFrame, - LLMTextFrame, - TranscriptionFrame, -) -from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext -from pipecat.processors.frame_processor import FrameDirection -from pipecat.services.openai.llm import ( - OpenAIAssistantContextAggregator, - OpenAIUserContextAggregator, -) - -from . import events -from .frames import RealtimeFunctionCallResultFrame, RealtimeMessagesUpdateFrame - - -class OpenAIRealtimeLLMContext(OpenAILLMContext): - """OpenAI Realtime LLM context with session management and message conversion. - - Extends the standard OpenAI LLM context to support real-time session properties, - instruction management, and conversion between standard message formats and - realtime conversation items. - """ - - def __init__(self, messages=None, tools=None, **kwargs): - """Initialize the OpenAIRealtimeLLMContext. - - Args: - messages: Initial conversation messages. Defaults to None. - tools: Available function tools. Defaults to None. - **kwargs: Additional arguments passed to parent OpenAILLMContext. - """ - super().__init__(messages=messages, tools=tools, **kwargs) - self.__setup_local() - - def __setup_local(self): - self.llm_needs_settings_update = True - self.llm_needs_initial_messages = True - self._session_instructions = "" - - return - - @staticmethod - def upgrade_to_realtime(obj: OpenAILLMContext) -> "OpenAIRealtimeLLMContext": - """Upgrade a standard OpenAI LLM context to a realtime context. - - Args: - obj: The OpenAILLMContext instance to upgrade. - - Returns: - The upgraded OpenAIRealtimeLLMContext instance. - """ - if isinstance(obj, OpenAILLMContext) and not isinstance(obj, OpenAIRealtimeLLMContext): - obj.__class__ = OpenAIRealtimeLLMContext - obj.__setup_local() - return obj - - # todo - # - finish implementing all frames - - def from_standard_message(self, message): - """Convert a standard message format to a realtime conversation item. - - Args: - message: The standard message dictionary to convert. - - Returns: - A ConversationItem instance for the realtime API. - """ - if message.get("role") == "user": - content = message.get("content") - if isinstance(message.get("content"), list): - content = "" - for c in message.get("content"): - if c.get("type") == "text": - content += " " + c.get("text") - else: - logger.error( - f"Unhandled content type in context message: {c.get('type')} - {message}" - ) - return events.ConversationItem( - role="user", - type="message", - content=[events.ItemContent(type="input_text", text=content)], - ) - if message.get("role") == "assistant" and message.get("tool_calls"): - tc = message.get("tool_calls")[0] - return events.ConversationItem( - type="function_call", - call_id=tc["id"], - name=tc["function"]["name"], - arguments=tc["function"]["arguments"], - ) - logger.error(f"Unhandled message type in from_standard_message: {message}") - - def get_messages_for_initializing_history(self): - """Get conversation items for initializing the realtime session history. - - Converts the context's messages to a format suitable for the realtime API, - handling system instructions and conversation history packaging. - - Returns: - List of conversation items for session initialization. - """ - # We can't load a long conversation history into the openai realtime api yet. (The API/model - # forgets that it can do audio, if you do a series of `conversation.item.create` calls.) So - # our general strategy until this is fixed is just to put everything into a first "user" - # message as a single input. - if not self.messages: - return [] - - messages = copy.deepcopy(self.messages) - - # If we have a "system" message as our first message, let's pull that out into session - # "instructions" - if messages[0].get("role") == "system": - self.llm_needs_settings_update = True - system = messages.pop(0) - content = system.get("content") - if isinstance(content, str): - self._session_instructions = content - elif isinstance(content, list): - self._session_instructions = content[0].get("text") - if not messages: - return [] - - # If we have just a single "user" item, we can just send it normally - if len(messages) == 1 and messages[0].get("role") == "user": - return [self.from_standard_message(messages[0])] - - # Otherwise, let's pack everything into a single "user" message with a bit of - # explanation for the LLM - intro_text = """ - This is a previously saved conversation. Please treat this conversation history as a - starting point for the current conversation.""" - - trailing_text = """ - This is the end of the previously saved conversation. Please continue the conversation - from here. If the last message is a user instruction or question, act on that instruction - or answer the question. If the last message is an assistant response, simple say that you - are ready to continue the conversation.""" - - return [ - { - "role": "user", - "type": "message", - "content": [ - { - "type": "input_text", - "text": "\n\n".join( - [intro_text, json.dumps(messages, indent=2), trailing_text] - ), - } - ], - } - ] - - def add_user_content_item_as_message(self, item): - """Add a user content item as a standard message to the context. - - Args: - item: The conversation item to add as a user message. - """ - message = { - "role": "user", - "content": [{"type": "text", "text": item.content[0].transcript}], - } - self.add_message(message) - - -class OpenAIRealtimeUserContextAggregator(OpenAIUserContextAggregator): - """User context aggregator for OpenAI Realtime API. - - Handles user input frames and generates appropriate context updates - for the realtime conversation, including message updates and tool settings. - - Args: - context: The OpenAI realtime LLM context. - **kwargs: Additional arguments passed to parent aggregator. - """ - - async def process_frame( - self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM - ): - """Process incoming frames and handle realtime-specific frame types. - - Args: - frame: The frame to process. - direction: The direction of frame flow in the pipeline. - """ - await super().process_frame(frame, direction) - # Parent does not push LLMMessagesUpdateFrame. This ensures that in a typical pipeline, - # messages are only processed by the user context aggregator, which is generally what we want. But - # we also need to send new messages over the websocket, so the openai realtime API has them - # in its context. - if isinstance(frame, LLMMessagesUpdateFrame): - await self.push_frame(RealtimeMessagesUpdateFrame(context=self._context)) - - # Parent also doesn't push the LLMSetToolsFrame. - if isinstance(frame, LLMSetToolsFrame): - await self.push_frame(frame, direction) - - async def push_aggregation(self): - """Push user input aggregation. - - Currently ignores all user input coming into the pipeline as realtime - audio input is handled directly by the service. - """ - # for the moment, ignore all user input coming into the pipeline. - # todo: think about whether/how to fix this to allow for text input from - # upstream (transport/transcription, or other sources) - pass - - -class OpenAIRealtimeAssistantContextAggregator(OpenAIAssistantContextAggregator): - """Assistant context aggregator for OpenAI Realtime API. - - Handles assistant output frames from the realtime service, filtering - out duplicate text frames and managing function call results. - - Args: - context: The OpenAI realtime LLM context. - **kwargs: Additional arguments passed to parent aggregator. - """ - - # The LLMAssistantContextAggregator uses TextFrames to aggregate the LLM output, - # but the OpenAIRealtimeLLMService pushes LLMTextFrames and TTSTextFrames. We - # need to override this proces_frame for LLMTextFrame, so that only the TTSTextFrames - # are process. This ensures that the context gets only one set of messages. - # OpenAIRealtimeLLMService also pushes TranscriptionFrames and InterimTranscriptionFrames, - # so we need to ignore pushing those as well, as they're also TextFrames. - async def process_frame(self, frame: Frame, direction: FrameDirection): - """Process assistant frames, filtering out duplicate text content. - - Args: - frame: The frame to process. - direction: The direction of frame flow in the pipeline. - """ - if not isinstance(frame, (LLMTextFrame, TranscriptionFrame, InterimTranscriptionFrame)): - await super().process_frame(frame, direction) - - async def handle_function_call_result(self, frame: FunctionCallResultFrame): - """Handle function call result and notify the realtime service. - - Args: - frame: The function call result frame to handle. - """ - await super().handle_function_call_result(frame) - - # The standard function callback code path pushes the FunctionCallResultFrame from the llm itself, - # so we didn't have a chance to add the result to the openai realtime api context. Let's push a - # special frame to do that. - await self.push_frame( - RealtimeFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM - ) diff --git a/src/pipecat/services/openai_realtime_beta/events.py b/src/pipecat/services/openai_realtime_beta/events.py deleted file mode 100644 index 596a11a3b..000000000 --- a/src/pipecat/services/openai_realtime_beta/events.py +++ /dev/null @@ -1,978 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Event models and data structures for OpenAI Realtime API communication.""" - -import json -import uuid -from typing import Any, Dict, List, Literal, Optional, Union - -from pydantic import BaseModel, ConfigDict, Field - -# -# session properties -# - - -class InputAudioTranscription(BaseModel): - """Configuration for audio transcription settings.""" - - model: str = "gpt-4o-transcribe" - language: Optional[str] - prompt: Optional[str] - - def __init__( - self, - model: Optional[str] = "gpt-4o-transcribe", - language: Optional[str] = None, - prompt: Optional[str] = None, - ): - """Initialize InputAudioTranscription. - - Args: - model: Transcription model to use (e.g., "gpt-4o-transcribe", "whisper-1"). - language: Optional language code for transcription. - prompt: Optional transcription hint text. - """ - super().__init__(model=model, language=language, prompt=prompt) - - -class TurnDetection(BaseModel): - """Server-side voice activity detection configuration. - - Parameters: - type: Detection type, must be "server_vad". - threshold: Voice activity detection threshold (0.0-1.0). Defaults to 0.5. - prefix_padding_ms: Padding before speech starts in milliseconds. Defaults to 300. - silence_duration_ms: Silence duration to detect speech end in milliseconds. Defaults to 800. - """ - - type: Optional[Literal["server_vad"]] = "server_vad" - threshold: Optional[float] = 0.5 - prefix_padding_ms: Optional[int] = 300 - silence_duration_ms: Optional[int] = 800 - - -class SemanticTurnDetection(BaseModel): - """Semantic-based turn detection configuration. - - Parameters: - type: Detection type, must be "semantic_vad". - eagerness: Turn detection eagerness level. Can be "low", "medium", "high", or "auto". - create_response: Whether to automatically create responses on turn detection. - interrupt_response: Whether to interrupt ongoing responses on turn detection. - """ - - type: Optional[Literal["semantic_vad"]] = "semantic_vad" - eagerness: Optional[Literal["low", "medium", "high", "auto"]] = None - create_response: Optional[bool] = None - interrupt_response: Optional[bool] = None - - -class InputAudioNoiseReduction(BaseModel): - """Input audio noise reduction configuration. - - Parameters: - type: Noise reduction type for different microphone scenarios. - """ - - type: Optional[Literal["near_field", "far_field"]] - - -class SessionProperties(BaseModel): - """Configuration properties for an OpenAI Realtime session. - - Parameters: - modalities: Communication modalities to enable (text, audio, or both). - instructions: System instructions for the assistant. - voice: Voice ID for text-to-speech output. - input_audio_format: Format for input audio data. - output_audio_format: Format for output audio data. - input_audio_transcription: Configuration for input audio transcription. - input_audio_noise_reduction: Configuration for input audio noise reduction. - turn_detection: Turn detection configuration or False to disable. - tools: Available function tools for the assistant. - tool_choice: Tool usage strategy ("auto", "none", or "required"). - temperature: Sampling temperature for response generation. - max_response_output_tokens: Maximum tokens in response or "inf" for unlimited. - """ - - modalities: Optional[List[Literal["text", "audio"]]] = None - instructions: Optional[str] = None - voice: Optional[str] = None - input_audio_format: Optional[Literal["pcm16", "g711_ulaw", "g711_alaw"]] = None - output_audio_format: Optional[Literal["pcm16", "g711_ulaw", "g711_alaw"]] = None - input_audio_transcription: Optional[InputAudioTranscription] = None - input_audio_noise_reduction: Optional[InputAudioNoiseReduction] = None - # set turn_detection to False to disable turn detection - turn_detection: Optional[Union[TurnDetection, SemanticTurnDetection, bool]] = Field( - default=None - ) - tools: Optional[List[Dict]] = None - tool_choice: Optional[Literal["auto", "none", "required"]] = None - temperature: Optional[float] = None - max_response_output_tokens: Optional[Union[int, Literal["inf"]]] = None - - -# -# context -# - - -class ItemContent(BaseModel): - """Content within a conversation item. - - Parameters: - type: Content type (text, audio, input_text, or input_audio). - text: Text content for text-based items. - audio: Base64-encoded audio data for audio items. - transcript: Transcribed text for audio items. - """ - - type: Literal["text", "audio", "input_text", "input_audio"] - text: Optional[str] = None - audio: Optional[str] = None # base64-encoded audio - transcript: Optional[str] = None - - -class ConversationItem(BaseModel): - """A conversation item in the realtime session. - - Parameters: - id: Unique identifier for the item, auto-generated if not provided. - object: Object type identifier for the realtime API. - type: Item type (message, function_call, or function_call_output). - status: Current status of the item. - role: Speaker role for message items (user, assistant, or system). - content: Content list for message items. - call_id: Function call identifier for function_call items. - name: Function name for function_call items. - arguments: Function arguments as JSON string for function_call items. - output: Function output as JSON string for function_call_output items. - """ - - id: str = Field(default_factory=lambda: str(uuid.uuid4().hex)) - object: Optional[Literal["realtime.item"]] = None - type: Literal["message", "function_call", "function_call_output"] - status: Optional[Literal["completed", "in_progress", "incomplete"]] = None - # role and content are present for message items - role: Optional[Literal["user", "assistant", "system"]] = None - content: Optional[List[ItemContent]] = None - # these four fields are present for function_call items - call_id: Optional[str] = None - name: Optional[str] = None - arguments: Optional[str] = None - output: Optional[str] = None - - -class RealtimeConversation(BaseModel): - """A realtime conversation session. - - Parameters: - id: Unique identifier for the conversation. - object: Object type identifier, always "realtime.conversation". - """ - - id: str - object: Literal["realtime.conversation"] - - -class ResponseProperties(BaseModel): - """Properties for configuring assistant responses. - - Parameters: - modalities: Output modalities for the response. Defaults to ["audio", "text"]. - instructions: Specific instructions for this response. - voice: Voice ID for text-to-speech in this response. - output_audio_format: Audio format for this response. - tools: Available tools for this response. - tool_choice: Tool usage strategy for this response. - temperature: Sampling temperature for this response. - max_response_output_tokens: Maximum tokens for this response. - """ - - modalities: Optional[List[Literal["text", "audio"]]] = ["audio", "text"] - instructions: Optional[str] = None - voice: Optional[str] = None - output_audio_format: Optional[Literal["pcm16", "g711_ulaw", "g711_alaw"]] = None - tools: Optional[List[Dict]] = Field(default_factory=list) - tool_choice: Optional[Literal["auto", "none", "required"]] = None - temperature: Optional[float] = None - max_response_output_tokens: Optional[Union[int, Literal["inf"]]] = None - - -# -# error class -# -class RealtimeError(BaseModel): - """Error information from the realtime API. - - Parameters: - type: Error type identifier. - code: Specific error code. - message: Human-readable error message. - param: Parameter name that caused the error, if applicable. - event_id: Event ID associated with the error, if applicable. - """ - - type: str - code: Optional[str] = "" - message: str - param: Optional[str] = None - event_id: Optional[str] = None - - -# -# client events -# - - -class ClientEvent(BaseModel): - """Base class for client events sent to the realtime API. - - Parameters: - event_id: Unique identifier for the event, auto-generated if not provided. - """ - - event_id: str = Field(default_factory=lambda: str(uuid.uuid4())) - - -class SessionUpdateEvent(ClientEvent): - """Event to update session properties. - - Parameters: - type: Event type, always "session.update". - session: Updated session properties. - """ - - type: Literal["session.update"] = "session.update" - session: SessionProperties - - def model_dump(self, *args, **kwargs) -> Dict[str, Any]: - """Serialize the event to a dictionary. - - Handles special serialization for turn_detection where False becomes null. - - Args: - *args: Positional arguments passed to parent model_dump. - **kwargs: Keyword arguments passed to parent model_dump. - - Returns: - Dictionary representation of the event. - """ - dump = super().model_dump(*args, **kwargs) - - # Handle turn_detection so that False is serialized as null - if "turn_detection" in dump["session"]: - if dump["session"]["turn_detection"] is False: - dump["session"]["turn_detection"] = None - - return dump - - -class InputAudioBufferAppendEvent(ClientEvent): - """Event to append audio data to the input buffer. - - Parameters: - type: Event type, always "input_audio_buffer.append". - audio: Base64-encoded audio data to append. - """ - - type: Literal["input_audio_buffer.append"] = "input_audio_buffer.append" - audio: str # base64-encoded audio - - -class InputAudioBufferCommitEvent(ClientEvent): - """Event to commit the current input audio buffer. - - Parameters: - type: Event type, always "input_audio_buffer.commit". - """ - - type: Literal["input_audio_buffer.commit"] = "input_audio_buffer.commit" - - -class InputAudioBufferClearEvent(ClientEvent): - """Event to clear the input audio buffer. - - Parameters: - type: Event type, always "input_audio_buffer.clear". - """ - - type: Literal["input_audio_buffer.clear"] = "input_audio_buffer.clear" - - -class ConversationItemCreateEvent(ClientEvent): - """Event to create a new conversation item. - - Parameters: - type: Event type, always "conversation.item.create". - previous_item_id: ID of the item to insert after, if any. - item: The conversation item to create. - """ - - type: Literal["conversation.item.create"] = "conversation.item.create" - previous_item_id: Optional[str] = None - item: ConversationItem - - -class ConversationItemTruncateEvent(ClientEvent): - """Event to truncate a conversation item's audio content. - - Parameters: - type: Event type, always "conversation.item.truncate". - item_id: ID of the item to truncate. - content_index: Index of the content to truncate within the item. - audio_end_ms: End time in milliseconds for the truncated audio. - """ - - type: Literal["conversation.item.truncate"] = "conversation.item.truncate" - item_id: str - content_index: int - audio_end_ms: int - - -class ConversationItemDeleteEvent(ClientEvent): - """Event to delete a conversation item. - - Parameters: - type: Event type, always "conversation.item.delete". - item_id: ID of the item to delete. - """ - - type: Literal["conversation.item.delete"] = "conversation.item.delete" - item_id: str - - -class ConversationItemRetrieveEvent(ClientEvent): - """Event to retrieve a conversation item by ID. - - Parameters: - type: Event type, always "conversation.item.retrieve". - item_id: ID of the item to retrieve. - """ - - type: Literal["conversation.item.retrieve"] = "conversation.item.retrieve" - item_id: str - - -class ResponseCreateEvent(ClientEvent): - """Event to create a new assistant response. - - Parameters: - type: Event type, always "response.create". - response: Optional response configuration properties. - """ - - type: Literal["response.create"] = "response.create" - response: Optional[ResponseProperties] = None - - -class ResponseCancelEvent(ClientEvent): - """Event to cancel the current assistant response. - - Parameters: - type: Event type, always "response.cancel". - """ - - type: Literal["response.cancel"] = "response.cancel" - - -# -# server events -# - - -class ServerEvent(BaseModel): - """Base class for server events received from the realtime API. - - Parameters: - event_id: Unique identifier for the event. - type: Type of the server event. - """ - - model_config = ConfigDict(arbitrary_types_allowed=True) - - event_id: str - type: str - - -class SessionCreatedEvent(ServerEvent): - """Event indicating a session has been created. - - Parameters: - type: Event type, always "session.created". - session: The created session properties. - """ - - type: Literal["session.created"] - session: SessionProperties - - -class SessionUpdatedEvent(ServerEvent): - """Event indicating a session has been updated. - - Parameters: - type: Event type, always "session.updated". - session: The updated session properties. - """ - - type: Literal["session.updated"] - session: SessionProperties - - -class ConversationCreated(ServerEvent): - """Event indicating a conversation has been created. - - Parameters: - type: Event type, always "conversation.created". - conversation: The created conversation. - """ - - type: Literal["conversation.created"] - conversation: RealtimeConversation - - -class ConversationItemCreated(ServerEvent): - """Event indicating a conversation item has been created. - - Parameters: - type: Event type, always "conversation.item.created". - previous_item_id: ID of the previous item, if any. - item: The created conversation item. - """ - - type: Literal["conversation.item.created"] - previous_item_id: Optional[str] = None - item: ConversationItem - - -class ConversationItemInputAudioTranscriptionDelta(ServerEvent): - """Event containing incremental input audio transcription. - - Parameters: - type: Event type, always "conversation.item.input_audio_transcription.delta". - item_id: ID of the conversation item being transcribed. - content_index: Index of the content within the item. - delta: Incremental transcription text. - """ - - type: Literal["conversation.item.input_audio_transcription.delta"] - item_id: str - content_index: int - delta: str - - -class ConversationItemInputAudioTranscriptionCompleted(ServerEvent): - """Event indicating input audio transcription is complete. - - Parameters: - type: Event type, always "conversation.item.input_audio_transcription.completed". - item_id: ID of the conversation item that was transcribed. - content_index: Index of the content within the item. - transcript: Complete transcription text. - """ - - type: Literal["conversation.item.input_audio_transcription.completed"] - item_id: str - content_index: int - transcript: str - - -class ConversationItemInputAudioTranscriptionFailed(ServerEvent): - """Event indicating input audio transcription failed. - - Parameters: - type: Event type, always "conversation.item.input_audio_transcription.failed". - item_id: ID of the conversation item that failed transcription. - content_index: Index of the content within the item. - error: Error details for the transcription failure. - """ - - type: Literal["conversation.item.input_audio_transcription.failed"] - item_id: str - content_index: int - error: RealtimeError - - -class ConversationItemTruncated(ServerEvent): - """Event indicating a conversation item has been truncated. - - Parameters: - type: Event type, always "conversation.item.truncated". - item_id: ID of the truncated conversation item. - content_index: Index of the content within the item. - audio_end_ms: End time in milliseconds for the truncated audio. - """ - - type: Literal["conversation.item.truncated"] - item_id: str - content_index: int - audio_end_ms: int - - -class ConversationItemDeleted(ServerEvent): - """Event indicating a conversation item has been deleted. - - Parameters: - type: Event type, always "conversation.item.deleted". - item_id: ID of the deleted conversation item. - """ - - type: Literal["conversation.item.deleted"] - item_id: str - - -class ConversationItemRetrieved(ServerEvent): - """Event containing a retrieved conversation item. - - Parameters: - type: Event type, always "conversation.item.retrieved". - item: The retrieved conversation item. - """ - - type: Literal["conversation.item.retrieved"] - item: ConversationItem - - -class ResponseCreated(ServerEvent): - """Event indicating an assistant response has been created. - - Parameters: - type: Event type, always "response.created". - response: The created response object. - """ - - type: Literal["response.created"] - response: "Response" - - -class ResponseDone(ServerEvent): - """Event indicating an assistant response is complete. - - Parameters: - type: Event type, always "response.done". - response: The completed response object. - """ - - type: Literal["response.done"] - response: "Response" - - -class ResponseOutputItemAdded(ServerEvent): - """Event indicating an output item has been added to a response. - - Parameters: - type: Event type, always "response.output_item.added". - response_id: ID of the response. - output_index: Index of the output item. - item: The added conversation item. - """ - - type: Literal["response.output_item.added"] - response_id: str - output_index: int - item: ConversationItem - - -class ResponseOutputItemDone(ServerEvent): - """Event indicating an output item is complete. - - Parameters: - type: Event type, always "response.output_item.done". - response_id: ID of the response. - output_index: Index of the output item. - item: The completed conversation item. - """ - - type: Literal["response.output_item.done"] - response_id: str - output_index: int - item: ConversationItem - - -class ResponseContentPartAdded(ServerEvent): - """Event indicating a content part has been added to a response. - - Parameters: - type: Event type, always "response.content_part.added". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - part: The added content part. - """ - - type: Literal["response.content_part.added"] - response_id: str - item_id: str - output_index: int - content_index: int - part: ItemContent - - -class ResponseContentPartDone(ServerEvent): - """Event indicating a content part is complete. - - Parameters: - type: Event type, always "response.content_part.done". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - part: The completed content part. - """ - - type: Literal["response.content_part.done"] - response_id: str - item_id: str - output_index: int - content_index: int - part: ItemContent - - -class ResponseTextDelta(ServerEvent): - """Event containing incremental text from a response. - - Parameters: - type: Event type, always "response.text.delta". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - delta: Incremental text content. - """ - - type: Literal["response.text.delta"] - response_id: str - item_id: str - output_index: int - content_index: int - delta: str - - -class ResponseTextDone(ServerEvent): - """Event indicating text content is complete. - - Parameters: - type: Event type, always "response.text.done". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - text: Complete text content. - """ - - type: Literal["response.text.done"] - response_id: str - item_id: str - output_index: int - content_index: int - text: str - - -class ResponseAudioTranscriptDelta(ServerEvent): - """Event containing incremental audio transcript from a response. - - Parameters: - type: Event type, always "response.audio_transcript.delta". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - delta: Incremental transcript text. - """ - - type: Literal["response.audio_transcript.delta"] - response_id: str - item_id: str - output_index: int - content_index: int - delta: str - - -class ResponseAudioTranscriptDone(ServerEvent): - """Event indicating audio transcript is complete. - - Parameters: - type: Event type, always "response.audio_transcript.done". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - transcript: Complete transcript text. - """ - - type: Literal["response.audio_transcript.done"] - response_id: str - item_id: str - output_index: int - content_index: int - transcript: str - - -class ResponseAudioDelta(ServerEvent): - """Event containing incremental audio data from a response. - - Parameters: - type: Event type, always "response.audio.delta". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - delta: Base64-encoded incremental audio data. - """ - - type: Literal["response.audio.delta"] - response_id: str - item_id: str - output_index: int - content_index: int - delta: str # base64-encoded audio - - -class ResponseAudioDone(ServerEvent): - """Event indicating audio content is complete. - - Parameters: - type: Event type, always "response.audio.done". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - content_index: Index of the content part. - """ - - type: Literal["response.audio.done"] - response_id: str - item_id: str - output_index: int - content_index: int - - -class ResponseFunctionCallArgumentsDelta(ServerEvent): - """Event containing incremental function call arguments. - - Parameters: - type: Event type, always "response.function_call_arguments.delta". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - call_id: ID of the function call. - delta: Incremental function arguments as JSON. - """ - - type: Literal["response.function_call_arguments.delta"] - response_id: str - item_id: str - output_index: int - call_id: str - delta: str - - -class ResponseFunctionCallArgumentsDone(ServerEvent): - """Event indicating function call arguments are complete. - - Parameters: - type: Event type, always "response.function_call_arguments.done". - response_id: ID of the response. - item_id: ID of the conversation item. - output_index: Index of the output item. - call_id: ID of the function call. - arguments: Complete function arguments as JSON string. - """ - - type: Literal["response.function_call_arguments.done"] - response_id: str - item_id: str - output_index: int - call_id: str - arguments: str - - -class InputAudioBufferSpeechStarted(ServerEvent): - """Event indicating speech has started in the input audio buffer. - - Parameters: - type: Event type, always "input_audio_buffer.speech_started". - audio_start_ms: Start time of speech in milliseconds. - item_id: ID of the associated conversation item. - """ - - type: Literal["input_audio_buffer.speech_started"] - audio_start_ms: int - item_id: str - - -class InputAudioBufferSpeechStopped(ServerEvent): - """Event indicating speech has stopped in the input audio buffer. - - Parameters: - type: Event type, always "input_audio_buffer.speech_stopped". - audio_end_ms: End time of speech in milliseconds. - item_id: ID of the associated conversation item. - """ - - type: Literal["input_audio_buffer.speech_stopped"] - audio_end_ms: int - item_id: str - - -class InputAudioBufferCommitted(ServerEvent): - """Event indicating the input audio buffer has been committed. - - Parameters: - type: Event type, always "input_audio_buffer.committed". - previous_item_id: ID of the previous item, if any. - item_id: ID of the committed conversation item. - """ - - type: Literal["input_audio_buffer.committed"] - previous_item_id: Optional[str] = None - item_id: str - - -class InputAudioBufferCleared(ServerEvent): - """Event indicating the input audio buffer has been cleared. - - Parameters: - type: Event type, always "input_audio_buffer.cleared". - """ - - type: Literal["input_audio_buffer.cleared"] - - -class ErrorEvent(ServerEvent): - """Event indicating an error occurred. - - Parameters: - type: Event type, always "error". - error: Error details. - """ - - type: Literal["error"] - error: RealtimeError - - -class RateLimitsUpdated(ServerEvent): - """Event indicating rate limits have been updated. - - Parameters: - type: Event type, always "rate_limits.updated". - rate_limits: List of rate limit information. - """ - - type: Literal["rate_limits.updated"] - rate_limits: List[Dict[str, Any]] - - -class TokenDetails(BaseModel): - """Detailed token usage information. - - Parameters: - cached_tokens: Number of cached tokens used. Defaults to 0. - text_tokens: Number of text tokens used. Defaults to 0. - audio_tokens: Number of audio tokens used. Defaults to 0. - """ - - model_config = ConfigDict(extra="allow") - - cached_tokens: Optional[int] = 0 - text_tokens: Optional[int] = 0 - audio_tokens: Optional[int] = 0 - - -class Usage(BaseModel): - """Token usage statistics for a response. - - Parameters: - total_tokens: Total number of tokens used. - input_tokens: Number of input tokens used. - output_tokens: Number of output tokens used. - input_token_details: Detailed breakdown of input token usage. - output_token_details: Detailed breakdown of output token usage. - """ - - total_tokens: int - input_tokens: int - output_tokens: int - input_token_details: TokenDetails - output_token_details: TokenDetails - - -class Response(BaseModel): - """A complete assistant response. - - Parameters: - id: Unique identifier for the response. - object: Object type, always "realtime.response". - status: Current status of the response. - status_details: Additional status information. - output: List of conversation items in the response. - usage: Token usage statistics for the response. - """ - - id: str - object: Literal["realtime.response"] - status: Literal["completed", "in_progress", "incomplete", "cancelled", "failed"] - status_details: Any - output: List[ConversationItem] - usage: Optional[Usage] = None - - -_server_event_types = { - "error": ErrorEvent, - "session.created": SessionCreatedEvent, - "session.updated": SessionUpdatedEvent, - "conversation.created": ConversationCreated, - "input_audio_buffer.committed": InputAudioBufferCommitted, - "input_audio_buffer.cleared": InputAudioBufferCleared, - "input_audio_buffer.speech_started": InputAudioBufferSpeechStarted, - "input_audio_buffer.speech_stopped": InputAudioBufferSpeechStopped, - "conversation.item.created": ConversationItemCreated, - "conversation.item.input_audio_transcription.delta": ConversationItemInputAudioTranscriptionDelta, - "conversation.item.input_audio_transcription.completed": ConversationItemInputAudioTranscriptionCompleted, - "conversation.item.input_audio_transcription.failed": ConversationItemInputAudioTranscriptionFailed, - "conversation.item.truncated": ConversationItemTruncated, - "conversation.item.deleted": ConversationItemDeleted, - "conversation.item.retrieved": ConversationItemRetrieved, - "response.created": ResponseCreated, - "response.done": ResponseDone, - "response.output_item.added": ResponseOutputItemAdded, - "response.output_item.done": ResponseOutputItemDone, - "response.content_part.added": ResponseContentPartAdded, - "response.content_part.done": ResponseContentPartDone, - "response.text.delta": ResponseTextDelta, - "response.text.done": ResponseTextDone, - "response.audio_transcript.delta": ResponseAudioTranscriptDelta, - "response.audio_transcript.done": ResponseAudioTranscriptDone, - "response.audio.delta": ResponseAudioDelta, - "response.audio.done": ResponseAudioDone, - "response.function_call_arguments.delta": ResponseFunctionCallArgumentsDelta, - "response.function_call_arguments.done": ResponseFunctionCallArgumentsDone, - "rate_limits.updated": RateLimitsUpdated, -} - - -def parse_server_event(str): - """Parse a server event from JSON string. - - Args: - str: JSON string containing the server event. - - Returns: - Parsed server event object of the appropriate type. - - Raises: - Exception: If the event type is unimplemented or parsing fails. - """ - try: - event = json.loads(str) - event_type = event["type"] - if event_type not in _server_event_types: - raise Exception(f"Unimplemented server event type: {event_type}") - return _server_event_types[event_type].model_validate(event) - except Exception as e: - raise Exception(f"{e} \n\n{str}") diff --git a/src/pipecat/services/openai_realtime_beta/frames.py b/src/pipecat/services/openai_realtime_beta/frames.py deleted file mode 100644 index 02ef64000..000000000 --- a/src/pipecat/services/openai_realtime_beta/frames.py +++ /dev/null @@ -1,37 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Custom frame types for OpenAI Realtime API integration.""" - -from dataclasses import dataclass -from typing import TYPE_CHECKING - -from pipecat.frames.frames import DataFrame, FunctionCallResultFrame - -if TYPE_CHECKING: - from pipecat.services.openai_realtime_beta.context import OpenAIRealtimeLLMContext - - -@dataclass -class RealtimeMessagesUpdateFrame(DataFrame): - """Frame indicating that the realtime context messages have been updated. - - Parameters: - context: The updated OpenAI realtime LLM context. - """ - - context: "OpenAIRealtimeLLMContext" - - -@dataclass -class RealtimeFunctionCallResultFrame(DataFrame): - """Frame containing function call results for the realtime service. - - Parameters: - result_frame: The function call result frame to send to the realtime API. - """ - - result_frame: FunctionCallResultFrame diff --git a/src/pipecat/services/openai_realtime_beta/openai.py b/src/pipecat/services/openai_realtime_beta/openai.py deleted file mode 100644 index 0d20039b1..000000000 --- a/src/pipecat/services/openai_realtime_beta/openai.py +++ /dev/null @@ -1,858 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""OpenAI Realtime Beta LLM service implementation with WebSocket support.""" - -import base64 -import json -import time -import warnings -from dataclasses import dataclass -from typing import Optional - -from loguru import logger - -from pipecat.adapters.services.open_ai_realtime_adapter import OpenAIRealtimeLLMAdapter -from pipecat.frames.frames import ( - AggregationType, - BotStoppedSpeakingFrame, - CancelFrame, - EndFrame, - ErrorFrame, - Frame, - InputAudioRawFrame, - InterimTranscriptionFrame, - InterruptionFrame, - LLMContextFrame, - LLMFullResponseEndFrame, - LLMFullResponseStartFrame, - LLMMessagesAppendFrame, - LLMSetToolsFrame, - LLMTextFrame, - LLMUpdateSettingsFrame, - StartFrame, - TranscriptionFrame, - TTSAudioRawFrame, - TTSStartedFrame, - TTSStoppedFrame, - TTSTextFrame, - UserStartedSpeakingFrame, - UserStoppedSpeakingFrame, -) -from pipecat.metrics.metrics import LLMTokenUsage -from pipecat.processors.aggregators.llm_response import ( - LLMAssistantAggregatorParams, - LLMUserAggregatorParams, -) -from pipecat.processors.aggregators.openai_llm_context import ( - OpenAILLMContext, - OpenAILLMContextFrame, -) -from pipecat.processors.frame_processor import FrameDirection -from pipecat.services.llm_service import FunctionCallFromLLM, LLMService -from pipecat.services.openai.llm import OpenAIContextAggregatorPair -from pipecat.services.settings import LLMSettings -from pipecat.transcriptions.language import Language -from pipecat.utils.time import time_now_iso8601 -from pipecat.utils.tracing.service_decorators import traced_openai_realtime, traced_stt - -from . import events -from .context import ( - OpenAIRealtimeAssistantContextAggregator, - OpenAIRealtimeLLMContext, - OpenAIRealtimeUserContextAggregator, -) -from .frames import RealtimeFunctionCallResultFrame, RealtimeMessagesUpdateFrame - -try: - from websockets.asyncio.client import connect as websocket_connect -except ModuleNotFoundError as e: - logger.error(f"Exception: {e}") - logger.error("In order to use OpenAI, you need to `pip install pipecat-ai[openai]`.") - raise Exception(f"Missing module: {e}") - - -@dataclass -class CurrentAudioResponse: - """Tracks the current audio response from the assistant. - - Parameters: - item_id: Unique identifier for the audio response item. - content_index: Index of the audio content within the item. - start_time_ms: Timestamp when the audio response started in milliseconds. - total_size: Total size of audio data received in bytes. Defaults to 0. - """ - - item_id: str - content_index: int - start_time_ms: int - total_size: int = 0 - - -@dataclass -class OpenAIRealtimeBetaLLMSettings(LLMSettings): - """Settings for OpenAIRealtimeBetaLLMService.""" - - pass - - -class OpenAIRealtimeBetaLLMService(LLMService): - """OpenAI Realtime Beta LLM service providing real-time audio and text communication. - - .. deprecated:: 0.0.84 - `OpenAIRealtimeBetaLLMService` is deprecated, use `OpenAIRealtimeLLMService` instead. - This class will be removed in version 1.0.0. - - Implements the OpenAI Realtime API Beta with WebSocket communication for low-latency - bidirectional audio and text interactions. Supports function calling, conversation - management, and real-time transcription. - """ - - Settings = OpenAIRealtimeBetaLLMSettings - _settings: Settings - - # Overriding the default adapter to use the OpenAIRealtimeLLMAdapter one. - adapter_class = OpenAIRealtimeLLMAdapter - - def __init__( - self, - *, - api_key: str, - model: Optional[str] = None, - base_url: str = "wss://api.openai.com/v1/realtime", - session_properties: Optional[events.SessionProperties] = None, - settings: Optional[Settings] = None, - start_audio_paused: bool = False, - send_transcription_frames: bool = True, - **kwargs, - ): - """Initialize the OpenAI Realtime Beta LLM service. - - Args: - api_key: OpenAI API key for authentication. - model: OpenAI model name. - - .. deprecated:: 0.0.105 - Use ``settings=OpenAIRealtimeBetaLLMService.Settings(model=...)`` instead. - - base_url: WebSocket base URL for the realtime API. - Defaults to "wss://api.openai.com/v1/realtime". - session_properties: Configuration properties for the realtime session. - If None, uses default SessionProperties. - settings: Runtime-updatable settings for this service. - start_audio_paused: Whether to start with audio input paused. Defaults to False. - send_transcription_frames: Whether to emit transcription frames. Defaults to True. - **kwargs: Additional arguments passed to parent LLMService. - """ - with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "OpenAIRealtimeBetaLLMService is deprecated and will be removed in version 1.0.0. " - "Use OpenAIRealtimeLLMService instead.", - DeprecationWarning, - stacklevel=2, - ) - - # 1. Initialize default_settings with hardcoded defaults - default_settings = self.Settings( - model="gpt-4o-realtime-preview-2025-06-03", - system_instruction=None, - temperature=None, - max_tokens=None, - top_p=None, - top_k=None, - frequency_penalty=None, - presence_penalty=None, - seed=None, - filter_incomplete_user_turns=False, - user_turn_completion_config=None, - ) - - # 2. Apply direct init arg overrides (deprecated) - if model is not None: - self._warn_init_param_moved_to_settings("model", "model") - default_settings.model = model - # 3. Apply settings delta (canonical API, always wins) - if settings is not None: - default_settings.apply_update(settings) - - full_url = f"{base_url}?model={default_settings.model}" - super().__init__( - base_url=full_url, - settings=default_settings, - **kwargs, - ) - - self.api_key = api_key - self.base_url = full_url - self._session_properties = session_properties or events.SessionProperties() - self._audio_input_paused = start_audio_paused - self._send_transcription_frames = send_transcription_frames - self._websocket = None - self._receive_task = None - self._context = None - - self._disconnecting = False - self._api_session_ready = False - self._run_llm_when_api_session_ready = False - - self._current_assistant_response = None - self._current_audio_response = None - - self._messages_added_manually = {} - self._user_and_response_message_tuple = None - - self._register_event_handler("on_conversation_item_created") - self._register_event_handler("on_conversation_item_updated") - self._retrieve_conversation_item_futures = {} - - def can_generate_metrics(self) -> bool: - """Check if the service can generate usage metrics. - - Returns: - True if metrics generation is supported. - """ - return True - - def set_audio_input_paused(self, paused: bool): - """Set whether audio input is paused. - - Args: - paused: True to pause audio input, False to resume. - """ - self._audio_input_paused = paused - - def _is_modality_enabled(self, modality: str) -> bool: - """Check if a specific modality is enabled, "text" or "audio".""" - modalities = self._session_properties.modalities or ["audio", "text"] - return modality in modalities - - def _get_enabled_modalities(self) -> list[str]: - """Get the list of enabled modalities.""" - return self._session_properties.modalities or ["audio", "text"] - - async def retrieve_conversation_item(self, item_id: str): - """Retrieve a conversation item by ID from the server. - - Args: - item_id: The ID of the conversation item to retrieve. - - Returns: - The retrieved conversation item. - """ - future = self.get_event_loop().create_future() - retrieval_in_flight = False - if not self._retrieve_conversation_item_futures.get(item_id): - self._retrieve_conversation_item_futures[item_id] = [] - else: - retrieval_in_flight = True - self._retrieve_conversation_item_futures[item_id].append(future) - if not retrieval_in_flight: - await self.send_client_event( - # Set event_id to "rci_{item_id}" so that we can identify an - # error later if the retrieval fails. We don't need a UUID - # suffix to the event_id because we're ensuring only one - # in-flight retrieval per item_id. (Note: "rci" = "retrieve - # conversation item") - events.ConversationItemRetrieveEvent(item_id=item_id, event_id=f"rci_{item_id}") - ) - return await future - - # - # standard AIService frame handling - # - - async def start(self, frame: StartFrame): - """Start the service and establish WebSocket connection. - - Args: - frame: The start frame triggering service initialization. - """ - await super().start(frame) - await self._connect() - - async def stop(self, frame: EndFrame): - """Stop the service and close WebSocket connection. - - Args: - frame: The end frame triggering service shutdown. - """ - await super().stop(frame) - await self._disconnect() - - async def cancel(self, frame: CancelFrame): - """Cancel the service and close WebSocket connection. - - Args: - frame: The cancel frame triggering service cancellation. - """ - await super().cancel(frame) - await self._disconnect() - - # - # speech and interruption handling - # - - async def _handle_interruption(self): - # None and False are different. Check for False. None means we're using OpenAI's - # built-in turn detection defaults. - if self._session_properties.turn_detection is False: - await self.send_client_event(events.InputAudioBufferClearEvent()) - await self.send_client_event(events.ResponseCancelEvent()) - await self._truncate_current_audio_response() - await self.stop_all_metrics() - if self._current_assistant_response: - await self.push_frame(LLMFullResponseEndFrame()) - # Only push TTSStoppedFrame if audio modality is enabled - if self._is_modality_enabled("audio"): - await self.push_frame(TTSStoppedFrame()) - - async def _handle_user_started_speaking(self, frame): - pass - - async def _handle_user_stopped_speaking(self, frame): - # None and False are different. Check for False. None means we're using OpenAI's - # built-in turn detection defaults. - if self._session_properties.turn_detection is False: - await self.send_client_event(events.InputAudioBufferCommitEvent()) - await self.send_client_event(events.ResponseCreateEvent()) - - async def _handle_bot_stopped_speaking(self): - self._current_audio_response = None - - def _calculate_audio_duration_ms( - self, total_bytes: int, sample_rate: int = 24000, bytes_per_sample: int = 2 - ) -> int: - """Calculate audio duration in milliseconds based on PCM audio parameters.""" - samples = total_bytes / bytes_per_sample - duration_seconds = samples / sample_rate - return int(duration_seconds * 1000) - - async def _truncate_current_audio_response(self): - """Truncates the current audio response at the appropriate duration. - - Calculates the actual duration of the audio content and truncates at the shorter of - either the wall clock time or the actual audio duration to prevent invalid truncation - requests. - """ - if not self._current_audio_response: - return - - # if the bot is still speaking, truncate the last message - try: - current = self._current_audio_response - self._current_audio_response = None - - # Calculate actual audio duration instead of using wall clock time - audio_duration_ms = self._calculate_audio_duration_ms(current.total_size) - - # Use the shorter of wall clock time or actual audio duration - elapsed_ms = int(time.time() * 1000 - current.start_time_ms) - truncate_ms = min(elapsed_ms, audio_duration_ms) - - logger.trace( - f"Truncating audio: duration={audio_duration_ms}ms, " - f"elapsed={elapsed_ms}ms, truncate={truncate_ms}ms" - ) - - await self.send_client_event( - events.ConversationItemTruncateEvent( - item_id=current.item_id, - content_index=current.content_index, - audio_end_ms=truncate_ms, - ) - ) - except Exception as e: - # Log warning and don't re-raise - allow session to continue - logger.warning(f"Audio truncation failed (non-fatal): {e}") - - # - # frame processing - # - # StartFrame, StopFrame, CancelFrame implemented in base class - # - - async def process_frame(self, frame: Frame, direction: FrameDirection): - """Process incoming frames from the pipeline. - - Args: - frame: The frame to process. - direction: The direction of frame flow in the pipeline. - """ - # Backward-compatible dict path: frame.settings contains SessionProperties - # fields, not our Settings fields, so we construct SessionProperties - # directly. The frame.delta path falls through to super, which calls - # _update_settings → our override handles the rest. - if isinstance(frame, LLMUpdateSettingsFrame) and frame.delta is None: - self._session_properties = events.SessionProperties(**frame.settings) - await self._send_session_update() - await self.push_frame(frame, direction) - return - - await super().process_frame(frame, direction) - - if isinstance(frame, TranscriptionFrame): - pass - elif isinstance(frame, OpenAILLMContextFrame): - context: OpenAIRealtimeLLMContext = OpenAIRealtimeLLMContext.upgrade_to_realtime( - frame.context - ) - if not self._context: - self._context = context - elif frame.context is not self._context: - # If the context has changed, reset the conversation - self._context = context - await self.reset_conversation() - # Run the LLM at next opportunity - await self._create_response() - elif isinstance(frame, LLMContextFrame): - raise NotImplementedError( - "Universal LLMContext is not yet supported for OpenAI Realtime." - ) - elif isinstance(frame, InputAudioRawFrame): - if not self._audio_input_paused: - await self._send_user_audio(frame) - elif isinstance(frame, InterruptionFrame): - await self._handle_interruption() - elif isinstance(frame, UserStartedSpeakingFrame): - await self._handle_user_started_speaking(frame) - elif isinstance(frame, UserStoppedSpeakingFrame): - await self._handle_user_stopped_speaking(frame) - elif isinstance(frame, BotStoppedSpeakingFrame): - await self._handle_bot_stopped_speaking() - elif isinstance(frame, LLMMessagesAppendFrame): - await self._handle_messages_append(frame) - elif isinstance(frame, RealtimeMessagesUpdateFrame): - self._context = frame.context - elif isinstance(frame, LLMSetToolsFrame): - await self._send_session_update() - elif isinstance(frame, RealtimeFunctionCallResultFrame): - await self._handle_function_call_result(frame.result_frame) - - await self.push_frame(frame, direction) - - async def _handle_messages_append(self, frame): - logger.error("!!! NEED TO IMPLEMENT MESSAGES APPEND") - - async def _handle_function_call_result(self, frame): - item = events.ConversationItem( - type="function_call_output", - call_id=frame.tool_call_id, - output=json.dumps(frame.result, ensure_ascii=False), - ) - await self.send_client_event(events.ConversationItemCreateEvent(item=item)) - - # - # websocket communication - # - - async def send_client_event(self, event: events.ClientEvent): - """Send a client event to the OpenAI Realtime API. - - Args: - event: The client event to send. - """ - await self._ws_send(event.model_dump(exclude_none=True)) - - async def _connect(self): - try: - if self._websocket: - # Here we assume that if we have a websocket, we are connected. We - # handle disconnections in the send/recv code paths. - return - self._websocket = await websocket_connect( - uri=self.base_url, - additional_headers={ - "Authorization": f"Bearer {self.api_key}", - "OpenAI-Beta": "realtime=v1", - }, - ) - self._receive_task = self.create_task(self._receive_task_handler()) - except Exception as e: - await self.push_error(error_msg=f"Error connecting: {e}", exception=e) - self._websocket = None - - async def _disconnect(self): - try: - self._disconnecting = True - self._api_session_ready = False - await self.stop_all_metrics() - if self._websocket: - await self._websocket.close() - self._websocket = None - if self._receive_task: - await self.cancel_task(self._receive_task, timeout=1.0) - self._receive_task = None - self._disconnecting = False - except Exception as e: - await self.push_error(error_msg=f"Error disconnecting: {e}", exception=e) - - async def _ws_send(self, realtime_message): - try: - if self._websocket: - await self._websocket.send(json.dumps(realtime_message)) - except Exception as e: - if self._disconnecting: - return - # In server-to-server contexts, a WebSocket error should be quite rare. Given how hard - # it is to recover from a send-side error with proper state management, and that exponential - # backoff for retries can have cost/stability implications for a service cluster, let's just - # treat a send-side error as fatal. - await self.push_error(error_msg=f"Error sending client event: {e}", exception=e) - - async def _update_settings(self, delta): - """Apply a settings delta.""" - changed = await super()._update_settings(delta) - self._warn_unhandled_updated_settings(changed.keys()) - return changed - - async def _send_session_update(self): - settings = self._session_properties - # tools given in the context override the tools in the session properties - if self._context and self._context.tools: - settings.tools = self._context.tools - # instructions in the context come from an initial "system" message in the - # messages list, and override instructions in the session properties - if self._context and self._context._session_instructions: - settings.instructions = self._context._session_instructions - await self.send_client_event(events.SessionUpdateEvent(session=settings)) - - # - # inbound server event handling - # https://platform.openai.com/docs/api-reference/realtime-server-events - # - - async def _receive_task_handler(self): - async for message in self._websocket: - evt = events.parse_server_event(message) - if evt.type == "session.created": - await self._handle_evt_session_created(evt) - elif evt.type == "session.updated": - await self._handle_evt_session_updated(evt) - elif evt.type == "response.audio.delta": - await self._handle_evt_audio_delta(evt) - elif evt.type == "response.audio.done": - await self._handle_evt_audio_done(evt) - elif evt.type == "conversation.item.created": - await self._handle_evt_conversation_item_created(evt) - elif evt.type == "conversation.item.input_audio_transcription.delta": - await self._handle_evt_input_audio_transcription_delta(evt) - elif evt.type == "conversation.item.input_audio_transcription.completed": - await self.handle_evt_input_audio_transcription_completed(evt) - elif evt.type == "conversation.item.retrieved": - await self._handle_conversation_item_retrieved(evt) - elif evt.type == "response.done": - await self._handle_evt_response_done(evt) - elif evt.type == "input_audio_buffer.speech_started": - await self._handle_evt_speech_started(evt) - elif evt.type == "input_audio_buffer.speech_stopped": - await self._handle_evt_speech_stopped(evt) - elif evt.type == "response.text.delta": - await self._handle_evt_text_delta(evt) - elif evt.type == "response.audio_transcript.delta": - await self._handle_evt_audio_transcript_delta(evt) - elif evt.type == "error": - if not await self._maybe_handle_evt_retrieve_conversation_item_error(evt): - if evt.error.code in ( - "response_cancel_not_active", - "conversation_already_has_active_response", - ): - logger.debug(f"{self} {evt.error.message}") - else: - await self._handle_evt_error(evt) - # errors are fatal, so exit the receive loop - return - - @traced_openai_realtime(operation="llm_setup") - async def _handle_evt_session_created(self, evt): - # session.created is received right after connecting. Send a message - # to configure the session properties. - await self._send_session_update() - - async def _handle_evt_session_updated(self, evt): - # If this is our first context frame, run the LLM - self._api_session_ready = True - # Now that we've configured the session, we can run the LLM if we need to. - if self._run_llm_when_api_session_ready: - self._run_llm_when_api_session_ready = False - await self._create_response() - - async def _handle_evt_audio_delta(self, evt): - # note: ttfb is faster by 1/2 RTT than ttfb as measured for other services, since we're getting - # this event from the server - await self.stop_ttfb_metrics() - - if self._current_audio_response and self._current_audio_response.item_id != evt.item_id: - logger.warning( - f"Received a new audio delta for an already completed audio response before receiving the BotStoppedSpeakingFrame." - ) - logger.debug("Forcing previous audio response to None") - self._current_audio_response = None - - if not self._current_audio_response: - self._current_audio_response = CurrentAudioResponse( - item_id=evt.item_id, - content_index=evt.content_index, - start_time_ms=int(time.time() * 1000), - ) - await self.push_frame(TTSStartedFrame()) - audio = base64.b64decode(evt.delta) - self._current_audio_response.total_size += len(audio) - frame = TTSAudioRawFrame( - audio=audio, - sample_rate=24000, - num_channels=1, - ) - await self.push_frame(frame) - - async def _handle_evt_audio_done(self, evt): - if self._current_audio_response: - await self.push_frame(TTSStoppedFrame()) - # Don't clear the self._current_audio_response here. We need to wait until we - # receive a BotStoppedSpeakingFrame from the output transport. - - async def _handle_evt_conversation_item_created(self, evt): - await self._call_event_handler("on_conversation_item_created", evt.item.id, evt.item) - - # This will get sent from the server every time a new "message" is added - # to the server's conversation state, whether we create it via the API - # or the server creates it from LLM output. - if self._messages_added_manually.get(evt.item.id): - del self._messages_added_manually[evt.item.id] - return - - if evt.item.role == "user": - # We need to wait for completion of both user message and response message. Then we'll - # add both to the context. User message is complete when we have a "transcript" field - # that is not None. Response message is complete when we get a "response.done" event. - self._user_and_response_message_tuple = (evt.item, {"done": False, "output": []}) - elif evt.item.role == "assistant": - self._current_assistant_response = evt.item - await self.push_frame(LLMFullResponseStartFrame()) - - async def _handle_evt_input_audio_transcription_delta(self, evt): - if self._send_transcription_frames: - await self.push_frame( - # no way to get a language code? - InterimTranscriptionFrame(evt.delta, "", time_now_iso8601(), result=evt) - ) - - @traced_stt - async def _handle_user_transcription( - self, transcript: str, is_final: bool, language: Optional[Language] = None - ): - """Handle a transcription result with tracing.""" - pass - - async def handle_evt_input_audio_transcription_completed(self, evt): - """Handle completion of input audio transcription. - - Args: - evt: The transcription completed event. - """ - await self._call_event_handler("on_conversation_item_updated", evt.item_id, None) - - if self._send_transcription_frames: - await self.push_frame( - # no way to get a language code? - TranscriptionFrame(evt.transcript, "", time_now_iso8601(), result=evt) - ) - await self._handle_user_transcription(evt.transcript, True, Language.EN) - pair = self._user_and_response_message_tuple - if pair: - user, assistant = pair - user.content[0].transcript = evt.transcript - if assistant["done"]: - self._user_and_response_message_tuple = None - self._context.add_user_content_item_as_message(user) - await self._handle_assistant_output(assistant["output"]) - else: - # User message without preceding conversation.item.created. Bug? - logger.warning(f"Transcript for unknown user message: {evt}") - - async def _handle_conversation_item_retrieved(self, evt: events.ConversationItemRetrieved): - futures = self._retrieve_conversation_item_futures.pop(evt.item.id, None) - if futures: - for future in futures: - future.set_result(evt.item) - - @traced_openai_realtime(operation="llm_response") - async def _handle_evt_response_done(self, evt): - # todo: figure out whether there's anything we need to do for "cancelled" events - # usage metrics - tokens = LLMTokenUsage( - prompt_tokens=evt.response.usage.input_tokens, - completion_tokens=evt.response.usage.output_tokens, - total_tokens=evt.response.usage.total_tokens, - ) - await self.start_llm_usage_metrics(tokens) - await self.stop_processing_metrics() - await self.push_frame(LLMFullResponseEndFrame()) - self._current_assistant_response = None - # error handling - if evt.response.status == "failed": - await self.push_error(ErrorFrame(error=evt.response.status_details["error"]["message"])) - return - # response content - for item in evt.response.output: - await self._call_event_handler("on_conversation_item_updated", item.id, item) - pair = self._user_and_response_message_tuple - if pair: - user, assistant = pair - assistant["done"] = True - assistant["output"] = evt.response.output - if user.content[0].transcript is not None: - self._user_and_response_message_tuple = None - self._context.add_user_content_item_as_message(user) - await self._handle_assistant_output(assistant["output"]) - else: - # Response message without preceding user message. Add it to the context. - await self._handle_assistant_output(evt.response.output) - - async def _handle_evt_text_delta(self, evt): - if evt.delta: - await self.push_frame(LLMTextFrame(evt.delta)) - - async def _handle_evt_audio_transcript_delta(self, evt): - if evt.delta: - await self.push_frame(LLMTextFrame(evt.delta)) - await self.push_frame(TTSTextFrame(evt.delta, aggregated_by=AggregationType.SENTENCE)) - - async def _handle_evt_speech_started(self, evt): - await self._truncate_current_audio_response() - await self.broadcast_frame(UserStartedSpeakingFrame) - await self.broadcast_interruption() - - async def _handle_evt_speech_stopped(self, evt): - await self.start_ttfb_metrics() - await self.start_processing_metrics() - await self.broadcast_frame(UserStoppedSpeakingFrame) - - async def _maybe_handle_evt_retrieve_conversation_item_error(self, evt: events.ErrorEvent): - """Maybe handle an error event related to retrieving a conversation item. - - If the given error event is an error retrieving a conversation item: - - - set an exception on the future that retrieve_conversation_item() is waiting on - - return true - Otherwise: - - return false - """ - if evt.error.code == "item_retrieve_invalid_item_id": - item_id = evt.error.event_id.split("_", 1)[1] # event_id is of the form "rci_{item_id}" - futures = self._retrieve_conversation_item_futures.pop(item_id, None) - if futures: - for future in futures: - future.set_exception(Exception(evt.error.message)) - return True - return False - - async def _handle_evt_error(self, evt): - # Errors are fatal to this connection. Send an ErrorFrame. - await self.push_error(error_msg=f"Error: {evt}") - - async def _handle_assistant_output(self, output): - # We haven't seen intermixed audio and function_call items in the same response. But let's - # try to write logic that handles that, if it does happen. - # Also, the assistant output is pushed as LLMTextFrame and TTSTextFrame to be handled by - # the assistant context aggregator. - function_calls = [item for item in output if item.type == "function_call"] - await self._handle_function_call_items(function_calls) - - async def _handle_function_call_items(self, items): - function_calls = [] - for item in items: - args = json.loads(item.arguments) - function_calls.append( - FunctionCallFromLLM( - context=self._context, - tool_call_id=item.call_id, - function_name=item.name, - arguments=args, - ) - ) - await self.run_function_calls(function_calls) - - # - # state and client events for the current conversation - # https://platform.openai.com/docs/api-reference/realtime-client-events - # - - async def reset_conversation(self): - """Reset the conversation by disconnecting and reconnecting. - - This is the safest way to start a new conversation. Note that this will - fail if called from the receive task. - """ - logger.debug("Resetting conversation") - await self._disconnect() - if self._context: - self._context.llm_needs_settings_update = True - self._context.llm_needs_initial_messages = True - await self._connect() - - @traced_openai_realtime(operation="llm_request") - async def _create_response(self): - if not self._api_session_ready: - self._run_llm_when_api_session_ready = True - return - - if self._context.llm_needs_initial_messages: - messages = self._context.get_messages_for_initializing_history() - for item in messages: - evt = events.ConversationItemCreateEvent(item=item) - self._messages_added_manually[evt.item.id] = True - await self.send_client_event(evt) - self._context.llm_needs_initial_messages = False - - if self._context.llm_needs_settings_update: - await self._send_session_update() - self._context.llm_needs_settings_update = False - - logger.debug(f"Creating response: {self._context.get_messages_for_logging()}") - - await self.push_frame(LLMFullResponseStartFrame()) - await self.start_processing_metrics() - await self.start_ttfb_metrics() - await self.send_client_event( - events.ResponseCreateEvent( - response=events.ResponseProperties(modalities=self._get_enabled_modalities()) - ) - ) - - async def _send_user_audio(self, frame): - payload = base64.b64encode(frame.audio).decode("utf-8") - await self.send_client_event(events.InputAudioBufferAppendEvent(audio=payload)) - - def create_context_aggregator( - self, - context: OpenAILLMContext, - *, - user_params: LLMUserAggregatorParams = LLMUserAggregatorParams(), - assistant_params: LLMAssistantAggregatorParams = LLMAssistantAggregatorParams(), - ) -> OpenAIContextAggregatorPair: - """Create an instance of OpenAIContextAggregatorPair from an OpenAILLMContext. - - Constructor keyword arguments for both the user and assistant aggregators can be provided. - - Args: - context: The LLM context. - user_params: User aggregator parameters. - assistant_params: Assistant aggregator parameters. - - Returns: - OpenAIContextAggregatorPair: A pair of context aggregators, one for - the user and one for the assistant, encapsulated in an - OpenAIContextAggregatorPair. - """ - context.set_llm_adapter(self.get_llm_adapter()) - - OpenAIRealtimeLLMContext.upgrade_to_realtime(context) - user = OpenAIRealtimeUserContextAggregator(context, params=user_params) - - assistant_params.expect_stripped_words = False - assistant = OpenAIRealtimeAssistantContextAggregator(context, params=assistant_params) - return OpenAIContextAggregatorPair(_user=user, _assistant=assistant) diff --git a/src/pipecat/services/riva/__init__.py b/src/pipecat/services/riva/__init__.py deleted file mode 100644 index eb438ef8a..000000000 --- a/src/pipecat/services/riva/__init__.py +++ /dev/null @@ -1,14 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -import sys - -from pipecat.services import DeprecatedModuleProxy - -from .stt import * -from .tts import * - -sys.modules[__name__] = DeprecatedModuleProxy(globals(), "riva", "riva.[stt,tts]") diff --git a/src/pipecat/services/riva/stt.py b/src/pipecat/services/riva/stt.py deleted file mode 100644 index 45faf08a0..000000000 --- a/src/pipecat/services/riva/stt.py +++ /dev/null @@ -1,35 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""NVIDIA Riva Speech-to-Text service implementations for real-time and batch transcription. - -.. deprecated:: 0.0.96 - This module is deprecated. Please NvidiaSTTService from - pipecat.services.nvidia.stt instead. -""" - -import warnings - -from pipecat.services.nvidia.stt import ( - NvidiaSegmentedSTTService, - NvidiaSTTService, - language_to_nvidia_riva_language, -) - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "RivaSTTService and ParakeetSTTService " - "from pipecat.services.riva.stt is deprecated. " - "Please use NvidiaSTTService from pipecat.services.nvidia.stt instead.", - DeprecationWarning, - stacklevel=2, - ) - -RivaSTTService = NvidiaSTTService -language_to_riva_language = language_to_nvidia_riva_language -RivaSegmentedSTTService = NvidiaSegmentedSTTService -ParakeetSTTService = NvidiaSTTService diff --git a/src/pipecat/services/riva/tts.py b/src/pipecat/services/riva/tts.py deleted file mode 100644 index 7b0af3d39..000000000 --- a/src/pipecat/services/riva/tts.py +++ /dev/null @@ -1,33 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""NVIDIA Riva text-to-speech service implementation. - -This module provides integration with NVIDIA Riva's TTS services through -gRPC API for high-quality speech synthesis. - -.. deprecated:: 0.0.96 - This module is deprecated. Please NvidiaTTSService from - pipecat.services.nvidia.tts instead. -""" - -import warnings - -from pipecat.services.nvidia.tts import NVIDIA_TTS_TIMEOUT_SECS, NvidiaTTSService - -with warnings.catch_warnings(): - warnings.simplefilter("always") - warnings.warn( - "FastPitchTTSService and RivaTTSService " - "from pipecat.services.nim.llm are deprecated. " - "Please use NvidiaLLMService from pipecat.services.nvidia.tts instead.", - DeprecationWarning, - stacklevel=2, - ) - -RivaTTSService = NvidiaTTSService -FastPitchTTSService = NvidiaTTSService -RIVA_TTS_TIMEOUT_SECS = NVIDIA_TTS_TIMEOUT_SECS diff --git a/src/pipecat/utils/tracing/service_attributes.py b/src/pipecat/utils/tracing/service_attributes.py index e5cf4a83f..5be781406 100644 --- a/src/pipecat/utils/tracing/service_attributes.py +++ b/src/pipecat/utils/tracing/service_attributes.py @@ -47,7 +47,6 @@ def _get_provider_name_from_service_name(service_name: str) -> str: "AzureLLMService": "az.ai.openai", # Google "GoogleLLMService": "gcp.gemini", - "GoogleLLMOpenAIBetaService": "gcp.gemini", "GoogleVertexLLMService": "gcp.vertex_ai", # Others "GrokLLMService": "xai", diff --git a/tests/test_google_llm_openai.py b/tests/test_google_llm_openai.py deleted file mode 100644 index 5e6cee6f8..000000000 --- a/tests/test_google_llm_openai.py +++ /dev/null @@ -1,81 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -"""Unit tests for Google LLM OpenAI Beta service.""" - -import asyncio -import warnings -from unittest.mock import AsyncMock, patch - -import pytest - -from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext - -try: - from pipecat.services.google.openai.llm import GoogleLLMOpenAIBetaService - - google_available = True -except Exception: - google_available = False - - -@pytest.mark.asyncio -@pytest.mark.skipif(not google_available, reason="Google dependencies not installed") -async def test_google_llm_openai_stream_closed_on_cancellation(): - """Test that the stream is closed when CancelledError occurs during iteration. - - This prevents socket leaks when the pipeline is interrupted (e.g., user interruption). - See issue #3639. - """ - with patch.object(GoogleLLMOpenAIBetaService, "create_client"): - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - service = GoogleLLMOpenAIBetaService(api_key="test-key", model="test-model") - service._client = AsyncMock() - - stream_closed = False - - class MockAsyncStream: - """Mock AsyncStream that tracks close() calls and raises CancelledError.""" - - def __init__(self): - self.iteration_count = 0 - - async def __aenter__(self): - return self - - async def __aexit__(self, exc_type, exc_val, exc_tb): - nonlocal stream_closed - stream_closed = True - return False - - def __aiter__(self): - return self - - async def __anext__(self): - self.iteration_count += 1 - if self.iteration_count > 1: - raise asyncio.CancelledError() - mock_chunk = AsyncMock() - mock_chunk.usage = None - mock_chunk.choices = [] - return mock_chunk - - mock_stream = MockAsyncStream() - - service._stream_chat_completions_specific_context = AsyncMock(return_value=mock_stream) - service.start_ttfb_metrics = AsyncMock() - service.stop_ttfb_metrics = AsyncMock() - service.start_llm_usage_metrics = AsyncMock() - - context = OpenAILLMContext( - messages=[{"role": "user", "content": "Hello"}], - ) - - with pytest.raises(asyncio.CancelledError): - await service._process_context(context) - - assert stream_closed, "Stream should be closed even when CancelledError occurs" diff --git a/tests/test_settings.py b/tests/test_settings.py index 3419f940e..1607fdc3a 100644 --- a/tests/test_settings.py +++ b/tests/test_settings.py @@ -8,8 +8,8 @@ from unittest.mock import patch +from pipecat.services.deepgram.sagemaker.stt import DeepgramSageMakerSTTSettings from pipecat.services.deepgram.stt import DeepgramSTTService, DeepgramSTTSettings -from pipecat.services.deepgram.stt_sagemaker import DeepgramSageMakerSTTSettings from pipecat.services.openai.realtime import events from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMSettings from pipecat.services.settings import (