diff --git a/examples/foundational/07e-interruptible-anthropic.py b/examples/foundational/07e-interruptible-anthropic.py deleted file mode 100644 index fbb497d9b..000000000 --- a/examples/foundational/07e-interruptible-anthropic.py +++ /dev/null @@ -1,125 +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.audio.vad.silero import SileroVADAnalyzer -from pipecat.frames.frames import LLMRunFrame -from pipecat.pipeline.pipeline import Pipeline -from pipecat.pipeline.runner import PipelineRunner -from pipecat.pipeline.task import PipelineParams, PipelineTask -from pipecat.processors.aggregators.llm_context import LLMContext -from pipecat.processors.aggregators.llm_response_universal import ( - LLMContextAggregatorPair, - LLMUserAggregatorParams, -) -from pipecat.runner.types import RunnerArguments -from pipecat.runner.utils import create_transport -from pipecat.services.anthropic.llm import AnthropicLLMService -from pipecat.services.cartesia.tts import CartesiaTTSService -from pipecat.services.deepgram.stt import DeepgramSTTService -from pipecat.transports.base_transport import BaseTransport, TransportParams -from pipecat.transports.daily.transport import DailyParams -from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams - -load_dotenv(override=True) - -# We use lambdas to defer transport parameter creation until the transport -# type is selected at runtime. -transport_params = { - "daily": lambda: DailyParams( - audio_in_enabled=True, - audio_out_enabled=True, - ), - "twilio": lambda: FastAPIWebsocketParams( - audio_in_enabled=True, - audio_out_enabled=True, - ), - "webrtc": lambda: TransportParams( - audio_in_enabled=True, - audio_out_enabled=True, - ), -} - - -async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): - logger.info(f"Starting bot") - - stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) - - tts = CartesiaTTSService( - api_key=os.getenv("CARTESIA_API_KEY"), - settings=CartesiaTTSService.Settings( - voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady - ), - ) - - llm = AnthropicLLMService( - api_key=os.getenv("ANTHROPIC_API_KEY"), - settings=AnthropicLLMService.Settings( - system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.", - ), - ) - - context = LLMContext() - user_aggregator, assistant_aggregator = LLMContextAggregatorPair( - context, - user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()), - ) - - pipeline = Pipeline( - [ - transport.input(), # Transport user input - stt, - user_aggregator, # User responses - llm, # LLM - tts, # TTS - transport.output(), # Transport bot output - assistant_aggregator, # Assistant spoken responses - ] - ) - - task = PipelineTask( - pipeline, - params=PipelineParams( - enable_metrics=True, - enable_usage_metrics=True, - ), - idle_timeout_secs=runner_args.pipeline_idle_timeout_secs, - ) - - @transport.event_handler("on_client_connected") - async def on_client_connected(transport, client): - logger.info(f"Client connected") - # Kick off the conversation. - context.add_message( - {"role": "developer", "content": "Please introduce yourself to the user."} - ) - await task.queue_frames([LLMRunFrame()]) - - @transport.event_handler("on_client_disconnected") - async def on_client_disconnected(transport, client): - logger.info(f"Client disconnected") - await task.cancel() - - runner = PipelineRunner(handle_sigint=runner_args.handle_sigint) - - await runner.run(task) - - -async def bot(runner_args: RunnerArguments): - """Main bot entry point compatible with Pipecat Cloud.""" - transport = await create_transport(runner_args, transport_params) - await run_bot(transport, runner_args) - - -if __name__ == "__main__": - from pipecat.runner.run import main - - main() diff --git a/examples/foundational/07e-interruptible-xai.py b/examples/foundational/07e-interruptible-xai.py index 762c27e7c..b12c469ef 100644 --- a/examples/foundational/07e-interruptible-xai.py +++ b/examples/foundational/07e-interruptible-xai.py @@ -93,7 +93,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): params=PipelineParams( enable_metrics=True, enable_usage_metrics=True, - audio_out_sample_rate=8000, ), idle_timeout_secs=runner_args.pipeline_idle_timeout_secs, ) @@ -103,7 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): logger.info(f"Client connected") # Kick off the conversation. context.add_message( - {"role": "user", "content": "Please introduce yourself to the user."} + {"role": "developer", "content": "Please introduce yourself to the user."} ) await task.queue_frames([LLMRunFrame()]) diff --git a/examples/foundational/14g-function-calling-grok.py b/examples/foundational/14g-function-calling-grok.py index 34ec82b5f..148e8f127 100644 --- a/examples/foundational/14g-function-calling-grok.py +++ b/examples/foundational/14g-function-calling-grok.py @@ -131,7 +131,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): logger.info(f"Client connected") # Kick off the conversation. context.add_message( - {"role": "user", "content": "Please introduce yourself to the user."} + {"role": "developer", "content": "Please introduce yourself to the user."} ) await task.queue_frames([LLMRunFrame()]) diff --git a/scripts/evals/run-release-evals.py b/scripts/evals/run-release-evals.py index 4d113844e..829f03538 100644 --- a/scripts/evals/run-release-evals.py +++ b/scripts/evals/run-release-evals.py @@ -108,7 +108,7 @@ TESTS_07 = [ ("07c-interruptible-deepgram-http.py", EVAL_SIMPLE_MATH), ("07d-interruptible-elevenlabs.py", EVAL_SIMPLE_MATH), ("07d-interruptible-elevenlabs-http.py", EVAL_SIMPLE_MATH), - ("07e-interruptible-anthropic.py", EVAL_SIMPLE_MATH), + ("07e-interruptible-xai.py", EVAL_SIMPLE_MATH), ("07f-interruptible-azure.py", EVAL_SIMPLE_MATH), ("07f-interruptible-azure-http.py", EVAL_SIMPLE_MATH), ("07g-interruptible-openai.py", EVAL_SIMPLE_MATH), diff --git a/src/pipecat/services/xai/__init__.py b/src/pipecat/services/xai/__init__.py index 5433f9431..e69de29bb 100644 --- a/src/pipecat/services/xai/__init__.py +++ b/src/pipecat/services/xai/__init__.py @@ -1,13 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -import sys - -from pipecat.services import DeprecatedModuleProxy - -from .tts import * - -sys.modules[__name__] = DeprecatedModuleProxy(globals(), "xai", "xai.tts") diff --git a/uv.lock b/uv.lock index 1c532819a..2693d32e5 100644 --- a/uv.lock +++ b/uv.lock @@ -4966,11 +4966,7 @@ requires-dist = [ { name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1,<1" }, { name = "websockets", marker = "extra == 'websockets-base'", specifier = ">=13.1,<16.0" }, ] -<<<<<<< HEAD -provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "krisp", "langchain", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "novita", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "smallest", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper"] -======= -provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "krisp", "langchain", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "novita", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper", "xai"] ->>>>>>> 43f25faca (Add xAI HTTP TTS service) +provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "krisp", "langchain", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "novita", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "smallest", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper", "xai"] [package.metadata.requires-dev] dev = [