Merge branch 'main' into groundingMetadata

examples/foundational/07n-interruptible-google.py

@@ -61,7 +61,12 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
-    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # turn on thinking if you want it
+        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
+    )
 
     messages = [
         {

examples/foundational/07s-interruptible-google-audio-in.py

@@ -214,7 +214,12 @@ transport_params = {
 async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
     logger.info(f"Starting bot")
 
-    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # turn on thinking if you want it
+        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
+    )
 
     tts = GoogleTTSService(
         voice_id="en-US-Chirp3-HD-Charon",

examples/foundational/39c-mcp-run-http.py

@@ -0,0 +1,133 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+from mcp.client.session_group import StreamableHttpParameters
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.mcp_service import MCPClient
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+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_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
+
+    try:
+        # Github MCP docs: https://github.com/github/github-mcp-server
+        # Enable Github Copilot on your GitHub account. Free tier is ok. (https://github.com/settings/copilot)
+        # Generate a personal access token. It must be a Fine-grained token, classic tokens are not supported. (https://github.com/settings/personal-access-tokens)
+        # Set permissions you want to use (eg. "all repositories", "profile: read/write", etc)
+        mcp = MCPClient(
+            server_params=StreamableHttpParameters(
+                url="https://api.githubcopilot.com/mcp/",
+                headers={"Authorization": f"Bearer {os.getenv('GITHUB_PERSONAL_ACCESS_TOKEN')}"},
+            )
+        )
+    except Exception as e:
+        logger.error(f"error setting up mcp")
+        logger.exception("error trace:")
+
+    tools = await mcp.register_tools(llm)
+
+    system = f"""
+    You are a helpful LLM in a WebRTC call.
+    Your goal is to answer questions about the user's GitHub repositories and account.
+    You have access to a number of tools provided by Github. Use any and all tools to help users.
+    Your output will be converted to audio so don't include special characters in your answers.
+    Don't overexplain what you are doing.
+    Just respond with short sentences when you are carrying out tool calls.
+    """
+
+    messages = [{"role": "system", "content": system}]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User spoken responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses and tool context
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @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=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

examples/foundational/42-interruption-config.py

@@ -10,8 +10,8 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+from pipecat.audio.interruptions.min_words_interruption_strategy import MinWordsInterruptionStrategy
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import MinWordsInterruptionStrategy
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask

examples/freeze-test/freeze_test_bot.py

@@ -7,9 +7,11 @@
 import argparse
 import asyncio
 import os
+import random
 from contextlib import asynccontextmanager
 from typing import Any, Dict
 
+import sentry_sdk
 import uvicorn
 from dotenv import load_dotenv
 from fastapi import FastAPI, Request, WebSocket
@@ -44,6 +46,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
 )
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIProcessor
+from pipecat.processors.metrics.sentry import SentryMetrics
 from pipecat.serializers.protobuf import ProtobufFrameSerializer
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -125,6 +128,7 @@ class SimulateFreezeInput(FrameProcessor):
             self._send_frames_task = None
 
     async def _send_user_text(self, text: str):
+        self.reset_watchdog()
         # Emulation as if the user has spoken and the stt transcribed
         await self.push_frame(UserStartedSpeakingFrame())
         await self.push_frame(StartInterruptionFrame())
@@ -149,14 +153,13 @@ class SimulateFreezeInput(FrameProcessor):
                 logger.debug("SimulateFreezeInput _send_frames")
                 await self._send_user_text("Tell me a brief history of Brazil!")
                 await asyncio.sleep(3)
-                await self._send_user_text("")
-                break
-                # i += 1
-                # if i >= 5:
-                #    break
+                await self._send_user_text("and who has discovered it")
+                i += 1
+                if i >= 20:
+                    break
                 # sleeping 1s before interrupting
-                # wait_time = random.uniform(1, 10)
-                # await asyncio.sleep(wait_time)
+                wait_time = random.uniform(1, 10)
+                await asyncio.sleep(wait_time)
         except Exception as e:
             logger.error(f"{self} exception receiving data: {e.__class__.__name__} ({e})")
 
@@ -176,6 +179,11 @@ async def run_example(websocket_client):
         ),
     )
 
+    sentry_sdk.init(
+        dsn=os.getenv("SENTRY_DSN"),
+        traces_sample_rate=1.0,
+    )
+
     freeze = SimulateFreezeInput()
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
@@ -183,9 +191,13 @@ async def run_example(websocket_client):
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        metrics=SentryMetrics(),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        metrics=SentryMetrics(),
+    )
 
     rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
 
@@ -247,6 +259,7 @@ async def run_example(websocket_client):
                 },
             ),
         ],
+        enable_watchdog_timers=True,
     )
 
     @transport.event_handler("on_client_connected")