Save race bot

examples/foundational/race_bot.py

@@ -0,0 +1,87 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+import time
+
+import aiohttp
+from loguru import logger
+from runner import configure
+
+from pipecat.frames.frames import (
+    TranscriptionFrame,
+    UserStartedSpeakingFrame,
+    UserStoppedSpeakingFrame,
+)
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True)
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = OpenAILLMService(api_key=os.environ["OPENAI_API_KEY"], model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(
+            Pipeline(
+                [
+                    context_aggregator.user(),
+                    llm,
+                    tts,
+                    transport.output(),
+                    context_aggregator.assistant(),
+                ]
+            )
+        )
+
+        # Register an event handler so we can play the audio when the
+        # participant joins.
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            frames = [
+                UserStartedSpeakingFrame(),
+                TranscriptionFrame("Tell a joke about dogs.", "user_id", time.time()),
+                UserStoppedSpeakingFrame(),
+            ]
+
+            await task.queue_frames(frames)
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

src/pipecat/processors/frame_processor.py

@@ -6,11 +6,10 @@
 
 import asyncio
 import inspect
+
 from enum import Enum
 from typing import Awaitable, Callable, Optional
 
-from loguru import logger
-
 from pipecat.clocks.base_clock import BaseClock
 from pipecat.frames.frames import (
     EndFrame,
@@ -25,6 +24,8 @@ from pipecat.metrics.metrics import LLMTokenUsage, MetricsData
 from pipecat.processors.metrics.frame_processor_metrics import FrameProcessorMetrics
 from pipecat.utils.utils import obj_count, obj_id
 
+from loguru import logger
+
 
 class FrameDirection(Enum):
     DOWNSTREAM = 1
@@ -219,16 +220,11 @@ class FrameProcessor:
     #
 
     async def _start_interruption(self):
-        try:
-            # Cancel the push frame task. This will stop pushing frames downstream.
-            await self.__cancel_push_task()
+        # Cancel the push frame task. This will stop pushing frames downstream.
+        await self.__cancel_push_task()
 
-            # Cancel the input task. This will stop processing queued frames.
-            await self.__cancel_input_task()
-        except Exception as e:
-            logger.exception(f"Uncaught exception in {self}: {e}")
-            await self.push_error(ErrorFrame(str(e)))
-            raise
+        # Cancel the input task. This will stop processing queued frames.
+        await self.__cancel_input_task()
 
         # Create a new input queue and task.
         self.__create_input_task()
@@ -285,11 +281,7 @@ class FrameProcessor:
 
                 self.__input_queue.task_done()
             except asyncio.CancelledError:
-                logger.trace(f"Cancelled input task in {self}")
                 break
-            except Exception as e:
-                logger.exception(f"Uncaught exception in {self}: {e}")
-                await self.push_error(ErrorFrame(str(e)))
 
     def __create_push_task(self):
         self.__push_queue = asyncio.Queue()
@@ -308,11 +300,7 @@ class FrameProcessor:
                 running = not isinstance(frame, EndFrame)
                 self.__push_queue.task_done()
             except asyncio.CancelledError:
-                logger.trace(f"Cancelled push task in {self}")
                 break
-            except Exception as e:
-                logger.exception(f"Uncaught exception in {self}: {e}")
-                await self.push_error(ErrorFrame(str(e)))
 
     async def _call_event_handler(self, event_name: str, *args, **kwargs):
         try: