Merge pull request #642 from pipecat-ai/aleix/input-queues-block-frames

introduce frame processor input queues block frames

examples/foundational/01-say-one-thing.py

@@ -9,11 +9,11 @@ import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import EndFrame, TextFrame
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.task import PipelineTask
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.services.cartesia import CartesiaHttpTTSService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
@@ -36,7 +36,7 @@ async def main():
             room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True)
         )
 
-        tts = CartesiaHttpTTSService(
+        tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
@@ -50,12 +50,9 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             participant_name = participant.get("info", {}).get("userName", "")
-            await task.queue_frame(TextFrame(f"Hello there, {participant_name}!"))
-
-        # Register an event handler to exit the application when the user leaves.
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.queue_frame(EndFrame())
+            await task.queue_frames(
+                [TTSSpeakFrame(f"Hello there, {participant_name}!"), EndFrame()]
+            )
 
         await runner.run(task)
 

examples/foundational/01a-local-audio.py

@@ -9,7 +9,7 @@ import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import TextFrame
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
@@ -28,25 +28,24 @@ logger.add(sys.stderr, level="DEBUG")
 
 
 async def main():
-    async with aiohttp.ClientSession() as session:
-        transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
+    transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+    )
 
-        pipeline = Pipeline([tts, transport.output()])
+    pipeline = Pipeline([tts, transport.output()])
 
-        task = PipelineTask(pipeline)
+    task = PipelineTask(pipeline)
 
-        async def say_something():
-            await asyncio.sleep(1)
-            await task.queue_frame(TextFrame("Hello there!"))
+    async def say_something():
+        await asyncio.sleep(1)
+        await task.queue_frames([TTSSpeakFrame("Hello there, how is it going!"), EndFrame()])
 
-        runner = PipelineRunner()
+    runner = PipelineRunner()
 
-        await asyncio.gather(runner.run(task), say_something())
+    await asyncio.gather(runner.run(task), say_something())
 
 
 if __name__ == "__main__":

examples/foundational/02-llm-say-one-thing.py

@@ -13,7 +13,7 @@ from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.services.cartesia import CartesiaHttpTTSService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -37,7 +37,7 @@ async def main():
             room_url, None, "Say One Thing From an LLM", DailyParams(audio_out_enabled=True)
         )
 
-        tts = CartesiaHttpTTSService(
+        tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
@@ -57,11 +57,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            await task.queue_frame(LLMMessagesFrame(messages))
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.queue_frame(EndFrame())
+            await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
 
         await runner.run(task)
 

examples/patient-intake/bot.py

@@ -182,7 +182,7 @@ class IntakeProcessor:
             }
         )
         print(f"!!! about to await llm process frame in start prescrpitions")
-        await llm.process_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
+        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
         print(f"!!! past await process frame in start prescriptions")
 
     async def start_allergies(self, function_name, llm, context):
@@ -222,7 +222,7 @@ class IntakeProcessor:
                 "content": "Now ask the user if they have any medical conditions the doctor should know about. Once they've answered the question, call the list_conditions function.",
             }
         )
-        await llm.process_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
+        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
 
     async def start_conditions(self, function_name, llm, context):
         print("!!! doing start conditions")
@@ -261,7 +261,7 @@ class IntakeProcessor:
                 "content": "Finally, ask the user the reason for their doctor visit today. Once they answer, call the list_visit_reasons function.",
             }
         )
-        await llm.process_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
+        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
 
     async def start_visit_reasons(self, function_name, llm, context):
         print("!!! doing start visit reasons")
@@ -270,7 +270,7 @@ class IntakeProcessor:
         context.add_message(
             {"role": "system", "content": "Now, thank the user and end the conversation."}
         )
-        await llm.process_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
+        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
 
     async def save_data(self, function_name, tool_call_id, args, llm, context, result_callback):
         logger.info(f"!!! Saving data: {args}")