Storytelling chatbot updates (#1066)

* initial changes for gemini storybot

* storybot updates for gemini

* more storybot updates

* interim interruptible commit

* cleanup

* cleanup

* cleanup

* cleanup

examples/storytelling-chatbot/src/bot.py

@@ -13,16 +13,23 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 from processors import StoryImageProcessor, StoryProcessor
-from prompts import CUE_USER_TURN, LLM_BASE_PROMPT, LLM_INTRO_PROMPT
+from prompts import CUE_USER_TURN, LLM_BASE_PROMPT
 from utils.helpers import load_images, load_sounds
 
-from pipecat.frames.frames import EndFrame, LLMMessagesFrame, StopTaskFrame
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame, StopTaskFrame
 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.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import (
+    OpenAILLMContext,
+    OpenAILLMContextFrame,
+)
+from pipecat.processors.logger import FrameLogger
+from pipecat.services.cartesia import CartesiaHttpTTSService, CartesiaTTSService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.fal import FalImageGenService
+from pipecat.services.google import GoogleLLMService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import (
     DailyParams,
@@ -53,6 +60,7 @@ async def main(room_url, token=None):
                 camera_out_width=768,
                 camera_out_height=768,
                 transcription_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
                 vad_enabled=True,
             ),
         )
@@ -61,11 +69,10 @@ async def main(room_url, token=None):
 
         # -------------- Services --------------- #
 
-        llm_service = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm_service = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
 
         tts_service = ElevenLabsTTSService(
-            api_key=os.getenv("ELEVENLABS_API_KEY"),
-            voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
+            api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id=os.getenv("ELEVENLABS_VOICE_ID")
         )
 
         fal_service_params = FalImageGenService.InputParams(
@@ -74,7 +81,7 @@ async def main(room_url, token=None):
 
         fal_service = FalImageGenService(
             aiohttp_session=session,
-            model="fal-ai/fast-lightning-sdxl",
+            model="fal-ai/stable-diffusion-v35-medium",
             params=fal_service_params,
             key=os.getenv("FAL_KEY"),
         )
@@ -97,35 +104,8 @@ async def main(room_url, token=None):
 
         runner = PipelineRunner()
 
-        # The intro pipeline is used to start
-        # the story (as per LLM_INTRO_PROMPT)
-        intro_pipeline = Pipeline([llm_service, tts_service, transport.output()])
-
-        intro_task = PipelineTask(intro_pipeline)
-
         logger.debug("Waiting for participant...")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            logger.debug("Participant joined, storytime commence!")
-            await transport.capture_participant_transcription(participant["id"])
-            await intro_task.queue_frames(
-                [
-                    images["book1"],
-                    LLMMessagesFrame([LLM_INTRO_PROMPT]),
-                    DailyTransportMessageFrame(CUE_USER_TURN),
-                    sounds["listening"],
-                    images["book2"],
-                    StopTaskFrame(),
-                ]
-            )
-
-        # We run the intro pipeline. This will start the transport. The intro
-        # task will exit after StopTaskFrame is processed.
-        await runner.run(intro_task)
-
-        # The main story pipeline is used to continue the story based on user
-        # input.
         main_pipeline = Pipeline(
             [
                 transport.input(),
@@ -139,11 +119,32 @@ async def main(room_url, token=None):
             ]
         )
 
-        main_task = PipelineTask(main_pipeline)
+        main_task = PipelineTask(
+            main_pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            logger.debug("Participant joined, storytime commence!")
+            await transport.capture_participant_transcription(participant["id"])
+            await main_task.queue_frames(
+                [
+                    images["book1"],
+                    context_aggregator.user().get_context_frame(),
+                    DailyTransportMessageFrame(CUE_USER_TURN),
+                    # sounds["listening"],
+                    images["book2"],
+                ]
+            )
 
         @transport.event_handler("on_participant_left")
         async def on_participant_left(transport, participant, reason):
-            await intro_task.queue_frame(EndFrame())
             await main_task.queue_frame(EndFrame())
 
         @transport.event_handler("on_call_state_updated")