Refactor QueueFrame

src/samples/foundational/01-say-one-thing.py

@@ -1,10 +1,7 @@
 import argparse
 import asyncio
-from typing import AsyncGenerator
 
-from dailyai.queue_frame import QueueFrame, FrameType
 from dailyai.services.daily_transport_service import DailyTransportService
-from dailyai.services.azure_ai_services import AzureTTSService
 from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
 
 async def main(room_url):

src/samples/foundational/02-llm-say-one-thing.py

@@ -1,8 +1,7 @@
 import argparse
 import asyncio
-from typing import AsyncGenerator
 
-from dailyai.queue_frame import QueueFrame, FrameType
+from dailyai.queue_frame import LLMMessagesQueueFrame
 from dailyai.services.daily_transport_service import DailyTransportService
 from dailyai.services.azure_ai_services import AzureLLMService
 from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
@@ -27,7 +26,7 @@ async def main(room_url):
     tts_task = asyncio.create_task(
         tts.run_to_queue(
             transport.send_queue,
-            llm.run([QueueFrame(FrameType.LLM_MESSAGE, messages)])
+            llm.run([LLMMessagesQueueFrame(messages)]),
         )
     )
 

src/samples/foundational/03-still-frame.py

@@ -1,7 +1,7 @@
 import argparse
 import asyncio
 
-from dailyai.queue_frame import QueueFrame, FrameType
+from dailyai.queue_frame import TextQueueFrame
 from dailyai.services.daily_transport_service import DailyTransportService
 from dailyai.services.open_ai_services import OpenAIImageGenService
 
@@ -23,7 +23,7 @@ async def main(room_url):
 
     imagegen = OpenAIImageGenService(image_size="1024x1024")
     image_task = asyncio.create_task(
-        imagegen.run_to_queue(transport.send_queue, [QueueFrame(FrameType.TEXT, "a cat in the style of picasso")])
+        imagegen.run_to_queue(transport.send_queue, [TextQueueFrame("a cat in the style of picasso")])
     )
 
     @transport.event_handler("on_participant_joined")

src/samples/foundational/04-utterance-and-speech.py

@@ -4,7 +4,7 @@ import re
 
 from dailyai.services.daily_transport_service import DailyTransportService
 from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
-from dailyai.queue_frame import QueueFrame, FrameType
+from dailyai.queue_frame import EndStreamQueueFrame, LLMMessagesQueueFrame
 from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
 
 async def main(room_url:str):
@@ -35,7 +35,7 @@ async def main(room_url:str):
     llm_response_task = asyncio.create_task(
         elevenlabs_tts.run_to_queue(
             buffer_queue,
-            llm.run([QueueFrame(FrameType.LLM_MESSAGE, messages)]),
+            llm.run([LLMMessagesQueueFrame(messages)]),
             True,
         )
     )
@@ -52,7 +52,7 @@ async def main(room_url:str):
                 frame = await buffer_queue.get()
                 await transport.send_queue.put(frame)
                 buffer_queue.task_done()
-                if frame.frame_type == FrameType.END_STREAM:
+                if isinstance(frame, EndStreamQueueFrame):
                     break
 
         await asyncio.gather(llm_response_task, buffer_to_send_queue())

src/samples/foundational/05-sync-speech-and-text.py

@@ -1,13 +1,9 @@
 import argparse
 import asyncio
 
-from asyncio.queues import Queue
-import re
-
-from dailyai.queue_frame import QueueFrame, FrameType
+from dailyai.queue_frame import AudioQueueFrame, ImageQueueFrame
 from dailyai.services.azure_ai_services import AzureLLMService
 from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.services.open_ai_services import OpenAIImageGenService
 from dailyai.services.daily_transport_service import DailyTransportService
 from dailyai.services.fal_ai_services import FalImageGenService
 
@@ -48,14 +44,20 @@ async def main(room_url):
         ]
 
         image_description = await llm.run_llm(messages)
+        if not image_description:
+            return
+
         to_speak = f"{month}: {image_description}"
+        audio_task = asyncio.create_task(get_all_audio(to_speak))
+        image_task = asyncio.create_task(dalle.run_image_gen(image_description))
         (audio, image_data) = await asyncio.gather(
-            get_all_audio(to_speak), dalle.run_image_gen(image_description)
+            audio_task, image_task
         )
 
         return {
             "month": month,
             "text": image_description,
+            "image_url": image_data[0],
             "image": image_data[1],
             "audio": audio,
         }
@@ -84,8 +86,8 @@ async def main(room_url):
             data = await month_data_task
             await transport.send_queue.put(
                 [
-                    QueueFrame(FrameType.IMAGE, data["image"]),
-                    QueueFrame(FrameType.AUDIO, data["audio"]),
+                    ImageQueueFrame(data["image_url"], data["image"]),
+                    AudioQueueFrame(data["audio"]),
                 ]
             )