Merge pull request #24 from daily-co/another-formatting-pass

Another autopep8 formatting pass

src/dailyai/queue_aggregators.py

@@ -61,13 +61,17 @@ async def process_frame(self, frame: QueueFrame) -> AsyncGenerator[QueueFrame, N
 
         # TODO: split up transcription by participant
         if self.complete_sentences:
-            self.sentence += frame.text # type: ignore -- the linter thinks this isn't a TextQueueFrame, even though we check it above
+            # type: ignore -- the linter thinks this isn't a TextQueueFrame, even
+            # though we check it above
+            self.sentence += frame.text
             if self.sentence.endswith((".", "?", "!")):
                 self.messages.append({"role": self.role, "content": self.sentence})
                 self.sentence = ""
                 yield LLMMessagesQueueFrame(self.messages)
         else:
-            self.messages.append({"role": self.role, "content": frame.text})  # type: ignore -- the linter thinks this isn't a TextQueueFrame, even though we check it above
+            # type: ignore -- the linter thinks this isn't a TextQueueFrame, even
+            # though we check it above
+            self.messages.append({"role": self.role, "content": frame.text})
             yield LLMMessagesQueueFrame(self.messages)
 
     async def finalize(self) -> AsyncGenerator[QueueFrame, None]:
@@ -79,9 +83,9 @@ async def finalize(self) -> AsyncGenerator[QueueFrame, None]:
 
 class LLMUserContextAggregator(LLMContextAggregator):
     def __init__(self,
-            messages: list[dict],
-            bot_participant_id=None,
-            complete_sentences=True):
+                 messages: list[dict],
+                 bot_participant_id=None,
+                 complete_sentences=True):
         super().__init__(messages, "user", bot_participant_id, complete_sentences, pass_through=False)
 
 

src/dailyai/queue_frame.py

@@ -18,9 +18,11 @@ class StartStreamQueueFrame(ControlQueueFrame):
 class EndStreamQueueFrame(ControlQueueFrame):
     pass
 
+
 class LLMResponseEndQueueFrame(QueueFrame):
     pass
 
+
 @dataclass()
 class AudioQueueFrame(QueueFrame):
     data: bytes

src/dailyai/services/base_transport_service.py

@@ -16,6 +16,7 @@
     StartStreamQueueFrame,
 )
 
+
 class BaseTransportService():
 
     def __init__(

src/dailyai/services/daily_transport_service.py

@@ -45,7 +45,7 @@ def __init__(
         start_transcription: bool = False,
         **kwargs,
     ):
-        super().__init__(**kwargs) # This will call BaseTransportService.__init__ method, not EventHandler
+        super().__init__(**kwargs)  # This will call BaseTransportService.__init__ method, not EventHandler
 
         self._room_url: str = room_url
         self._bot_name: str = bot_name

src/dailyai/services/fal_ai_services.py

@@ -13,7 +13,13 @@
 
 
 class FalImageGenService(ImageGenService):
-    def __init__(self, *, image_size, aiohttp_session: aiohttp.ClientSession, key_id=None, key_secret=None):
+    def __init__(
+            self,
+            *,
+            image_size,
+            aiohttp_session: aiohttp.ClientSession,
+            key_id=None,
+            key_secret=None):
         super().__init__(image_size)
         self._aiohttp_session = aiohttp_session
         if key_id:

src/dailyai/services/local_transport_service.py

@@ -22,11 +22,15 @@ def __init__(self, **kwargs):
 
     async def _write_frame_to_tkinter(self, frame: bytes):
         data = f"P6 {self._camera_width} {self._camera_height} 255 ".encode() + frame
-        photo = tk.PhotoImage(width=self._camera_width, height=self._camera_height, data=data, format="PPM")
+        photo = tk.PhotoImage(
+            width=self._camera_width,
+            height=self._camera_height,
+            data=data,
+            format="PPM")
         self._image_label.config(image=photo)
 
         # This holds a reference to the photo, preventing it from being garbage collected.
-        self._image_label.image = photo # type: ignore
+        self._image_label.image = photo  # type: ignore
 
     def write_frame_to_camera(self, frame: bytes):
         if self._camera_enabled and self._loop:

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

@@ -7,6 +7,7 @@
 
 from examples.foundational.support.runner import configure
 
+
 async def main(room_url):
     async with aiohttp.ClientSession() as session:
         # create a transport service object using environment variables for
@@ -25,7 +26,10 @@ async def main(room_url):
             meeting_duration_minutes,
             mic_enabled=True
         )
-        tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
+        tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
 
         # Register an event handler so we can play the audio when the participant joins.
         @transport.event_handler("on_participant_joined")

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

@@ -11,6 +11,7 @@
 from dailyai.services.open_ai_services import OpenAILLMService
 from examples.foundational.support.runner import configure
 
+
 async def main(room_url):
     async with aiohttp.ClientSession() as session:
         meeting_duration_minutes = 1
@@ -22,12 +23,18 @@ async def main(room_url):
             mic_enabled=True
         )
 
-        tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
+        tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
         # tts = AzureTTSService(api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
         # tts = DeepgramTTSService(aiohttp_session=session, api_key=os.getenv("DEEPGRAM_API_KEY"), voice=os.getenv("DEEPGRAM_VOICE"))
 
-        llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-        #llm = OpenAILLMService(api_key=os.getenv("OPENAI_CHATGPT_API_KEY"))
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"))
+        # llm = OpenAILLMService(api_key=os.getenv("OPENAI_CHATGPT_API_KEY"))
         messages = [{
             "role": "system",
             "content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world."

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

@@ -28,7 +28,11 @@ async def main(room_url):
             camera_height=1024
         )
 
-        imagegen = FalImageGenService(image_size="1024x1024", aiohttp_session=session, key_id=os.getenv("FAL_KEY_ID"), key_secret=os.getenv("FAL_KEY_SECRET"))
+        imagegen = FalImageGenService(
+            image_size="1024x1024",
+            aiohttp_session=session,
+            key_id=os.getenv("FAL_KEY_ID"),
+            key_secret=os.getenv("FAL_KEY_SECRET"))
         # imagegen = OpenAIImageGenService(aiohttp_session=session, api_key=os.getenv("OPENAI_DALLE_API_KEY"), image_size="1024x1024")
         # imagegen = AzureImageGenServiceREST(image_size="1024x1024", aiohttp_session=session, api_key=os.getenv("AZURE_DALLE_API_KEY"), endpoint=os.getenv("AZURE_DALLE_ENDPOINT"), model=os.getenv("AZURE_DALLE_MODEL"))
 

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

@@ -10,6 +10,7 @@
 
 from examples.foundational.support.runner import configure
 
+
 async def main(room_url: str):
     async with aiohttp.ClientSession() as session:
         transport = DailyTransportService(
@@ -22,9 +23,17 @@ async def main(room_url: str):
             camera_enabled=False
         )
 
-        llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-        azure_tts = AzureTTSService(api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
-        elevenlabs_tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"))
+        azure_tts = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"))
+        elevenlabs_tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
 
         messages = [{"role": "system", "content": "tell the user a joke about llamas"}]
 

src/examples/foundational/05-sync-speech-and-image.py

@@ -11,6 +11,7 @@
 
 from examples.foundational.support.runner import configure
 
+
 async def main(room_url):
     async with aiohttp.ClientSession() as session:
         meeting_duration_minutes = 5
@@ -26,11 +27,21 @@ async def main(room_url):
             camera_height=1024
         )
 
-        llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-        tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id="ErXwobaYiN019PkySvjV")
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"))
+        tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id="ErXwobaYiN019PkySvjV")
         # tts = AzureTTSService(api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
 
-        dalle = FalImageGenService(image_size="1024x1024", aiohttp_session=session, key_id=os.getenv("FAL_KEY_ID"), key_secret=os.getenv("FAL_KEY_SECRET"))
+        dalle = FalImageGenService(
+            image_size="1024x1024",
+            aiohttp_session=session,
+            key_id=os.getenv("FAL_KEY_ID"),
+            key_secret=os.getenv("FAL_KEY_SECRET"))
         # dalle = OpenAIImageGenService(aiohttp_session=session, api_key=os.getenv("OPENAI_DALLE_API_KEY"), image_size="1024x1024")
         # dalle = AzureImageGenServiceREST(image_size="1024x1024", aiohttp_session=session, api_key=os.getenv("AZURE_DALLE_API_KEY"), endpoint=os.getenv("AZURE_DALLE_ENDPOINT"), model=os.getenv("AZURE_DALLE_MODEL"))
 

src/examples/foundational/06-listen-and-respond.py

@@ -6,6 +6,7 @@
 from dailyai.queue_aggregators import LLMAssistantContextAggregator, LLMContextAggregator, LLMUserContextAggregator
 from examples.foundational.support.runner import configure
 
+
 async def main(room_url: str, token):
     transport = DailyTransportService(
         room_url,
@@ -15,11 +16,16 @@ async def main(room_url: str, token):
         start_transcription=True,
         mic_enabled=True,
         mic_sample_rate=16000,
-        camera_enabled = False
+        camera_enabled=False
     )
 
-    llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-    tts = AzureTTSService(api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
+    llm = AzureLLMService(
+        api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+        endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+        model=os.getenv("AZURE_CHATGPT_MODEL"))
+    tts = AzureTTSService(
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"))
 
     @transport.event_handler("on_first_other_participant_joined")
     async def on_first_other_participant_joined(transport):

src/examples/foundational/06a-image-sync.py

@@ -18,6 +18,7 @@
 
 from examples.foundational.support.runner import configure
 
+
 class ImageSyncAggregator(AIService):
     def __init__(self, speaking_path: str, waiting_path: str):
         self._speaking_image = Image.open(speaking_path)
@@ -46,9 +47,18 @@ async def main(room_url: str, token):
         transport._mic_enabled = True
         transport._mic_sample_rate = 16000
 
-        llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-        tts = AzureTTSService(api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
-        img = FalImageGenService(image_size="1024x1024", aiohttp_session=session, key_id=os.getenv("FAL_KEY_ID"), key_secret=os.getenv("FAL_KEY_SECRET"))
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"))
+        tts = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"))
+        img = FalImageGenService(
+            image_size="1024x1024",
+            aiohttp_session=session,
+            key_id=os.getenv("FAL_KEY_ID"),
+            key_secret=os.getenv("FAL_KEY_SECRET"))
 
         async def get_images():
             get_speaking_task = asyncio.create_task(

src/examples/foundational/07-interruptible.py

@@ -10,6 +10,7 @@
 
 from examples.foundational.support.runner import configure
 
+
 async def main(room_url: str, token):
     async with aiohttp.ClientSession() as session:
         transport = DailyTransportService(
@@ -23,8 +24,13 @@ async def main(room_url: str, token):
             camera_enabled=False,
         )
 
-        llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-        tts = AzureTTSService(api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"))
+        tts = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"))
 
         async def run_response(user_speech, tma_in, tma_out):
             await tts.run_to_queue(

src/examples/foundational/08-bots-arguing.py

@@ -10,7 +10,8 @@
 
 from examples.foundational.support.runner import configure
 
-async def main(room_url:str):
+
+async def main(room_url: str):
     async with aiohttp.ClientSession() as session:
         transport = DailyTransportService(
             room_url,
@@ -24,16 +25,30 @@ async def main(room_url:str):
             camera_height=1024
         )
 
-        llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-        tts1 = AzureTTSService(api_key=os.getenv("AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
-        tts2 = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id="jBpfuIE2acCO8z3wKNLl")
-        dalle = FalImageGenService(image_size="1024x1024", aiohttp_session=session, key_id=os.getenv("FAL_KEY_ID"), key_secret=os.getenv("FAL_KEY_SECRET"))
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"))
+        tts1 = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"))
+        tts2 = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id="jBpfuIE2acCO8z3wKNLl")
+        dalle = FalImageGenService(
+            image_size="1024x1024",
+            aiohttp_session=session,
+            key_id=os.getenv("FAL_KEY_ID"),
+            key_secret=os.getenv("FAL_KEY_SECRET"))
 
         bot1_messages = [
             {"role": "system", "content": "You are a stern librarian. You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever compromise on the fundamental truth that a hot dog is a sandwich. Your responses should only be a few sentences long."},
         ]
         bot2_messages = [
-            {"role": "system", "content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich."},
+            {
+                "role": "system",
+                "content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich."},
         ]
 
         async def get_bot1_statement():

src/examples/foundational/10-wake-word.py

@@ -71,7 +71,7 @@ async def process_frame(self, frame: QueueFrame) -> AsyncGenerator[QueueFrame, N
 
 
 class NameCheckFilter(AIService):
-    def __init__(self, names:list[str]):
+    def __init__(self, names: list[str]):
         self.names = names
         self.sentence = ""
 
@@ -123,8 +123,14 @@ async def main(room_url: str, token):
         transport._camera_width = 720
         transport._camera_height = 1280
 
-        llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
-        tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id="jBpfuIE2acCO8z3wKNLl")
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"))
+        tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id="jBpfuIE2acCO8z3wKNLl")
         isa = ImageSyncAggregator()
 
         @transport.event_handler("on_first_other_participant_joined")