add code

app.py

@@ -17,6 +17,24 @@ from dotenv import load_dotenv
 
 load_dotenv()
 
+import logging
+
+# Configure the root logger to WARNING to suppress debug messages from other libraries
+logging.basicConfig(level=logging.WARNING)
+
+# Create a console handler
+console_handler = logging.StreamHandler()
+console_handler.setLevel(logging.DEBUG)
+
+# Create a formatter
+formatter = logging.Formatter("%(name)s - %(levelname)s - %(message)s")
+console_handler.setFormatter(formatter)
+
+# Configure the logger for your specific library
+logger = logging.getLogger("gradio_webrtc")
+logger.setLevel(logging.DEBUG)
+logger.addHandler(console_handler)
+
 @dataclass
 class Deps:
     client: AsyncClient
@@ -134,10 +152,16 @@ deps = Deps(
 )
 
 
-async def stream_from_agent(prompt: str, chatbot: list[dict], past_messages: list):
-    yield "", gr.skip(), gr.skip()
+async def stream_from_agent(audio: tuple[int, np.ndarray], chatbot: list[dict], past_messages: list):
+
+    prompt = groq_client.audio.transcriptions.create(
+      file=("audio-file.mp3", audio_to_bytes(audio)),
+        model="whisper-large-v3-turbo",
+        response_format="verbose_json",
+    ).text
+
     chatbot.append({'role': 'user', 'content': prompt})
-    yield gr.skip(), chatbot, gr.skip() 
+    yield AdditionalOutputs(chatbot, gr.skip())
     async with weather_agent.run_stream(prompt, deps=deps, message_history=past_messages) as result:
         for message in result.new_messages():
             past_messages.append(message)
@@ -153,14 +177,14 @@ async def stream_from_agent(prompt: str, chatbot: list[dict], past_messages: lis
                 for gr_message in chatbot:
                     if gr_message.get('metadata', {}).get('id', "") == message.tool_id:
                         gr_message['content'] = f"Output: {json.dumps(message.content)}"
-            yield gr.skip(), chatbot, gr.skip()
+            yield AdditionalOutputs(chatbot, gr.skip())
         chatbot.append({'role': 'assistant', 'content': ""})
         async for message in result.stream_text():
             chatbot[-1]["content"] = message
-            yield gr.skip(), chatbot, gr.skip()
+            yield AdditionalOutputs(chatbot, gr.skip())
         data = await result.get_data()
         past_messages.append(ModelTextResponse(content=data))
-        yield gr.skip(), gr.skip(), past_messages
+        yield AdditionalOutputs(gr.skip(), past_messages)
 
 
 with gr.Blocks() as demo:
@@ -183,9 +207,13 @@ with gr.Blocks() as demo:
     past_messages = gr.State([])
     chatbot = gr.Chatbot(label="Packing Assistant", type="messages",
                          avatar_images=(None, "https://ai.pydantic.dev/img/logo-white.svg"))
-    prompt = gr.Textbox(lines=1, label="Enter your destination or follow-up question", placeholder="Miami, Florida")
-    prompt.submit(stream_from_agent, inputs=[prompt, chatbot, past_messages],
-                   outputs=[prompt, chatbot, past_messages])
+    audio= WebRTC(label="Talk with the Agent",
+                  modality="audio",
+                  mode="send")
+    audio.stream(ReplyOnPause(stream_from_agent), inputs=[audio, chatbot, past_messages],
+                 outputs=[audio])
+    audio.on_additional_outputs(lambda c,s: (c, s), outputs=[chatbot, past_messages],
+                                queue=False, show_progress="hidden")