Update qa.py

qa.py

@@ -2,11 +2,11 @@
 
 import os
 import requests
-import tempfile
 import json
+import tempfile
 import streamlit as st
 
-from utils import generate_audio_mp3  # We'll reuse your existing TTS function
+from utils import generate_audio_mp3  # Reuse your existing TTS function
 
 def transcribe_audio_deepgram(local_audio_path: str) -> str:
     """
@@ -18,11 +18,12 @@ def transcribe_audio_deepgram(local_audio_path: str) -> str:
         raise ValueError("Deepgram API key not found in environment variables.")
 
     url = "https://api.deepgram.com/v1/listen?model=nova-2&smart_format=true"
-    # For WAV, set Content-Type to audio/wav. For MP3, use audio/mpeg, etc.
     headers = {
         "Authorization": f"Token {DEEPGRAM_API_KEY}",
-        "Content-Type": "audio/wav",
+        # Adjust Content-Type if user upload might be MP3: "audio/mpeg"
+        "Content-Type": "audio/wav"
     }
+
     with open(local_audio_path, "rb") as f:
         response = requests.post(url, headers=headers, data=f)
     response.raise_for_status()
@@ -32,14 +33,14 @@ def transcribe_audio_deepgram(local_audio_path: str) -> str:
     transcript = data["results"]["channels"][0]["alternatives"][0].get("transcript", "")
     return transcript
 
+
 def call_llm_for_qa(conversation_so_far: str, user_question: str) -> dict:
     """
     Minimal function that calls your LLM (Groq) to answer a follow-up question.
     Returns a Python dict, e.g.: {"speaker": "John", "text": "..."}
     """
-    # Example system prompt:
     system_prompt = f"""
-    You are John, the guest on this podcast. The user is asking a follow-up question.
+    You are John, the guest speaker. The user is asking a follow-up question.
     Conversation so far:
     {conversation_so_far}
 
@@ -50,19 +51,15 @@ def call_llm_for_qa(conversation_so_far: str, user_question: str) -> dict:
     {{ "speaker": "John", "text": "Sure, here's my answer..." }}
     """
 
-    # Here, you'd do something like your existing generate_script or direct Groq call
-    # For demonstration, let's do a placeholder
-    # This should be replaced by your real LLM call, e.g., call_groq_api(system_prompt)
-    # and parse out the JSON response.
-
-    # Example pseudo-code:
-    from utils import call_groq_api_for_qa  # Suppose you define this in utils
+    # We'll rely on a helper in utils.py to do the Groq call:
+    from utils import call_groq_api_for_qa
 
     raw_json_response = call_groq_api_for_qa(system_prompt)
-    # Expect something like: {"speaker": "John", "text": "Here's an answer."}
+    # Expect a JSON string like: {"speaker": "John", "text": "some short answer"}
     response_dict = json.loads(raw_json_response)
     return response_dict
 
+
 def handle_qa_exchange(user_question: str) -> (bytes, str):
     """
     1) Read conversation_so_far from session_state
@@ -78,7 +75,7 @@ def handle_qa_exchange(user_question: str) -> (bytes, str):
     speaker = response_dict.get("speaker", "John")
 
     # Update conversation
-    # We store: "User: question" and "John: answer"
+    # e.g., "User: question" and "John: answer"
     new_history = conversation_so_far + f"\nUser: {user_question}\n{speaker}: {answer_text}\n"
     st.session_state["conversation_history"] = new_history