Update app.py

app.py

@@ -22,7 +22,8 @@ class NativeGeminiAgent:
         
         self.api_url = api_url
         
-        # Enable native grounding with Google Search
+        # --- CORRECTED INITIALIZATION ---
+        # Enable native grounding with Google Search. No parameters are needed.
         google_search_retrieval = genai.protos.Tool(
             google_search_retrieval=genai.protos.GoogleSearchRetrieval()
         )
@@ -32,9 +33,7 @@ class NativeGeminiAgent:
         self.model = genai.GenerativeModel(
             model_name=self.model_name,
             tools=[google_search_retrieval],
-            # A more direct prompt, trusting the model's native abilities
             system_instruction="You are a world-class problem solver. Your goal is to answer the user's question accurately. Use your tools and reasoning abilities to provide a definitive answer.",
-            # Safety settings dialed down to allow answering controversial topics if they appear in GAIA
             safety_settings={
                 HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
                 HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_NONE,
@@ -55,8 +54,6 @@ class NativeGeminiAgent:
     def __call__(self, question: str, task_id: str) -> str:
         print(f"\n{'='*20}\nProcessing Task ID: {task_id}")
         
-        # --- This is the core of the new multi-modal logic ---
-        # We build a list of "parts" to send to the model, not just a string.
         prompt_parts = [question]
         
         # 1. Automatically find and add any URLs from the question text
@@ -64,17 +61,17 @@ class NativeGeminiAgent:
         if urls_in_question:
             for url in urls_in_question:
                 print(f"Found URL in question: {url}")
-                prompt_parts.append(genai.Part.from_uri(uri=url, mime_type="video/mp4")) # Assume video for now, Gemini can handle it
+                # Use a general MIME type that Gemini can often auto-detect for sources like YouTube
+                prompt_parts.append(genai.Part.from_uri(uri=url, mime_type="video/mp4"))
 
         # 2. Check for and add any associated files from the GAIA server
         file_url = f"{self.api_url}/files/{task_id}"
         if self._check_if_file_exists(file_url):
             print(f"Found associated file, adding URL: {file_url}")
-            # We need to determine the mime type. Let's assume common ones for GAIA.
-            # A simple heuristic can be used, or we can try to guess from the URL.
-            mime_type = "image/jpeg" # Default, can be improved
-            if '.pdf' in file_url: mime_type = "application/pdf"
-            if '.txt' in file_url: mime_type = "text/plain"
+            # Simple MIME type guessing for common GAIA file types
+            mime_type = "image/jpeg" # Default
+            if file_url.endswith('.pdf'): mime_type = "application/pdf"
+            if file_url.endswith('.txt'): mime_type = "text/plain"
             prompt_parts.append(genai.Part.from_uri(uri=file_url, mime_type=mime_type))
         else:
             print("No associated file found for this task.")
@@ -82,10 +79,9 @@ class NativeGeminiAgent:
         print(f"Sending {len(prompt_parts)} parts to the model.")
 
         try:
-            # Generate the response using the multi-modal prompt
-            response = self.model.generate_content(prompt_parts)
+            response = self.model.generate_content(prompt_parts, request_options={'timeout': 120})
             
-            # The grounding feature may add citations. We need to remove them for the final answer.
+            # The grounding feature may add citations. We remove them for the final answer.
             final_answer = re.sub(r'\[\d+\]', '', response.text).strip()
             print(f"Model generated answer: {final_answer}")
             return final_answer
@@ -94,18 +90,17 @@ class NativeGeminiAgent:
             print(f"An error occurred while calling the Gemini API: {e}")
             return f"AGENT_ERROR: Could not get a response from the model. Details: {e}"
 
-# --- Main run_and_submit_all function (largely the same, but simpler) ---
+# --- Main run_and_submit_all function ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
     if not profile: return "Please Login to Hugging Face with the button.", None
     username = f"{profile.username}"
 
-    pplx_key, gemini_key = os.getenv("PPLX_API_KEY"), os.getenv("GEMINI_API_KEY")
+    gemini_key = os.getenv("GEMINI_API_KEY")
     if not gemini_key: return "CRITICAL ERROR: GEMINI_API_KEY not found in Space secrets.", None
     
     api_url = DEFAULT_API_URL
     try:
-        # We no longer need the Perplexity key for the agent
         agent = NativeGeminiAgent(gemini_api_key=gemini_key, api_url=api_url)
         questions_data = requests.get(f"{api_url}/questions", timeout=15).json()
     except Exception as e: return f"Error during setup: {e}", None
@@ -123,7 +118,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
              print(error_message)
              results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_message})
         
-        # API calls are now fewer but more complex. A delay is still wise.
         print(f"--- Waiting for 10 seconds before next question... ---")
         time.sleep(10)