Update app.py

app.py

@@ -24,7 +24,7 @@ class AssistantAgent:
         self.headers = {"Content-Type": "application/json"}
 
     def call_gemini_api(self, prompt: str) -> str:
-        retry_delay = 60  # Chờ 60 giây nếu gặp lỗi quota
+        retry_delay = 5  # Chờ 5 giây nếu gặp lỗi quota
         payload = {
             "contents": [{
                 "parts": [{"text": prompt}]
@@ -37,10 +37,10 @@ class AssistantAgent:
                 return response.json()["candidates"][0]["content"]["parts"][0]["text"].strip()
             except requests.exceptions.RequestException as e:
                 if "429" in str(e):
-                    retry_delay = max(retry_delay, 60)
+                    retry_delay = max(retry_delay, 5)
                     print(f"Quota error, retrying after {retry_delay} seconds... (Attempt {attempt + 1}/3)")
                     time.sleep(retry_delay)
-                    retry_delay += 10
+                    retry_delay += 5
                 else:
                     return f"Error calling Gemini API: {e}"
         return "Error: Exceeded retry attempts due to quota limits."
@@ -130,8 +130,8 @@ class AssistantAgent:
                     answer = batch_answers[idx].split('. ', 1)[1] if idx < len(batch_answers) and '. ' in batch_answers[idx] else "Error: Could not parse answer."
                     answers.append(answer)
             if i + batch_size < len(questions):
-                print("Waiting 60 seconds before next batch to avoid rate limit...")
-                time.sleep(60)
+                print("Waiting 5 seconds before next batch to avoid rate limit...")
+                time.sleep(5)  # Giảm từ 60 giây xuống 5 giây
         return answers
 
     def process_file(self, question: str, file_path: str) -> str: