Update app.py

app.py

@@ -2,107 +2,115 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+from transformers import pipeline
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-DEFAULT_HF_MODEL = "mistralai/Mistral-7B-Instruct-v0.1"
+HF_MODEL_NAME = "facebook/bart-large-mnli"  # Smaller, free model that works well in Spaces
 
-# --- Basic Agent Definition ---
+# --- Enhanced Agent Definition ---
 class BasicAgent:
-    def __init__(self, hf_token=None, model_name=DEFAULT_HF_MODEL):
-        print("Initializing BasicAgent with LLM...")
+    def __init__(self, hf_token=None):
+        print("Initializing LLM Agent...")
         self.hf_token = hf_token
-        self.model_name = model_name
         self.llm = None
         
-        if hf_token:
-            try:
-                print(f"Loading model: {model_name}")
-                self.tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
-                self.model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token)
-                self.llm = pipeline(
-                    "text-generation",
-                    model=self.model,
-                    tokenizer=self.tokenizer,
-                    device_map="auto"
-                )
-                print("Model loaded successfully")
-            except Exception as e:
-                print(f"Error loading model: {e}")
-                raise Exception(f"Could not load model: {e}")
-        else:
-            print("No HF token provided - agent will use default answers")
-    
+        try:
+            # Using a smaller model that works better in Spaces
+            self.llm = pipeline(
+                "text-generation",
+                model=HF_MODEL_NAME,
+                token=hf_token,
+                device_map="auto"
+            )
+            print("LLM initialized successfully")
+        except Exception as e:
+            print(f"Error initializing LLM: {e}")
+            # Fallback to simple responses if LLM fails
+            self.llm = None
+
     def __call__(self, question: str) -> str:
         if not self.llm:
-            return "This is a default answer (no LLM initialized)"
+            return "This is a default answer (LLM not available)"
             
         try:
-            print(f"Generating answer for question: {question[:50]}...")
+            print(f"Generating answer for: {question[:50]}...")
             response = self.llm(
                 question,
-                max_new_tokens=150,
+                max_length=100,
                 do_sample=True,
-                temperature=0.7,
-                top_p=0.9
+                temperature=0.7
             )
             return response[0]['generated_text']
         except Exception as e:
             print(f"Error generating answer: {e}")
             return f"Error generating answer: {e}"
 
-def run_and_submit_all(hf_token: str, request: gr.Request):
-    """Main function to run evaluation and submit answers"""
-    # Get user info from the request
+def run_and_submit_all(request: gr.Request):
+    """
+    Modified to work with Gradio's auth system
+    """
+    # Get username from auth
     if not request.username:
-        return "Please Login to Hugging Face with the button.", None
-
+        return "Please login with Hugging Face account", None
+    
     username = request.username
     space_id = os.getenv("SPACE_ID")
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # Initialize agent
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent(hf_token=hf_token)
+        agent = BasicAgent(hf_token=os.getenv("HF_TOKEN"))
     except Exception as e:
         return f"Error initializing agent: {e}", None
     
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
 
-    # Fetch questions
+    # 2. Fetch Questions
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-            return "Fetched questions list is empty or invalid format.", None
+            return "No questions received from server", None
     except Exception as e:
         return f"Error fetching questions: {e}", None
 
-    # Process questions
+    # 3. Process Questions
     results_log = []
     answers_payload = []
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
-        if not task_id or question_text is None:
+        if not task_id or not question_text:
             continue
+            
         try:
-            submitted_answer = agent(question_text)
-            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            answer = agent(question_text)
+            answers_payload.append({
+                "task_id": task_id,
+                "submitted_answer": answer
+            })
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": answer
+            })
         except Exception as e:
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": f"ERROR: {str(e)}"
+            })
 
     if not answers_payload:
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+        return "No valid answers generated", pd.DataFrame(results_log)
 
-    # Submit answers
+    # 4. Submit Answers
     submission_data = {
-        "username": username.strip(),
+        "username": username,
         "agent_code": agent_code,
         "answers": answers_payload
     }
@@ -110,47 +118,40 @@ def run_and_submit_all(hf_token: str, request: gr.Request):
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
-        result_data = response.json()
-        final_status = (
+        result = response.json()
+        
+        status = (
             f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
+            f"User: {result.get('username')}\n"
+            f"Score: {result.get('score', 'N/A')}% "
+            f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')})\n"
+            f"Message: {result.get('message', '')}"
         )
-        return final_status, pd.DataFrame(results_log)
+        return status, pd.DataFrame(results_log)
     except Exception as e:
-        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+        return f"Submission failed: {str(e)}", pd.DataFrame(results_log)
 
 # --- Gradio Interface ---
 with gr.Blocks() as demo:
     gr.Markdown("# LLM Agent Evaluation Runner")
     gr.Markdown("""
         **Instructions:**
-        1. Get your Hugging Face API token from [your settings](https://huggingface.co/settings/tokens)
-        2. Enter your token below
-        3. Log in to your Hugging Face account
-        4. Click 'Run Evaluation & Submit All Answers'
+        1. Log in with your Hugging Face account
+        2. Click 'Run Evaluation'
+        3. View your results
     """)
 
+    gr.LoginButton()
+    
     with gr.Row():
-        hf_token_input = gr.Textbox(
-            label="Hugging Face API Token",
-            type="password",
-            placeholder="hf_xxxxxxxxxxxxxxxx",
-            info="Required for LLM access"
-        )
+        run_btn = gr.Button("Run Evaluation & Submit Answers", variant="primary")
     
-    gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status", lines=5)
+    status_output = gr.Textbox(label="Status", interactive=False)
     results_table = gr.DataFrame(label="Results", wrap=True)
 
-    run_button.click(
+    run_btn.click(
         fn=run_and_submit_all,
-        inputs=[hf_token_input],
+        inputs=[],
         outputs=[status_output, results_table]
     )