Initial commit with LlamaIndex-based agent

app.py

@@ -7,10 +7,22 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
+import traceback
 
-from duckduckgo_search import DDGS
-from sympy import sympify
-from sympy.core.sympify import SympifyError
+# Import real tool dependencies
+try:
+    from duckduckgo_search import DDGS
+except ImportError:
+    print("Warning: duckduckgo_search not installed. Web search will be limited.")
+    DDGS = None
+
+try:
+    from sympy import sympify
+    from sympy.core.sympify import SympifyError
+except ImportError:
+    print("Warning: sympy not installed. Math calculator will be limited.")
+    sympify = None
+    SympifyError = Exception
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
@@ -19,7 +31,7 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class SmartAgent:
     def __init__(self):
         print("Initializing Local LLM Agent...")
-
+        
         # Initialize Zephyr-7B model
         self.llm = HuggingFaceLLM(
             model_name="HuggingFaceH4/zephyr-7b-beta",
@@ -29,21 +41,21 @@ class SmartAgent:
             generate_kwargs={"temperature": 0.7, "do_sample": True},
             device_map="auto"
         )
-
+        
         # Define tools with real implementations
         self.tools = [
             FunctionTool.from_defaults(
                 fn=self.web_search,
                 name="web_search",
-                description="Searches the web for current information using DuckDuckGo."
+                description="Searches the web for current information using DuckDuckGo when questions require up-to-date knowledge"
             ),
             FunctionTool.from_defaults(
                 fn=self.math_calculator,
                 name="math_calculator",
-                description="Performs symbolic math using SymPy."
+                description="Performs mathematical calculations and symbolic math using SymPy when questions involve numbers or equations"
             )
         ]
-
+        
         # Create ReAct agent with tools
         self.agent = ReActAgent.from_tools(
             tools=self.tools,
@@ -55,27 +67,51 @@ class SmartAgent:
     def web_search(self, query: str) -> str:
         """Real web search using DuckDuckGo"""
         print(f"Web search triggered for: {query[:50]}...")
+        
+        if not DDGS:
+            return "Web search unavailable - duckduckgo_search not installed"
+        
         try:
             with DDGS() as ddgs:
-                results = ddgs.text(query, max_results=3)
+                results = list(ddgs.text(query, max_results=3))
                 if results:
-                    return "\n\n".join([f"{r['title']}: {r['href']}" for r in results])
+                    formatted_results = []
+                    for i, r in enumerate(results, 1):
+                        title = r.get('title', 'No title')
+                        body = r.get('body', 'No description')[:200]
+                        url = r.get('href', '')
+                        formatted_results.append(f"{i}. {title}\n{body}...\nSource: {url}")
+                    return "\n\n".join(formatted_results)
                 else:
-                    return "No results found."
+                    return "No search results found for the query."
         except Exception as e:
             print(f"Web search error: {e}")
-            return f"Error during web search: {e}"
+            return f"Error during web search: {str(e)}"
 
     def math_calculator(self, expression: str) -> str:
         """Safe math evaluation using SymPy"""
         print(f"Math calculation triggered for: {expression}")
+        
+        if not sympify:
+            # Fallback to basic eval with safety checks
+            try:
+                # Only allow basic math operations
+                allowed_chars = set('0123456789+-*/().^ ')
+                if not all(c in allowed_chars for c in expression.replace(' ', '')):
+                    return "Error: Only basic math operations are allowed"
+                result = eval(expression.replace('^', '**'))
+                return str(result)
+            except Exception as e:
+                return f"Error: Could not evaluate the mathematical expression - {str(e)}"
+        
         try:
+            # Use SymPy for safe evaluation
             result = sympify(expression).evalf()
             return str(result)
         except SympifyError as e:
-            return f"Error: Could not parse the expression ({e})"
+            return f"Error: Could not parse the mathematical expression - {str(e)}"
         except Exception as e:
-            return f"Error: Calculation failed ({e})"
+            return f"Error: Calculation failed - {str(e)}"
 
     def __call__(self, question: str) -> str:
         print(f"Processing question (first 50 chars): {question[:50]}...")
@@ -84,10 +120,11 @@ class SmartAgent:
             return str(response)
         except Exception as e:
             print(f"Agent error: {str(e)}")
+            print(f"Full traceback: {traceback.format_exc()}")
             return f"Error processing question: {str(e)}"
 
 
-# --- Original Submission Logic ---
+# --- Submission Logic ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the agent on them, submits all answers,
@@ -111,10 +148,11 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         agent = SmartAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
+        print(f"Full traceback: {traceback.format_exc()}")
         return f"Error initializing agent: {e}", None
 
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+    print(f"Agent code URL: {agent_code}")
 
     # Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -131,7 +169,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
         print(f"Error decoding JSON response from questions endpoint: {e}")
-        print(f"Response text: {response.text[:500]}")
         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
@@ -141,45 +178,68 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    
+    for i, item in enumerate(questions_data, 1):
         task_id = item.get("task_id")
         question_text = item.get("question")
+        
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
+            
+        print(f"Processing question {i}/{len(questions_data)}: {task_id}")
+        
         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})
+            results_log.append({
+                "Task ID": task_id, 
+                "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text,
+                "Submitted Answer": submitted_answer[:200] + "..." if len(submitted_answer) > 200 else submitted_answer
+            })
+            print(f"✅ Completed question {i}: {task_id}")
         except Exception as e:
-            print(f"Error running agent on task {task_id}: {e}")
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            print(f"❌ Error running agent on task {task_id}: {e}")
+            error_answer = f"AGENT ERROR: {str(e)}"
+            answers_payload.append({"task_id": task_id, "submitted_answer": error_answer})
+            results_log.append({
+                "Task ID": task_id, 
+                "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text,
+                "Submitted Answer": error_answer
+            })
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
     # Prepare submission
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    submission_data = {
+        "username": username.strip(), 
+        "agent_code": agent_code, 
+        "answers": answers_payload
+    }
+    
+    status_update = f"Agent finished processing. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
 
-    # Submit
+    # Submit answers
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
+        
         final_status = (
-            f"Submission Successful!\n"
+            f"🎉 Submission Successful!\n\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.')}"
         )
-        print("Submission successful.")
+        print("✅ Submission successful!")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
+        
     except requests.exceptions.HTTPError as e:
         error_detail = f"Server responded with status {e.response.status_code}."
         try:
@@ -187,44 +247,72 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
         except requests.exceptions.JSONDecodeError:
             error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
+        status_message = f"❌ Submission Failed: {error_detail}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
+        
     except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
+        status_message = "❌ Submission Failed: The request timed out."
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
+        
     except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
+        status_message = f"❌ Submission Failed: Network error - {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
+        
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
+        status_message = f"❌ An unexpected error occurred during submission: {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
 
 # --- Gradio UI ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Local LLM Agent Evaluation Runner")
+with gr.Blocks(title="Local LLM Agent Evaluation") as demo:
+    gr.Markdown("# 🤖 Local LLM Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1. Log in to your Hugging Face account
-        2. Click 'Run Evaluation & Submit All Answers'
-        3. Wait for the local LLM to process all questions
+        1. 🔐 Log in to your Hugging Face account using the button below
+        2. 🚀 Click 'Run Evaluation & Submit All Answers'
+        3. ⏳ Wait for the local LLM (Zephyr-7B) to process all questions
+        4. 📊 View your results and submission status
+        
+        **Features:**
+        - 🔍 Real web search using DuckDuckGo
+        - 🧮 Advanced math calculations with SymPy
+        - 🧠 Powered by HuggingFace Zephyr-7B model
         """
     )
 
-    gr.LoginButton()
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    with gr.Row():
+        gr.LoginButton()
+    
+    with gr.Row():
+        run_button = gr.Button(
+            "🚀 Run Evaluation & Submit All Answers", 
+            variant="primary", 
+            size="lg"
+        )
+    
+    status_output = gr.Textbox(
+        label="📋 Run Status / Submission Result", 
+        lines=8, 
+        interactive=False,
+        placeholder="Click the button above to start the evaluation..."
+    )
+    
+    results_table = gr.DataFrame(
+        label="📊 Questions and Agent Answers", 
+        wrap=True,
+        interactive=False
+    )
 
+    # Wire up the button
     run_button.click(
         fn=run_and_submit_all,
         outputs=[status_output, results_table]
@@ -232,14 +320,32 @@ with gr.Blocks() as demo:
 
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    print("\n" + "="*60)
+    print("🚀 Application Startup at", pd.Timestamp.now().strftime("%Y-%m-%d %H:%M:%S"))
+    print("="*60)
+    
     space_host_startup = os.getenv("SPACE_HOST")
     space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+
+    if space_id_startup:
         print(f"✅ SPACE_ID found: {space_id_startup}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
     else:
-        print("❌ SPACE_HOST not found. Please set environment variables.")
+        print("ℹ️  SPACE_ID environment variable not found (running locally?).")
 
-    demo.launch()
+    print("-" * 60)
+    print("🎯 Launching Gradio Interface for Local LLM Agent Evaluation...")
+    
+    # Launch without share=True for Hugging Face Spaces
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        show_error=True
+    )

requirements.txt

@@ -3,9 +3,11 @@ llama-index-llms-huggingface
 transformers>=4.30.0
 torch>=2.0.0
 accelerate
-gradio>=3.30
+gradio>=4.0.0
 requests
 pandas
 python-dotenv
-duckduckgo_search
+duckduckgo-search
 sympy
+sentencepiece
+protobuf