Update app.py

app.py

@@ -1,229 +1,153 @@
+"""
+Advanced Agent Evaluation Runner with Custom LangGraph Implementation
+"""
 import os
 import gradio as gr
 import requests
 import pandas as pd
+from typing import Dict, List, Optional
 from datetime import datetime
-import random
-from transformers import Tool
-from transformers.agents import Agent
+from langgraph.graph import StateGraph, END
+from langchain_core.messages import HumanMessage, AIMessage
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Enhanced Agent Definition ---
-class EnhancedAgent:
-    def __init__(self):
-        print("EnhancedAgent initialized with tools.")
-        self.tools = {
-            "calculator": self.calculator,
-            "time": self.get_current_time,
-            "random_choice": self.random_choice
-        }
-        
-    def calculator(self, expression: str) -> str:
-        """Evaluate mathematical expressions"""
+# --- Custom Agent State Definition ---
+class AgentState(Dict):
+    messages: List[Dict]
+    question: str
+    response: Optional[str]
+
+# --- Custom Tool Implementations ---
+class MathTool:
+    def execute(self, expression: str) -> str:
         try:
-            return str(eval(expression))
+            return f"Calculation result: {eval(expression)}"
         except:
-            return "Error: Could not evaluate the expression"
+            return "Error: Invalid mathematical expression"
 
-    def get_current_time(self) -> str:
-        """Get current UTC time"""
-        return datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC")
+class TimeTool:
+    def execute(self) -> str:
+        return f"Current time: {datetime.utcnow().strftime('%Y-%m-%d %H:%M:%S UTC')}"
 
-    def random_choice(self, items: str) -> str:
-        """Randomly select from comma-separated items"""
-        try:
-            options = [x.strip() for x in items.split(",")]
-            return f"I choose: {random.choice(options)}"
-        except:
-            return "Error: Please provide comma-separated options"
+# --- Custom Agent Graph Builder ---
+def create_agent_workflow():
+    workflow = StateGraph(AgentState)
+    
+    # Define nodes
+    def route_question(state: AgentState):
+        question = state["question"].lower()
+        if any(op in question for op in ["+", "-", "*", "/", "calculate"]):
+            return "math_tool"
+        elif "time" in question or "current time" in question:
+            return "time_tool"
+        return "llm_response"
+    
+    def math_node(state: AgentState):
+        tool = MathTool()
+        return {"response": tool.execute(state["question"])}
+    
+    def time_node(state: AgentState):
+        tool = TimeTool()
+        return {"response": tool.execute()}
+    
+    def llm_node(state: AgentState):
+        # Simulated LLM response
+        return {"response": f"AI response to: {state['question']}"}
+    
+    # Build graph
+    workflow.add_node("math_tool", math_node)
+    workflow.add_node("time_tool", time_node)
+    workflow.add_node("llm_response", llm_node)
+    
+    workflow.add_conditional_edges(
+        "start",
+        route_question,
+        {
+            "math_tool": "math_tool",
+            "time_tool": "time_tool",
+            "llm_response": "llm_response"
+        }
+    )
+    
+    workflow.add_edge("math_tool", END)
+    workflow.add_edge("time_tool", END)
+    workflow.add_edge("llm_response", END)
+    
+    workflow.set_entry_point("start")
+    return workflow.compile()
 
+# --- Custom Agent Class ---
+class CustomLangGraphAgent:
+    def __init__(self):
+        self.workflow = create_agent_workflow()
+        print("Custom LangGraph agent initialized")
+    
     def __call__(self, question: str) -> str:
-        print(f"Processing question: {question[:100]}...")
-        question_lower = question.lower()
-        
-        # Math questions
-        if any(word in question_lower for word in ["calculate", "what is", "how much is", "+", "-", "*", "/"]):
-            expr = question.replace("?", "").replace("what is", "").replace("calculate", "").strip()
-            return self.tools["calculator"](expr)
-        
-        # Time questions
-        if any(word in question_lower for word in ["time", "current time", "what time is it"]):
-            return self.tools["time"]()
-        
-        # Random choice questions
-        if " or " in question_lower and not any(word in question_lower for word in ["who", "what", "when", "where", "why", "how"]):
-            return self.tools["random_choice"](question.replace("?", "").replace(" or ", ","))
-        
-        # Fallback to HF Agent for complex questions
         try:
-            agent = Agent("bigcode/starcoder")
-            return agent.run(question, remote=True)
+            state = {"question": question, "messages": [], "response": None}
+            result = self.workflow.invoke(state)
+            return result["response"]
         except Exception as e:
             print(f"Agent error: {e}")
-            return "I couldn't find an answer to that question."
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the EnhancedAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID")
-
-    if profile:
-        username = f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
-
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+            return "Error processing question"
 
-    # 1. Instantiate Agent
-    try:
-        agent = EnhancedAgent()
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
+# --- Evaluation Runner ---
+def run_evaluation(profile: gr.OAuthProfile | None):
+    if not profile:
+        return "Please login first", None
+    
+    space_id = os.getenv("SPACE_ID", "local-test")
+    api_url = os.getenv("API_URL", DEFAULT_API_URL)
     
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
-    try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
-        if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
-        print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        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}")
-        return f"An unexpected error occurred fetching questions: {e}", None
-
-    # 3. Run your Agent
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    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:
-            print(f"Skipping item with missing task_id or question: {item}")
-            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})
-        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}"})
-
-    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)
-
-    # 4. 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}'..."
-    print(status_update)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
+        agent = CustomLangGraphAgent()
+        questions = requests.get(f"{api_url}/questions", timeout=15).json()
+        
+        results = []
+        answers = []
+        for q in questions:
+            try:
+                answer = agent(q["question"])
+                answers.append({"task_id": q["task_id"], "submitted_answer": answer})
+                results.append({"Task ID": q["task_id"], "Question": q["question"], "Answer": answer})
+            except Exception as e:
+                results.append({"Task ID": q["task_id"], "Question": q["question"], "Answer": f"Error: {e}"})
+        
+        submission = {
+            "username": profile.username,
+            "agent_code": f"https://huggingface.co/spaces/{space_id}",
+            "answers": answers
+        }
+        
+        response = requests.post(f"{api_url}/submit", json=submission, timeout=60)
         response.raise_for_status()
-        result_data = response.json()
-        final_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.')}"
+        
+        return (
+            f"Success! Score: {response.json().get('score', 'N/A')}%",
+            pd.DataFrame(results)
         )
-        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:
-            error_json = e.response.json()
-            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}"
-        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."
-        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}"
-        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}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Enhanced Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-        1. Log in to your Hugging Face account using the button below.
-        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the enhanced agent, submit answers, and see the score.
-
-        **Agent Capabilities:**
-        - Math calculations
-        - Current time lookup
-        - Random choice selection
-        - Complex question handling via AI
-        """
-    )
-
+        return f"Evaluation failed: {e}", None
+
+# --- Gradio Interface ---
+with gr.Blocks(title="Custom LangGraph Agent Evaluator") as app:
+    gr.Markdown("""
+    ## Custom LangGraph Agent Evaluation
+    Test your agent against the benchmark questions
+    """)
+    
     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)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+    run_btn = gr.Button("Start Evaluation")
+    output = gr.Textbox(label="Results")
+    results = gr.DataFrame(label="Details")
+    
+    run_btn.click(
+        fn=run_evaluation,
+        outputs=[output, results]
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    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}.hf.space")
-
-    if space_id_startup:
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-    print("Launching Gradio Interface for Enhanced Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    app.launch()