Update app.py

app.py

@@ -2,122 +2,118 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-from langchain_core.messages import HumanMessage
-from tools import build_graph
+import re
 
-# Constants
+# --- Ensure HF Hub token is available in the Space ---
+token = gr.get_oauth_token()
+if token:
+    os.environ["agents_token"] = token.token
+
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class BasicAgent:
-    
-    def __init__(self, csv_file_path: str = "embeddings.csv"):
-        print("BasicAgent initialized.")
-        self.graph = build_graph(csv_file_path=csv_file_path)
-    
+# --- LangChain Agent Definition ---
+from langchain.llms import HuggingFaceHub
+from langchain.agents import initialize_agent, Tool
+from langchain.agents.agent_types import AgentType
+from langchain.tools import tool
+from duckduckgo_search import DDGS
+
+@tool
+def search_web(query: str) -> str:
+    with DDGS() as ddgs:
+        results = list(ddgs.text(query, max_results=3))
+    return results[0]["body"] if results else "No result"
+
+@tool
+def run_code_snippet(code: str) -> str:
+    try:
+        local_env = {}
+        exec(code, {}, local_env)
+        result = [v for v in local_env.values() if isinstance(v, (int, float, str))]
+        return str(result[0]) if result else "0"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+class GAIAAgent:
+    def __init__(self):
+        print("Initializing LangChain agent with Hugging Face model...")
+        self.llm = HuggingFaceHub(
+            repo_id="google/flan-t5-xl",  # You can change this to another HF model
+            model_kwargs={"temperature": 0.3, "max_length": 256}
+        )
+        self.tools = [search_web, run_code_snippet]
+        self.agent = initialize_agent(
+            self.tools,
+            self.llm,
+            agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+            verbose=True
+        )
+
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        
-        # Wrap the question in a HumanMessage
-        messages = [HumanMessage(content=question)]
-        messages = self.graph.invoke({"messages": messages})
-        
-        # Extract answer and remove "FINAL ANSWER: " prefix
-        answer = messages['messages'][-1].content
-        if answer.startswith("FINAL ANSWER: "):
-            return answer[14:]
-        else:
-            # Look for FINAL ANSWER in the response
-            lines = answer.split('\n')
-            for line in lines:
-                if line.strip().startswith("FINAL ANSWER:"):
-                    return line.strip()[14:].strip()
-            return answer
+        try:
+            result = self.agent.run(question)
+            return f"FINAL ANSWER: {self.clean_answer(result)}"
+        except Exception as e:
+            return f"FINAL ANSWER: Error: {e}"
+
+    def clean_answer(self, ans: str) -> str:
+        ans = re.sub(r"[\$,%]", "", ans)
+        return ans.strip()
 
+# --- Evaluation & Submission Pipeline ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    if not profile:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
-    
-    username = f"{profile.username}"
-    print(f"User logged in: {username}")
-    
     space_id = os.getenv("SPACE_ID")
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Local Development"
-    
+    if profile:
+        username = f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        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"
-    
+
     try:
-        agent = BasicAgent()  # Make sure your CSV file is named "embeddings.csv" or update the path
+        agent = GAIAAgent()
     except Exception as e:
-        print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    
-    # Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+
     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
-        
         print(f"Fetched {len(questions_data)} questions.")
     except Exception as e:
-        print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
-    
+
     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
-            })
-            print(f"Completed task {task_id}: {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}"
-            })
-    
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+
     if not answers_payload:
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-    
-    submission_data = {
-        "username": username.strip(), 
-        "agent_code": agent_code, 
-        "answers": answers_payload
-    }
-    
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     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"User: {result_data.get('username')}\n"
@@ -125,56 +121,57 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             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.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-        
+        return final_status, pd.DataFrame(results_log)
     except Exception as e:
-        print(f"Submission failed: {e}")
-        status_message = f"Submission Failed: {e}"
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
+# --- Gradio UI ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Agent Evaluation Runner")
+
     gr.Markdown("""
-        **Instructions:**
-        1. Make sure your `embeddings.csv` file is in the same directory
-        2. Log in to your Hugging Face account using the button below
-        3. Click 'Run Evaluation & Submit All Answers' to start the evaluation
-        
-        **Note:** The evaluation process may take several minutes depending on the number of questions.
+    **Instructions:**
+    1. Clone this space and modify the agent logic as needed.
+    2. Log in to Hugging Face to associate your submission.
+    3. Click the button below to fetch questions, run your agent, and submit results.
     """)
-    
+
     gr.LoginButton()
-    
-    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
+
+    gr.Markdown("## 🔍 Try a Question Preview")
+    preview_input = gr.Textbox(label="Your GAIA-style question")
+    preview_output = gr.Textbox(label="Agent's Response", lines=2)
+    preview_button = gr.Button("Preview Answer")
+    preview_button.click(lambda q: GAIAAgent()(q), inputs=preview_input, outputs=preview_output)
+
+    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]
     )
 
+# --- Main Entry ---
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    
-    space_host = os.getenv("SPACE_HOST")
-    space_id = os.getenv("SPACE_ID")
-    
-    if space_host:
-        print(f"✅ SPACE_HOST found: {space_host}")
-        print(f"   Runtime URL: https://{space_host}.hf.space")
+    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")
+    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("ℹ️  Running locally")
-    
-    if space_id:
-        print(f"✅ SPACE_ID found: {space_id}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id}")
-    
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
     print("-"*(60 + len(" App Starting ")) + "\n")
-    print("Launching Gradio Interface...")
-    
-    demo.launch(debug=True, share=False)
+    print("Launching Gradio Interface for GAIA Agent Evaluation...")
+    demo.launch(debug=True, share=False)