First attempt

app.py

@@ -4,28 +4,72 @@ import requests
 import inspect
 import pandas as pd
 
-# (Keep Constants as is)
+# Import necessary libraries for LangChain Agent
+from langchain_huggingface import HuggingFaceEndpoint # NEW IMPORT!
+from langchain.agents import AgentExecutor, create_react_agent
+from langchain import hub
+# Removed from langchain.tools import tool, as SerpAPIWrapper is a direct tool
+from langchain_community.utilities import SerpAPIWrapper
+
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
+# --- LangChain Agent Definition ---
+class GAIAAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("GAIAAgent initialized using LangChain.")
+
+        repo_id = "mistralai/Mistral-7B-Instruct-v0.3" 
+
+        self.llm = HuggingFaceEndpoint(
+            endpoint_url=f"https://api-inference.huggingface.co/models/{repo_id}", # Explicitly set endpoint URL
+            temperature=0.1, # Directly pass model parameters
+            max_new_tokens=512, # Directly pass model parameters (common for generation)
+            huggingfacehub_api_token=os.getenv("HUGGINGFACEHUB_API_TOKEN") # Env var name is correct
+        )
+
+        # Define tools for the agent
+        self.tools = []
+
+        # Initialize SerpAPIWrapper tool
+        # It will automatically pick up SERPAPI_API_KEY from environment variables
+        self.serpapi_tool = SerpAPIWrapper()
+
+        # Define a LangChain tool function that uses the SerpAPIWrapper
+        # The description is crucial for the LLM to know when to use this tool
+        from langchain.tools import Tool # Re-import Tool if needed for explicit wrapping
+        web_search_tool = Tool(
+            name="Serpapi Search",
+            description="useful for when you need to answer questions about current events or facts. Input should be a search query.",
+            func=self.serpapi_tool.run,
+        )
+        self.tools.append(web_search_tool)
+
+        self.prompt = hub.pull("hwchase17/react")
+
+        self.agent = create_react_agent(self.llm, self.tools, self.prompt)
+
+        self.agent_executor = AgentExecutor(agent=self.agent, tools=self.tools, verbose=True, handle_parsing_errors=True)
+
+
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        try:
+            response = self.agent_executor.invoke({"input": question})
+            agent_answer = response["output"]
+            print(f"Agent returning answer: {agent_answer}")
+            return agent_answer
+        except Exception as e:
+            print(f"Error during agent execution: {e}")
+            return f"An error occurred while processing your request: {e}. Please ensure API keys are set correctly."
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the GAIAAgent on them, submits all answers,
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
         username= f"{profile.username}"
@@ -38,132 +82,85 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = GAIAAgent()
     except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+        return f"Failed to initialize agent: {e}", None
+
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = requests.get(questions_url)
         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.")
+        questions = questions_data # Assume questions_data is directly the list of questions
+        print(f"Fetched {len(questions)} 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}")
+        return f"Failed to fetch questions: {e}", None
+
+    all_answers = []
+    results_for_display = []
+
+    for q_data in questions:
+        q_id = q_data.get("task_id") # Use 'task_id' as per the data
+        q_text = q_data.get("question")
+        if not q_id or not q_text:
+            print(f"Skipping malformed question data: {q_data}")
             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)
+        print(f"\n--- Processing Question ID: {q_id} ---")
+        agent_answer = agent(q_text)
+
+        all_answers.append({"task_id": q_id, "submitted_answer": agent_answer}) 
+        results_for_display.append({"Question ID": q_id, "Question": q_text, "Agent Answer": agent_answer})
+
+    results_df = pd.DataFrame(results_for_display)
 
-    # 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)
+    submission_data = {
+        "answers": all_answers,
+        "space_id": space_id, # Include SPACE_ID for the leaderboard link
+        "username": username, # Add the username here
+        "agent_code": inspect.getsource(GAIAAgent), # Add agent code (for debugging on leaderboard)
+    }
 
-    # 5. Submit
-    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"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.")
-        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)
+        print(f"\nSubmitting {len(all_answers)} answers to {submit_url}...")
+        submit_response = requests.post(submit_url, json=submission_data)
+        submit_response.raise_for_status()
+        submission_result = submit_response.json()
+        print("Submission successful!")
+        print(f"Submission Result: {submission_result}")
+
+        score = submission_result.get("score", "N/A")
+        leaderboard_link = submission_result.get("leaderboard_link", "")
+        status_message = f"Evaluation complete! Your score: {score:.2f}%\n"
+        if leaderboard_link:
+            status_message += f"Check the leaderboard: {leaderboard_link}\n"
+        else:
+            status_message += "No leaderboard link provided."
+
         return status_message, results_df
 
+    except requests.exceptions.RequestException as e:
+        error_message = f"Failed to submit answers: {e}"
+        if hasattr(e, 'response') and e.response is not None:
+            error_message += f"\nResponse: {e.response.text}"
+        print(error_message)
+        return error_message, results_df
 
-# --- Build Gradio Interface using Blocks ---
+# (Keep Gradio UI setup as is)
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
-        """
-        **Instructions:**
-
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
-        ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-        """
-    )
+    """
+    # Unit 4: Agentic AI for GAIA Benchmark
 
+    This Gradio app allows you to run your agent against the GAIA benchmark questions and submit your answers.
+    Your goal is to modify the `GAIAAgent` class in `app.py` to achieve a score above 30%.
+    """
+    )
     gr.LoginButton()
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -173,9 +170,8 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,14 +179,10 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+        print("ℹ️  SPACE_ID environment variable not found...")
+    demo.launch()

requirements.txt

@@ -1,2 +1,90 @@
-gradio
-requests
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.13
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.9.0
+attrs==25.3.0
+Authlib==1.6.0
+certifi==2025.6.15
+cffi==1.17.1
+charset-normalizer==3.4.2
+click==8.2.1
+cryptography==45.0.4
+dataclasses-json==0.6.7
+fastapi==0.115.13
+ffmpy==0.6.0
+filelock==3.18.0
+frozenlist==1.7.0
+fsspec==2025.5.1
+google_search_results==2.4.2
+gradio==5.34.2
+gradio_client==1.10.3
+greenlet==3.2.3
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.5
+httpcore==1.0.9
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.33.0
+idna==3.10
+itsdangerous==2.2.0
+Jinja2==3.1.6
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.26
+langchain-community==0.3.26
+langchain-core==0.3.66
+langchain-huggingface==0.3.0
+langchain-text-splitters==0.3.8
+langsmith==0.4.1
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+multidict==6.5.0
+mypy_extensions==1.1.0
+numpy==2.3.1
+orjson==3.10.18
+packaging==24.2
+pandas==2.3.0
+pillow==11.2.1
+propcache==0.3.2
+pycparser==2.22
+pydantic==2.11.7
+pydantic-settings==2.10.0
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+requests==2.32.4
+requests-toolbelt==1.0.0
+rich==14.0.0
+ruff==0.12.0
+safehttpx==0.1.6
+semantic-version==2.10.0
+serpapi==0.1.5
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+SQLAlchemy==2.0.41
+starlette==0.46.2
+tenacity==9.1.2
+tokenizers==0.21.1
+tomlkit==0.13.3
+tqdm==4.67.1
+typer==0.16.0
+typing-inspect==0.9.0
+typing-inspection==0.4.1
+typing_extensions==4.14.0
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.34.3
+websockets==15.0.1
+yarl==1.20.1
+zstandard==0.23.0