Add LangGraph + Groq ReAct agent for GAIA benchmark

Replace placeholder BasicAgent with LangGraph ReAct agent using Groq
(llama-3.1-70b-versatile). Tools: DuckDuckGo, Wikipedia, Python REPL,
GAIA file fetcher. System prompt enforces exact-match answer format.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app.py

@@ -1,34 +1,81 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from langchain_groq import ChatGroq
+from langgraph.prebuilt import create_react_agent
+from langchain_community.tools import DuckDuckGoSearchRun, WikipediaQueryRun
+from langchain_community.utilities import WikipediaAPIWrapper
+from langchain_experimental.tools import PythonREPLTool
+from langchain.tools import tool
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+SYSTEM_PROMPT = """You are a general AI assistant tasked with answering questions accurately.
+
+Reason step by step, then finish your answer with exactly this format:
+FINAL ANSWER: [your answer]
+
+Rules for FINAL ANSWER:
+- Numbers: no commas, no units unless specified
+- Strings: no articles (a/an/the), no abbreviations, write digits in plain text
+- Lists: comma-separated, apply above rules per element
+- Be precise and concise — the answer is evaluated by exact match"""
+
+
+@tool
+def fetch_task_file(task_id: str) -> str:
+    """Fetch a file associated with a GAIA task by its task_id. Use this when the question references an attachment, file, or additional data."""
+    try:
+        response = requests.get(f"{DEFAULT_API_URL}/files/{task_id}", timeout=15)
+        if response.status_code == 200:
+            content_type = response.headers.get("content-type", "")
+            if any(t in content_type for t in ["text", "json", "csv", "xml"]):
+                return response.text[:8000]
+            return f"Binary file ({content_type}) — cannot read as text"
+        return "No file found for this task"
+    except Exception as e:
+        return f"Error fetching file: {e}"
+
+
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
-    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
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+        llm = ChatGroq(model="llama-3.1-70b-versatile", temperature=0)
+        tools = [
+            DuckDuckGoSearchRun(),
+            WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(top_k_results=3)),
+            PythonREPLTool(),
+            fetch_task_file,
+        ]
+        self.agent = create_react_agent(llm, tools, state_modifier=SYSTEM_PROMPT)
+        print("BasicAgent initialized with LangGraph + Groq (llama-3.1-70b-versatile).")
+
+    def __call__(self, question: str, task_id: str = "") -> str:
+        full_question = f"[Task ID: {task_id}]\n\n{question}" if task_id else question
+        print(f"Running agent on task {task_id}: {question[:80]}...")
+        result = self.agent.invoke(
+            {"messages": [("user", full_question)]},
+            {"recursion_limit": 50},
+        )
+        raw_answer = result["messages"][-1].content
+        if "FINAL ANSWER:" in raw_answer:
+            answer = raw_answer.split("FINAL ANSWER:")[-1].strip()
+        else:
+            answer = raw_answer.strip()
+        print(f"Answer for {task_id}: {answer}")
+        return answer
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent 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}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,13 +85,13 @@ 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)
+    # 1. Instantiate Agent
     try:
         agent = BasicAgent()
     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)
 
@@ -55,21 +102,21 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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("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
+        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
+    # 3. Run Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -80,23 +127,22 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, task_id)
             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}"})
+            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 
+    # 4. Submit
     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)
@@ -110,8 +156,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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 requests.exceptions.HTTPError as e:
         error_detail = f"Server responded with status {e.response.status_code}."
         try:
@@ -121,40 +166,36 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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
+        return status_message, pd.DataFrame(results_log)
     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
+        return status_message, pd.DataFrame(results_log)
     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
+        return status_message, pd.DataFrame(results_log)
     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
+        return status_message, pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Agent Evaluation Runner — LangGraph + Groq")
     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.
+        1. Log in to your Hugging Face account using the button below.
+        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the agent, and submit.
+
+        **Agent:** LangGraph ReAct agent with Groq (llama-3.1-70b-versatile)
+        **Tools:** DuckDuckGo search, Wikipedia, Python REPL, File fetcher
 
         ---
-        **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.
+        *Note: Running 20 questions takes several minutes.*
         """
     )
 
@@ -163,7 +204,6 @@ with gr.Blocks() as demo:
     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(
@@ -172,25 +212,21 @@ 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
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     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}")
         print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
     else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+        print("ℹ️  SPACE_HOST 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("ℹ️  SPACE_ID not found (running locally?).")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    print("-" * (60 + len(" App Starting ")) + "\n")
+    demo.launch(debug=True, share=False)

requirements.txt

@@ -1,2 +1,10 @@
 gradio
-requests
+requests
+pandas
+langchain-groq
+langgraph
+langchain-community
+langchain-experimental
+langchain
+duckduckgo-search
+wikipedia