code update

README.md

@@ -1,5 +1,5 @@
 ---
-title: Template Final Assignment
+title: GAIA Agent Final Assignment
 emoji: 🕵🏻‍♂️
 colorFrom: indigo
 colorTo: indigo
@@ -8,8 +8,17 @@ sdk_version: 5.25.2
 app_file: app.py
 pinned: false
 hf_oauth: true
-# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
-hf_oauth_expiration_minutes: 480
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# GAIA Agent — smolagents + Claude Sonnet
+
+Final assignment for the HuggingFace Agents Course (Unit 4).
+
+Uses `smolagents.CodeAgent` with Anthropic Claude Sonnet via LiteLLM to answer GAIA Level 1 benchmark questions.
+
+## Setup
+
+1. Duplicate this Space to your HF account
+2. Add secret `ANTHROPIC_API_KEY` in Space Settings → Secrets
+3. Click "Run Evaluation & Submit All Answers"
+4. Score ≥30% → claim your certificate

app.py

@@ -1,196 +1,175 @@
 import os
+import io
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    LiteLLMModel,
+    Tool,
+    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 ------
-class BasicAgent:
+
+# --- Custom Tool: Read task files from GAIA API ---
+class TaskFileReaderTool(Tool):
+    name = "task_file_reader"
+    description = (
+        "Downloads and reads a file attached to a GAIA task by its task_id. "
+        "Use this when the question mentions an attached file, document, spreadsheet, or image."
+    )
+    inputs = {
+        "task_id": {
+            "type": "string",
+            "description": "The task_id to download the file for.",
+        }
+    }
+    output_type = "string"
+
+    def forward(self, task_id: str) -> str:
+        try:
+            r = requests.get(f"{DEFAULT_API_URL}/files/{task_id}", timeout=30)
+            r.raise_for_status()
+            ct = r.headers.get("Content-Type", "")
+            if "text" in ct or "json" in ct or "csv" in ct:
+                return r.text[:10000]
+            elif "spreadsheet" in ct or "excel" in ct:
+                df = pd.read_excel(io.BytesIO(r.content))
+                return df.to_string()
+            else:
+                try:
+                    return r.text[:10000]
+                except Exception:
+                    return f"[Binary file, {len(r.content)} bytes, type: {ct}]"
+        except Exception as e:
+            return f"Error downloading file for task {task_id}: {e}"
+
+
+# --- Agent Definition ---
+class GAIAAgent:
     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):
-    """
-    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
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
+        api_key = os.getenv("ANTHROPIC_API_KEY")
+        if not api_key:
+            raise ValueError("Set ANTHROPIC_API_KEY env var")
+
+        model = LiteLLMModel(
+            model_id="anthropic/claude-sonnet-4-20250514",
+            api_key=api_key,
+        )
+
+        self.agent = CodeAgent(
+            tools=[DuckDuckGoSearchTool(), TaskFileReaderTool()],
+            model=model,
+            max_steps=8,
+            verbosity_level=1,
+            additional_authorized_imports=[
+                "re", "json", "math", "collections",
+                "itertools", "statistics", "unicodedata",
+            ],
+        )
+        print("GAIAAgent initialized with Claude Sonnet.")
+
+    def __call__(self, question: str, task_id: str = None) -> str:
+        prompt = (
+            f"Question: {question}\n\n"
+            f"INSTRUCTIONS:\n"
+            f"- If the question references an attached file, use task_file_reader with task_id='{task_id}'.\n"
+            f"- Use web_search to find factual information when needed.\n"
+            f"- Give ONLY the exact final answer. No explanation, no 'The answer is', no extra words.\n"
+            f"- For numbers: just the number. For names: just the name. For lists: comma-separated.\n"
+        )
+        try:
+            result = self.agent.run(prompt)
+            answer = str(result).strip()
+            for prefix in ["The answer is ", "Answer: ", "FINAL ANSWER: ", "Final answer: "]:
+                if answer.lower().startswith(prefix.lower()):
+                    answer = answer[len(prefix):].strip()
+            return answer
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return "Unable to determine answer"
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+    if not profile:
         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"
+    username = profile.username
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Init 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}")
+    # 2. Fetch questions
     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
+        resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
+        resp.raise_for_status()
+        questions_data = resp.json()
         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
+        return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # 3. Run agent
     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):
         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"\n--- Q{i+1}/{len(questions_data)} [{task_id}] ---")
+        print(f"Q: {question_text[:120]}")
         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})
+            answer = agent(question_text, task_id=task_id)
+            print(f"A: {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}"})
+            answer = f"ERROR: {e}"
+            print(f"Error: {e}")
+        answers_payload.append({"task_id": task_id, "submitted_answer": answer})
+        results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": 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)
-
-    # 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)
+        return "No answers produced.", pd.DataFrame(results_log)
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # 4. Submit
+    submission = {"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 = (
+        resp = requests.post(f"{DEFAULT_API_URL}/submit", json=submission, timeout=120)
+        resp.raise_for_status()
+        data = resp.json()
+        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.')}"
+            f"User: {data.get('username')}\n"
+            f"Score: {data.get('score', 'N/A')}% "
+            f"({data.get('correct_count', '?')}/{data.get('total_attempted', '?')} correct)\n"
+            f"Message: {data.get('message', '')}"
         )
-        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
+        return status, 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 f"Submission Failed: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio UI ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Agent — smolagents + Claude Sonnet")
     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.
-        """
+        "1. Log in with HuggingFace\n"
+        "2. Click 'Run Evaluation & Submit'\n"
+        "3. Wait for the agent to answer all 20 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)
-    # Removed max_rows=10 from DataFrame constructor
-    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("Run Evaluation & Submit All Answers")
+    status_box = gr.Textbox(label="Status", lines=5, interactive=False)
+    results_tbl = gr.DataFrame(label="Results", wrap=True)
+    run_btn.click(fn=run_and_submit_all, outputs=[status_box, results_tbl])
 
 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
-
-    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 repo URLs if SPACE_ID is found
-        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)
+    demo.launch(debug=True, share=False)

requirements.txt

@@ -1,2 +1,9 @@
+smolagents
+litellm
 gradio
-requests
+requests
+pandas
+ddgs
+markdownify
+requests
+openpyxl