Update app.py

app.py

@@ -1,34 +1,135 @@
+import spaces  # must be the first import — required by ZeroGPU Spaces
+
 import os
+import tempfile
+from pathlib import Path
+from typing import Optional
+
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
+from smolagents import CodeAgent, InferenceClientModel
+
 # --- 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:
+# This Space's free-tier hardware is ZeroGPU, which refuses to start unless
+# at least one function is decorated with @spaces.GPU. The agent itself never
+# touches a GPU (it only calls HF Inference Providers over HTTP), so this
+# function exists purely to satisfy that startup check and is never called.
+@spaces.GPU
+def _zerogpu_startup_check():
+    return None
+
+# Instructions appended to every question so the CodeAgent behaves like a
+# GAIA-solving agent rather than a free-form chatbot. Kept as plain task
+# framing (not a tool) to avoid adding moving parts.
+TASK_RULES = """
+Rules:
+1. Think step by step. Break multi-part questions into sub-steps before acting.
+2. Use web search for anything requiring current facts, names, dates, or
+   information you are not already certain of. Never invent facts or sources.
+3. Use Python (you write code as your actions) for arithmetic, counting,
+   sorting, filtering, or any data processing rather than doing it in your head.
+4. If an attachment path is given below, open and inspect it with Python
+   before answering — never guess its contents.
+5. Where practical, verify an important intermediate result a second way
+   before finalizing.
+6. Call final_answer(...) with ONLY the exact value requested:
+   - a bare number (no commas, no units unless the question asks for units)
+   - a bare string (no "The answer is", no trailing period, no quotes)
+   - a comma-separated list only if asked for a list, formatted exactly as
+     requested (spacing, order, etc.)
+   Do not include your reasoning or the words "FINAL ANSWER" in that value.
+"""
+
+MAX_STEPS = 10
+ADDITIONAL_IMPORTS = [
+    "pandas", "numpy", "csv", "json", "re", "math", "statistics",
+    "datetime", "itertools", "collections", "io", "os", "pypdf", "openpyxl",
+]
+
+
+class GAIAAgent:
+    """
+    Wraps a smolagents CodeAgent for GAIA-style questions: general reasoning,
+    Python for calculation/data processing, web search, and local-file
+    inspection when a question ships an attachment.
+    """
+
     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):
+        hf_token = os.environ.get("HF_TOKEN")
+        model_id = os.environ.get("GAIA_MODEL_ID")  # optional override
+
+        model_kwargs = {}
+        if hf_token:
+            model_kwargs["token"] = hf_token
+        if model_id:
+            model_kwargs["model_id"] = model_id
+        model = InferenceClientModel(**model_kwargs)
+
+        self.agent = CodeAgent(
+            tools=[],
+            model=model,
+            add_base_tools=True,  # gives web search + python interpreter + friends
+            additional_authorized_imports=ADDITIONAL_IMPORTS,
+            max_steps=MAX_STEPS,
+        )
+        print("GAIAAgent initialized (smolagents CodeAgent).")
+
+    def __call__(self, question: str, file_path: Optional[str] = None) -> str:
+        task = question + "\n\n" + TASK_RULES
+        if file_path:
+            task += (
+                f"\nAn attachment for this task was downloaded to this local "
+                f"path: {file_path}\nOpen it with Python and inspect its "
+                f"contents before answering.\n"
+            )
+        raw_answer = self.agent.run(task)
+        return clean_final_answer(raw_answer)
+
+
+def clean_final_answer(raw) -> str:
+    """Light, conservative cleanup only — no aggressive normalization that
+    could alter a valid exact-match answer."""
+    text = str(raw).strip()
+    if len(text) >= 2 and text[0] == text[-1] and text[0] in "\"'":
+        text = text[1:-1].strip()
+    for prefix in ("FINAL ANSWER:", "Final answer:", "Answer:", "answer:"):
+        if text.startswith(prefix):
+            text = text[len(prefix):].strip()
+    return text
+
+
+def download_task_file(api_url: str, task_id: str, file_name: str) -> Optional[str]:
+    """Downloads the attachment for a task via the existing /files/{task_id}
+    endpoint. Returns a local path, or None if there's no file or the
+    download fails (failure here must not crash the whole run)."""
+    if not file_name:
+        return None
+    try:
+        resp = requests.get(f"{api_url}/files/{task_id}", timeout=30)
+        resp.raise_for_status()
+        out_dir = Path(tempfile.gettempdir()) / "gaia_files"
+        out_dir.mkdir(exist_ok=True)
+        out_path = out_dir / file_name
+        out_path.write_bytes(resp.content)
+        return str(out_path)
+    except Exception as e:
+        print(f"Could not download file for task {task_id}: {e}")
+        return None
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetches all questions, runs the GAIAAgent on them (downloading any
+    attachment first), 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.")
@@ -38,65 +139,66 @@ 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}")
     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("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
     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")
+        file_name = item.get("file_name")
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
+
+        file_path = None
+        if file_name:
+            file_path = download_task_file(api_url, task_id, file_name)
+
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, file_path=file_path)
             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 
     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)
@@ -146,15 +248,14 @@ with gr.Blocks() as demo:
     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,
+           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.
+        This can take a while — the agent works through each GAIA question in turn,
+        calling the model and, when needed, web search or Python execution.
         """
     )
 
@@ -163,7 +264,6 @@ 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 +272,24 @@ 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 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("ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("-" * (60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)