Update app.py

app.py

@@ -1,196 +1,320 @@
 import os
+import re
+import json
+import tempfile
+from pathlib import Path
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
+
+from smolagents import CodeAgent, tool
+from smolagents import DuckDuckGoSearchTool, VisitWebpageTool
+from smolagents import OpenAIServerModel
+
 
-# (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:
-    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):
+
+@tool
+def get_task_file_url(task_id: str) -> str:
+    """
+    Returns the download URL for the file attached to a GAIA task.
+
+    Args:
+        task_id: The GAIA task id.
+
+    Returns:
+        Direct URL to the attached file for this task.
+    """
+    return f"{DEFAULT_API_URL}/files/{task_id}"
+
+
+@tool
+def download_file(url: str) -> str:
+    """
+    Downloads a file from a URL to a temporary local path and returns that path.
+
+    Args:
+        url: The file URL.
+
+    Returns:
+        Local file path as a string.
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    suffix = ""
+    match = re.search(r"\.([a-zA-Z0-9]{1,6})(?:\?|$)", url)
+    if match:
+        suffix = "." + match.group(1)
+
+    fd, temp_path = tempfile.mkstemp(suffix=suffix)
+    os.close(fd)
+
+    r = requests.get(url, timeout=60)
+    r.raise_for_status()
+
+    with open(temp_path, "wb") as f:
+        f.write(r.content)
+
+    return temp_path
+
+
+@tool
+def inspect_local_text_file(path: str, max_chars: int = 12000) -> str:
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    Reads a local text-like file and returns a preview.
 
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
+    Args:
+        path: Local file path.
+        max_chars: Max number of characters to return.
+
+    Returns:
+        Text preview.
+    """
+    p = Path(path)
+    try:
+        return p.read_text(encoding="utf-8", errors="ignore")[:max_chars]
+    except Exception as e:
+        return f"Could not read text file: {e}"
+
+
+@tool
+def analyze_spreadsheet(path: str, instruction: str) -> str:
+    """
+    Loads an Excel/CSV spreadsheet with pandas and executes a constrained analysis
+    instruction by giving the LLM a schema + preview.
+
+    Args:
+        path: Local spreadsheet path.
+        instruction: What to compute.
+
+    Returns:
+        JSON string with columns, preview, dtypes, shape.
+    """
+    p = Path(path)
+    if p.suffix.lower() in [".csv", ".tsv"]:
+        sep = "\t" if p.suffix.lower() == ".tsv" else ","
+        df = pd.read_csv(path, sep=sep)
     else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        df = pd.read_excel(path)
+
+    payload = {
+        "instruction": instruction,
+        "shape": list(df.shape),
+        "columns": list(df.columns),
+        "dtypes": {c: str(t) for c, t in df.dtypes.items()},
+        "head": df.head(8).to_dict(orient="records"),
+        "numeric_column_sums": {
+            c: float(df[c].sum())
+            for c in df.select_dtypes(include="number").columns
+        },
+    }
+    return json.dumps(payload, ensure_ascii=False)
+
+
+@tool
+def python_compute(code: str) -> str:
+    """
+    Executes trusted short Python snippets for local analysis.
+
+    Args:
+        code: Python code. Must assign the final value to a variable named `result`.
+
+    Returns:
+        Stringified result.
+    """
+    local_vars = {}
+    global_vars = {
+        "pd": pd,
+        "Path": Path,
+        "json": json,
+        "re": re,
+    }
+
+    exec(code, global_vars, local_vars)
+
+    if "result" not in local_vars:
+        return "ERROR: code did not define variable `result`"
+    return str(local_vars["result"])
+
+
+def clean_final_answer(text: str) -> str:
+    if text is None:
+        return ""
 
+    answer = str(text).strip()
+    answer = re.sub(r"^```.*?\n", "", answer, flags=re.DOTALL)
+    answer = answer.replace("```", "").strip()
+    answer = re.sub(r"^(FINAL ANSWER\s*:\s*)", "", answer, flags=re.IGNORECASE)
+    answer = re.sub(r"^(Answer\s*:\s*)", "", answer, flags=re.IGNORECASE)
+    answer = re.sub(r"[ \t]+", " ", answer).strip()
+
+    return answer
+
+
+SYSTEM_PROMPT = """
+You are solving GAIA-style benchmark tasks.
+
+Rules:
+- You may use tools.
+- If the task includes a file, use the file tools.
+- If the task asks for a web fact, search and verify.
+- For spreadsheet/math/data tasks, compute carefully.
+- For exact-match scoring, your final output must be ONLY the answer and nothing else.
+- Do not include explanations in your final answer.
+- Do not include the words FINAL ANSWER.
+- When a question requests a format (comma-separated list, USD with two decimals, single word, date, etc.),
+  obey that exact format.
+- If the answer is numeric and the prompt requests decimals, format correctly.
+"""
+
+
+class GaiaAgent:
+    def __init__(self):
+        api_key = os.environ.get("OPENAI_API_KEY")
+        if not api_key:
+            raise ValueError("Missing OPENAI_API_KEY secret.")
+
+        model_id = os.environ.get("OPENAI_MODEL", "gpt-4o-mini")
+
+        self.model = OpenAIServerModel(
+            model_id=model_id,
+            api_base="https://api.openai.com/v1",
+            api_key=api_key,
+            temperature=0.1,
+            max_tokens=1200,
+        )
+
+        self.agent = CodeAgent(
+            model=self.model,
+            tools=[
+                DuckDuckGoSearchTool(),
+                VisitWebpageTool(),
+                get_task_file_url,
+                download_file,
+                inspect_local_text_file,
+                analyze_spreadsheet,
+                python_compute,
+            ],
+            add_base_tools=False,
+            max_steps=10,
+            system_prompt=SYSTEM_PROMPT,
+        )
+
+    def __call__(self, question: str, task_id: str) -> str:
+        full_prompt = f"""
+Task ID: {task_id}
+
+Question:
+{question}
+
+Important:
+- If there is an attached file, its URL can be obtained using get_task_file_url(task_id).
+- Return only the final answer.
+"""
+        raw = self.agent.run(full_prompt)
+        return clean_final_answer(raw)
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+
+    if not profile:
+        return "Please Login to Hugging Face first.", None
+
+    username = profile.username
     api_url = DEFAULT_API_URL
     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(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
+        r = requests.get(questions_url, timeout=30)
+        r.raise_for_status()
+        questions_data = r.json()
     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
     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}")
+
+        if not task_id or not question_text:
             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})
+            submitted_answer = agent(question_text, task_id)
         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}"})
+            submitted_answer = f"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)
+        answers_payload.append(
+            {
+                "task_id": task_id,
+                "submitted_answer": submitted_answer,
+            }
+        )
 
-    # 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)
+        results_log.append(
+            {
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": submitted_answer,
+            }
+        )
+
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
 
-    # 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()
+        r = requests.post(submit_url, json=submission_data, timeout=120)
+        r.raise_for_status()
+        result_data = r.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.')}"
+            f"Message: {result_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 final_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 ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Unit 4 GAIA Agent")
     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. Add your API key as a Space Secret: `OPENAI_API_KEY`
+2. Optional: set `OPENAI_MODEL`
+3. Login with Hugging Face
+4. Click run
+"""
     )
 
     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
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=6, 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]
+        outputs=[status_output, results_table],
     )
 
-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)
+if __name__ == "__main__":
+    demo.launch(debug=True)