Update app.py

app.py

@@ -1,213 +1,243 @@
 import os
-import re
-import json
-import textwrap
+import gradio as gr
 import requests
+import inspect
 import pandas as pd
+
+# 👇 NEW imports (added only what’s needed)
 import torch
-import gradio as gr
+import re
+import textwrap
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# ---------------- Constants ----------------
+# (Keep Constants as is)
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-
-# ---------------- Agent Definition ----------------
+# --- Basic Agent Definition ---
+# ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
-    """
-    Local small LLM answering strictly in the GAIA Unit 4 format:
-    Uses the official system prompt and outputs `FINAL ANSWER: <answer>`.
-    """
-
     def __init__(self):
+        # ✅ Load a small, CPU-friendly model
         model_id = "microsoft/Phi-3-mini-4k-instruct"
         print(f"🚀 Loading model locally: {model_id}")
         self.tokenizer = AutoTokenizer.from_pretrained(model_id)
         self.model = AutoModelForCausalLM.from_pretrained(
             model_id,
-            torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+            torch_dtype=torch.float32,  # safe for CPU
             device_map="auto",
         )
-        print("✅ Local model ready.")
+        print("✅ Model ready.")
 
-    def _clean_final_answer(self, text: str) -> tuple[str, str]:
-        """
-        Extracts and cleans the 'FINAL ANSWER' part, and also returns the reasoning trace.
-        """
-        reasoning_trace = text.strip()
+    def _extract_final_answer(self, text: str) -> str:
+        """Extracts text after 'FINAL ANSWER:' if present."""
         match = re.search(r"FINAL ANSWER\s*[:\-]?\s*(.*)", text, re.IGNORECASE | re.DOTALL)
         if match:
-            final_answer = match.group(1)
-        else:
-            final_answer = text
-        # Basic normalization for exact match scoring
-        final_answer = final_answer.strip("`'\" \t\n\r. ")
-        return final_answer, reasoning_trace
-
-    def __call__(self, question: str) -> dict:
-        print(f"🧠 Processing question: {question[:80]}...")
-        system_prompt = textwrap.dedent(f"""
-        You are a general AI assistant. I will ask you a question.
-        Report your thoughts, and finish your answer with the following template:
-        FINAL ANSWER: [YOUR FINAL ANSWER].
+            return match.group(1).strip("`'\" \t\n\r.")
+        return text.strip()
 
-        YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
-        If you are asked for a number, don't use commas or units.
-        If you are asked for a string, don't use articles or abbreviations.
-        If you are asked for a list, apply the above format for each element.
+    def __call__(self, question: str) -> str:
+        print(f"🧠 Agent received question (first 50 chars): {question[:50]}...")
+
+        # Instruction to produce a clean final answer
+        system_prompt = textwrap.dedent(f"""
+        You are a helpful AI assistant.
+        Think step by step and end with:
+        FINAL ANSWER: <your concise answer>
 
         Question: {question}
         """).strip()
 
+        # Tokenize and generate
         inputs = self.tokenizer(system_prompt, return_tensors="pt").to(self.model.device)
         with torch.no_grad():
             outputs = self.model.generate(
                 **inputs,
-                max_new_tokens=100,
-                temperature=0.0,       # deterministic
-                do_sample=False,       # no randomness
+                max_new_tokens=128,
+                temperature=0.0,
+                do_sample=False,
                 pad_token_id=self.tokenizer.eos_token_id,
             )
 
-        generated_ids = outputs[0][inputs["input_ids"].shape[1]:]
-        raw_output = self.tokenizer.decode(generated_ids, skip_special_tokens=True)
-        model_answer, reasoning = self._clean_final_answer(raw_output)
-        print(f"💡 Raw: '{raw_output[:80]}' → Final answer: '{model_answer}'")
-        return {"model_answer": model_answer, "reasoning_trace": reasoning}
+        # Decode and extract
+        generated = self.tokenizer.decode(
+            outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True
+        )
+        final_answer = self._extract_final_answer(generated)
+        print(f"💡 Model raw: '{generated[:80]}' → Final answer: '{final_answer}'")
+        return final_answer
 
 
-# ---------------- API Utilities ----------------
-def fetch_questions() -> list[dict]:
-    """Fetch all evaluation questions from the API."""
-    try:
-        resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=60)
-        resp.raise_for_status()
-        data = resp.json()
-        if isinstance(data, list):
-            print(f"✅ Retrieved {len(data)} questions from API.")
-            return data
-    except Exception as e:
-        print(f"❌ Error fetching questions: {e}")
-    return []
+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.")
+        return "Please Login to Hugging Face with the button.", None
 
-def submit_answers(username: str, code_link: str, answers: list[dict], token: str) -> dict:
-    """Submit answers in GAIA JSON-lines format."""
-    payload = {
-        "username": username,
-        "agent_code": code_link,
-        "answers": [{"task_id": a["task_id"], "submitted_answer": a["model_answer"]} for a in answers],
-    }
-    headers = {"Authorization": f"Bearer {token}"} if token else {}
+    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:
-        resp = requests.post(f"{DEFAULT_API_URL}/submit", json=payload, headers=headers, timeout=90)
-        resp.raise_for_status()
-        print("✅ Submission successful.")
-        return resp.json()
+        agent = BasicAgent()
     except Exception as e:
-        print(f"❌ Submission failed: {e}")
-        return {"success": False, "message": str(e)}
-
-
-# ---------------- Main Pipeline ----------------
-def run_and_submit_all(profile: gr.OAuthProfile | None = None, *_):
-    # 1️⃣ Identify username
-    username = profile.name if profile and hasattr(profile, "name") else os.getenv("HF_USERNAME", "anonymous")
-    print(f"👤 Submitting as: {username}")
-
-    # 2️⃣ Load token from env secret
-    token = os.getenv("HF_TOKEN")
-    if not token:
-        return (
-            "❌ Missing Hugging Face token. Add a secret named `HF_TOKEN` in your Space → Settings → Repository secrets.",
-            pd.DataFrame(),
-        )
+        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
+    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}")
+            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}"})
 
-    # 3️⃣ Prepare agent_code link (as required by API)
-    space_id = os.getenv("SPACE_ID", "")
-    code_link = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "unknown"
+    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)
 
-    # 4️⃣ Fetch questions
-    questions = fetch_questions()
-    if not questions:
-        return "❌ Could not fetch questions from API.", pd.DataFrame()
+    # 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)
 
-    # 5️⃣ Run model locally
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        agent = BasicAgent()
-    except Exception as e:
-        return f"❌ Model initialization error: {e}", pd.DataFrame()
-
-    results = []
-    for q in questions:
-        task_id = q.get("task_id")
-        text = q.get("question", "")
+        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:
-            res = agent(text)
-        except Exception as e:
-            res = {"model_answer": f"[Error: {e}]", "reasoning_trace": ""}
-        res["task_id"] = task_id
-        results.append(res)
-
-    # 6️⃣ Build display DataFrame
-    df = pd.DataFrame(results)
-
-    # 7️⃣ Submit
-    submission_result = submit_answers(username, code_link, results, token)
-    msg = submission_result.get("message", "No message returned.")
-    score = submission_result.get("score")
-    if score is not None:
-        msg += f" | Score: {score:.2%}"
-
-    if submission_result.get("success", True):
-        return f"✅ Submission successful: {msg}", df
-    else:
-        return f"❌ Submission failed: {msg}", df
+            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)
+        return status_message, results_df
 
 
-# ---------------- Gradio UI ----------------
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# 🧠 GAIA Unit 4 Agent Evaluation")
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
-        ### Instructions
-        1. Log in with your Hugging Face account.
-        2. Add your **HF_TOKEN** as a secret in Space Settings → Repository Secrets.
-        3. Click **Run Evaluation & Submit All Answers**.
-
+        **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.
         ---
-        This app:
-        - Fetches all tasks via `GET /questions`
-        - Runs your local agent using GAIA’s official prompt
-        - Submits answers to `POST /submit` in the required JSON format
+        **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.
         """
     )
-    login_btn = gr.LoginButton()
-    run_btn = gr.Button("🚀 Run Evaluation & Submit All Answers")
-    status_box = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    result_table = gr.DataFrame(label="Questions and Model Answers", wrap=True)
 
-    run_btn.click(fn=run_and_submit_all, inputs=[login_btn], outputs=[status_box, result_table])
+    gr.LoginButton()
 
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-# ---------------- Launch ----------------
-if __name__ == "__main__":
-    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
-    space_host = os.getenv("SPACE_HOST")
-    space_id = os.getenv("SPACE_ID")
+    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]
+    )
 
-    if space_host:
-        print(f"✅ SPACE_HOST: {space_host}")
-        print(f"   Runtime: https://{space_host}.hf.space")
+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 not found (running locally?)")
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id:
-        print(f"✅ SPACE_ID: {space_id}")
-        print(f"   Repo: https://huggingface.co/spaces/{space_id}/tree/main")
+    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 not found (running locally?)")
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("------------------------------------------------------------\n")
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)