Create app.py

app.py

@@ -1,107 +1,245 @@
 import os
-import gradio as gr
+import io
+import re
 import requests
-import inspect
 import pandas as pd
+import gradio as gr
+
+from huggingface_hub import InferenceClient
+from pypdf import PdfReader
 
-# (Keep Constants as is)
-# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+MODEL_ID = os.getenv("MODEL_ID", "Qwen/Qwen2.5-14B-Instruct")
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+
+def clean_answer(text: str) -> str:
+    if not text:
+        return ""
+
+    text = text.strip()
+
+    # remove markdown fences
+    text = re.sub(r"^```.*?\n", "", text, flags=re.DOTALL)
+    text = text.replace("```", "").strip()
+
+    # common prefixes
+    text = re.sub(r"(?i)^final answer\s*:\s*", "", text).strip()
+    text = re.sub(r"(?i)^answer\s*:\s*", "", text).strip()
+    text = re.sub(r"(?i)^submitted_answer\s*:\s*", "", text).strip()
+
+    # if model gave multiple lines, keep the first meaningful one
+    lines = [line.strip() for line in text.splitlines() if line.strip()]
+    if lines:
+        text = lines[0]
+
+    # trim wrapping quotes
+    text = text.strip().strip('"').strip("'").strip()
+
+    return text
+
+
+def try_extract_text_from_pdf(content: bytes) -> str:
+    try:
+        reader = PdfReader(io.BytesIO(content))
+        pages = []
+        for page in reader.pages[:10]:
+            page_text = page.extract_text() or ""
+            if page_text.strip():
+                pages.append(page_text)
+        return "\n".join(pages)[:12000]
+    except Exception:
+        return ""
+
+
+def try_extract_text_from_bytes(content: bytes) -> str:
+    for enc in ["utf-8", "latin-1"]:
+        try:
+            text = content.decode(enc, errors="ignore").strip()
+            if text:
+                return text[:12000]
+        except Exception:
+            pass
+    return ""
+
+
+def fetch_task_file_text(task_id: str) -> str:
+    file_url = f"{DEFAULT_API_URL}/files/{task_id}"
+    try:
+        r = requests.get(file_url, timeout=30)
+        if r.status_code != 200:
+            return ""
+
+        content_type = (r.headers.get("content-type") or "").lower()
+        content = r.content
+
+        if "pdf" in content_type:
+            pdf_text = try_extract_text_from_pdf(content)
+            if pdf_text:
+                return pdf_text
+
+        if any(x in content_type for x in ["text", "json", "csv", "xml", "html"]):
+            return try_extract_text_from_bytes(content)
+
+        # fallback: try text anyway
+        return try_extract_text_from_bytes(content)
+
+    except Exception:
+        return ""
+
 
-# --- 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):
-    """
-    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 not HF_TOKEN:
+            raise ValueError("Missing HF_TOKEN secret in your Space settings.")
+        self.client = InferenceClient(token=HF_TOKEN)
+        print(f"BasicAgent initialized with model: {MODEL_ID}")
+
+    def __call__(self, question: str, file_text: str = "") -> str:
+        system_prompt = (
+            "You solve benchmark questions. "
+            "Return only the exact final answer. "
+            "Do not explain. "
+            "Do not use markdown. "
+            "Do not say FINAL ANSWER. "
+            "If the answer is a number, date, name, or short phrase, return exactly that."
+        )
+
+        user_prompt = f"Question:\n{question}\n"
+        if file_text.strip():
+            user_prompt += f"\nAttached file content:\n{file_text}\n"
+
+        completion = self.client.chat.completions.create(
+            model=MODEL_ID,
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_prompt},
+            ],
+            temperature=0.1,
+            max_tokens=120,
+        )
+
+        raw = completion.choices[0].message.content
+        answer = clean_answer(raw)
+        print(f"RAW MODEL OUTPUT: {raw}")
+        print(f"CLEANED ANSWER: {answer}")
+        return answer
+
+
+def run_random_test():
+    random_url = f"{DEFAULT_API_URL}/random-question"
+
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        return f"Agent init error: {e}", None
+
+    try:
+        r = requests.get(random_url, timeout=20)
+        r.raise_for_status()
+        item = r.json()
+    except Exception as e:
+        return f"Could not fetch random question: {e}", None
+
+    task_id = item.get("task_id", "")
+    question = item.get("question", "")
+    file_text = fetch_task_file_text(task_id) if task_id else ""
+
+    try:
+        answer = agent(question, file_text=file_text)
+    except Exception as e:
+        return f"Agent failed on random test: {e}", None
+
+    preview = pd.DataFrame([
+        {
+            "Task ID": task_id,
+            "Question": question,
+            "Attached File Text Found": "yes" if file_text else "no",
+            "Submitted Answer": answer,
+        }
+    ])
+
+    return "Random test completed. Check whether the answer is short and clean.", preview
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
+        username = f"{profile.username}"
     else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        return "Please login to Hugging Face first.", None
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+    if not space_id:
+        return "SPACE_ID environment variable missing.", None
+
+    questions_url = f"{DEFAULT_API_URL}/questions"
+    submit_url = f"{DEFAULT_API_URL}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your 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)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = requests.get(questions_url, timeout=20)
         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
+        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}")
+        question_text = item.get("question", "")
+
+        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})
+            file_text = fetch_task_file_text(task_id)
+            submitted_answer = agent(question_text, file_text=file_text)
+
+            answers_payload.append(
+                {"task_id": task_id, "submitted_answer": submitted_answer}
+            )
+
+            results_log.append(
+                {
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Attached File Text Found": "yes" if file_text else "no",
+                    "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}"})
+            results_log.append(
+                {
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Attached File Text Found": "unknown",
+                    "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)
+        return "No answers were produced.", 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)
+    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 = requests.post(submit_url, json=submission_data, timeout=120)
         response.raise_for_status()
         result_data = response.json()
+
         final_status = (
             f"Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
@@ -109,88 +247,55 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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
+
+        return final_status, pd.DataFrame(results_log)
+
     except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
+        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
+            detail_json = e.response.json()
+            detail += f" Detail: {detail_json.get('detail', e.response.text)}"
+        except Exception:
+            detail += f" Response: {e.response.text[:500]}"
+        return f"Submission failed: {detail}", 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 Cheap Baseline Agent")
     gr.Markdown(
         """
-        **Instructions:**
+        1. Add your HF_TOKEN secret in Space settings.
+        2. Login with Hugging Face below.
+        3. Click 'Run One Cheap Test' first.
+        4. If the answer looks clean, click 'Run Full Evaluation and Submit'.
 
-        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.
+        Notes:
+        - This version is optimized for simplicity and low cost.
+        - It tries to read attached text/PDF files.
+        - It returns short exact answers for exact-match scoring.
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    test_button = gr.Button("Run One Cheap Test")
+    run_button = gr.Button("Run Full Evaluation and Submit")
+
+    status_output = gr.Textbox(label="Status", lines=6, interactive=False)
+    results_table = gr.DataFrame(label="Agent Output", wrap=True)
 
-    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)
+    test_button.click(
+        fn=run_random_test,
+        outputs=[status_output, results_table],
+    )
 
     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)
+    demo.launch(debug=True, share=False)