Update app.py

app.py

@@ -1,34 +1,231 @@
 import os
+import re
+import io
+import base64
+import mimetypes
+import tempfile
+from pathlib import Path
+
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from openai import OpenAI
 
-# (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 ------
+# Set these in your Space Secrets:
+# LLM_API_KEY       -> your API key
+# LLM_BASE_URL      -> optional, for OpenAI-compatible providers
+# MODEL_NAME        -> e.g. gpt-4o-mini or another strong model
+# TRANSCRIBE_MODEL  -> e.g. gpt-4o-mini-transcribe
+LLM_API_KEY = os.getenv("LLM_API_KEY", "")
+LLM_BASE_URL = os.getenv("LLM_BASE_URL", "https://api.openai.com/v1")
+MODEL_NAME = os.getenv("MODEL_NAME", "gpt-4o-mini")
+TRANSCRIBE_MODEL = os.getenv("TRANSCRIBE_MODEL", "gpt-4o-mini-transcribe")
+
+
+def to_data_url(file_path: str) -> str:
+    mime, _ = mimetypes.guess_type(file_path)
+    if not mime:
+        mime = "application/octet-stream"
+    with open(file_path, "rb") as f:
+        b64 = base64.b64encode(f.read()).decode("utf-8")
+    return f"data:{mime};base64,{b64}"
+
+
+def clean_final_answer(text: str) -> str:
+    if not text:
+        return ""
+    text = text.strip()
+    text = re.sub(r"^\s*(final answer|answer)\s*[:\-]\s*", "", text, flags=re.I)
+    text = text.strip().strip('"').strip("'")
+    return text
+
+
+def extract_urls(text: str):
+    return re.findall(r"https?://[^\s)\]]+", text or "")
+
+
 class BasicAgent:
     def __init__(self):
+        if not LLM_API_KEY:
+            raise ValueError("Missing LLM_API_KEY in Space Secrets.")
+        self.client = OpenAI(api_key=LLM_API_KEY, base_url=LLM_BASE_URL)
+        self.api_url = DEFAULT_API_URL
         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):
+    def download_task_file(self, task_id: str, file_name: str) -> str | None:
+        if not file_name:
+            return None
+
+        url = f"{self.api_url}/files/{task_id}"
+        print(f"Downloading attached file from {url}")
+
+        r = requests.get(url, timeout=60)
+        if r.status_code != 200:
+            print(f"Could not fetch file for task {task_id}: {r.status_code}")
+            return None
+
+        suffix = Path(file_name).suffix or ""
+        fd, tmp_path = tempfile.mkstemp(suffix=suffix)
+        os.close(fd)
+        with open(tmp_path, "wb") as f:
+            f.write(r.content)
+        return tmp_path
+
+    def read_text_like_file(self, file_path: str) -> str | None:
+        suffix = Path(file_path).suffix.lower()
+        if suffix not in {".txt", ".md", ".json", ".csv", ".py", ".html"}:
+            return None
+
+        try:
+            with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+                data = f.read()
+            return data[:15000]
+        except Exception as e:
+            return f"[Could not read text file: {e}]"
+
+    def summarize_spreadsheet(self, file_path: str) -> str:
+        try:
+            xls = pd.ExcelFile(file_path)
+            out = []
+            for sheet_name in xls.sheet_names[:3]:
+                df = pd.read_excel(file_path, sheet_name=sheet_name)
+                out.append(f"Sheet: {sheet_name}")
+                out.append("Columns: " + ", ".join(map(str, df.columns.tolist())))
+                out.append("Preview:")
+                out.append(df.head(20).to_csv(index=False))
+                out.append("")
+            return "\n".join(out)[:15000]
+        except Exception as e:
+            return f"[Could not read spreadsheet: {e}]"
+
+    def transcribe_audio(self, file_path: str) -> str:
+        try:
+            with open(file_path, "rb") as audio_file:
+                transcript = self.client.audio.transcriptions.create(
+                    model=TRANSCRIBE_MODEL,
+                    file=audio_file,
+                )
+            text = getattr(transcript, "text", "") or ""
+            return text[:12000]
+        except Exception as e:
+            return f"[Could not transcribe audio: {e}]"
+
+    def fetch_web_context(self, question: str) -> str:
+        urls = extract_urls(question)
+        if not urls:
+            return ""
+
+        chunks = []
+        for url in urls[:2]:
+            try:
+                r = requests.get(url, timeout=30, headers={"User-Agent": "Mozilla/5.0"})
+                content = r.text[:12000]
+                chunks.append(f"URL: {url}\nCONTENT:\n{content}\n")
+            except Exception as e:
+                chunks.append(f"URL: {url}\n[Could not fetch: {e}]")
+        return "\n\n".join(chunks)
+
+    def ask_model(self, question: str, extra_context: str = "", image_paths=None) -> str:
+        image_paths = image_paths or []
+
+        system_prompt = (
+            "You solve benchmark questions carefully.\n"
+            "Return ONLY the final answer.\n"
+            "Do not add explanations.\n"
+            "Do not add 'FINAL ANSWER'.\n"
+            "Keep formatting exactly as requested in the question.\n"
+            "If the question asks for alphabetical order, preserve it.\n"
+            "If it asks for comma-separated output, return only that comma-separated output.\n"
+            "If it asks for a name, return only the name requested.\n"
+        )
+
+        user_parts = []
+        user_parts.append({
+            "type": "text",
+            "text": f"QUESTION:\n{question}\n\nEXTRA CONTEXT:\n{extra_context[:20000]}"
+        })
+
+        for img in image_paths[:3]:
+            user_parts.append({
+                "type": "image_url",
+                "image_url": {"url": to_data_url(img)}
+            })
+
+        response = self.client.chat.completions.create(
+            model=MODEL_NAME,
+            temperature=0,
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_parts},
+            ],
+        )
+
+        answer = response.choices[0].message.content or ""
+        return clean_final_answer(answer)
+
+    def __call__(self, task: dict) -> str:
+        task_id = task.get("task_id", "")
+        question = task.get("question", "")
+        file_name = task.get("file_name", "") or ""
+
+        print(f"Task {task_id} | file_name={file_name}")
+
+        extra_context = []
+        image_paths = []
+
+        # 1) Fetch webpage content if URLs appear in the question
+        web_context = self.fetch_web_context(question)
+        if web_context:
+            extra_context.append("WEB CONTEXT:\n" + web_context)
+
+        # 2) Download attached file if any
+        local_file = None
+        if file_name:
+            local_file = self.download_task_file(task_id, file_name)
+
+        # 3) Handle attachment types
+        if local_file:
+            suffix = Path(local_file).suffix.lower()
+
+            if suffix in {".png", ".jpg", ".jpeg", ".webp"}:
+                image_paths.append(local_file)
+
+            elif suffix in {".mp3", ".wav", ".m4a", ".mpeg"}:
+                transcript = self.transcribe_audio(local_file)
+                extra_context.append("AUDIO TRANSCRIPT:\n" + transcript)
+
+            elif suffix in {".xlsx", ".xls"}:
+                sheet_summary = self.summarize_spreadsheet(local_file)
+                extra_context.append("SPREADSHEET CONTENT:\n" + sheet_summary)
+
+            else:
+                text_data = self.read_text_like_file(local_file)
+                if text_data:
+                    extra_context.append(f"ATTACHED FILE CONTENT ({file_name}):\n{text_data}")
+
+        # 4) Ask model
+        final_answer = self.ask_model(
+            question=question,
+            extra_context="\n\n".join(extra_context),
+            image_paths=image_paths,
+        )
+
+        print(f"Final answer for task {task_id}: {final_answer}")
+        return final_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
+    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.")
@@ -38,70 +235,73 @@ 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()
     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=30)
         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
+            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}")
+            print(f"Skipping invalid item: {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})
+            submitted_answer = agent(item)
+            answers_payload.append({
+                "task_id": task_id,
+                "submitted_answer": submitted_answer
+            })
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "File": item.get("file_name", ""),
+                "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,
+                "File": item.get("file_name", ""),
+                "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)
+    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"
@@ -109,61 +309,43 @@ 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
+
     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:
+        except Exception:
             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
+        return f"Submission Failed: {error_detail}", pd.DataFrame(results_log)
+
     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
+        return "Submission Failed: The request timed out.", pd.DataFrame(results_log)
+
     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 f"Submission Failed: Network error - {e}", 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"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     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. Edit this Space to define your agent's logic and tools.
+        2. Log in to your Hugging Face account using the button below.
+        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
         """
     )
 
     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(
@@ -172,25 +354,4 @@ 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
-    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)