Update app.py

app.py

@@ -1,73 +1,72 @@
 import os
+import re
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-import re
 from huggingface_hub import InferenceClient
 
-
-# (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 ------
+
 # --- Basic Agent Definition ---
 class BasicAgent:
     """
     Minimal LLM-based agent for GAIA level-1 style questions.
-    Goal: >=30% (at least 6/20 exact match).
+    Target: >=30% (>=6/20 exact match) by keeping output clean.
     """
+
     def __init__(self):
         print("BasicAgent initialized (LLM mode).")
 
-        # 必須先在 Space 設定 Secret：HF_TOKEN（你的 Hugging Face access token）
+        # ✅ 必須在 Space 設定 Secret：HF_TOKEN
         self.hf_token = os.getenv("HF_TOKEN") or os.getenv("HUGGINGFACEHUB_API_TOKEN")
         if not self.hf_token:
-            raise RuntimeError("Missing HF_TOKEN. Please set it in Space Settings → Secrets.")
+            raise RuntimeError("Missing HF_TOKEN. Set it in Space Settings → Variables and secrets → New secret.")
 
-        # 先用 7B 最穩最容易跑完；不夠分再升 14B/32B
+        # ✅ 先用 7B 穩定跑完；不夠分再用 Settings 加 MODEL_ID 升到 14B/32B
         self.model_id = os.getenv("MODEL_ID", "Qwen/Qwen2.5-7B-Instruct")
 
-        # 重要：用 router，不要用 api-inference（你之前 410 就是這個）
+        # ✅ 不要傳 base_url（會跟 model 參數衝突，造成你剛剛那個錯誤）
+        # 新版 huggingface_hub 會走新的推理路由；只要給 model + token 就行
         self.client = InferenceClient(
             model=self.model_id,
             token=self.hf_token,
-            base_url="https://router.huggingface.co",
             timeout=120,
         )
 
+        # 強制乾淨輸出（exact match）
+        self.system = (
+            "You are a precise question-answering assistant.\n"
+            "Return ONLY the final answer, nothing else.\n"
+            "No explanation. No extra words.\n"
+            "No surrounding quotes unless the answer itself includes them.\n"
+        )
+
     def _sanitize(self, text: str) -> str:
         if not text:
             return ""
-        t = text.strip()
+        t = str(text).strip()
 
-        # 移除 FINAL ANSWER 這種字眼（課程有說不要加）
+        # 移除 FINAL ANSWER / Answer: 之類常見包裝
         t = re.sub(r"(?i)\bFINAL ANSWER\b\s*[:\-]*\s*", "", t).strip()
+        t = re.sub(r"(?i)^\s*answer\s*[:\-]\s*", "", t).strip()
 
-        # 如果模型分行，取最後一行（通常答案會在最後）
+        # 取最後一個非空行（模型如果亂輸出多行，答案常在最後）
         lines = [ln.strip() for ln in t.splitlines() if ln.strip()]
         if lines:
             t = lines[-1]
 
-        # 去掉引號
+        # 去掉外層引號
         t = t.strip().strip('"').strip("'").strip()
         return t
 
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        print(f"Agent received question (first 80 chars): {question[:80]}...")
 
-        system = (
-            "You are a precise question-answering assistant.\n"
-            "Return ONLY the final answer, nothing else.\n"
-            "No explanations. No extra words. No punctuation unless required.\n"
-            "If the answer is a number/date/name, output it exactly.\n"
-        )
+        prompt = f"{self.system}\nQuestion: {question}\nAnswer:"
 
-        prompt = f"{system}\nQuestion: {question}\nAnswer:"
-
-        # 用 chat completion 風格（InferenceClient 會依模型支援）
+        # 優先用 text_generation（快），失敗再用 chat_completion
         try:
             out = self.client.text_generation(
                 prompt,
@@ -77,31 +76,30 @@ class BasicAgent:
                 return_full_text=False,
             )
         except Exception as e:
-            # 如果 text_generation 因模型接口差異出錯，退回 chat_completion
             print("text_generation failed, fallback to chat_completion:", e)
             out = self.client.chat_completion(
                 messages=[
-                    {"role": "system", "content": system},
+                    {"role": "system", "content": self.system},
                     {"role": "user", "content": question},
                 ],
                 max_tokens=128,
                 temperature=0.0,
             ).choices[0].message.content
 
-        ans = self._sanitize(str(out))
+        ans = self._sanitize(out)
         print(f"Agent answer: {ans}")
         return ans
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the agent 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")  # used for code link
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -111,70 +109,71 @@ 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)
+    # 1) Instantiate 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
+    # code link for verification
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else ""
+    print("agent_code:", 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:
+    except Exception 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
+    # 3) Run 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})
+            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)
+    # 4) Prepare submission
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
 
-    # 5. Submit
+    # 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"
@@ -182,88 +181,53 @@ 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}."
+        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)
+            detail_json = e.response.json()
+            detail += f" Detail: {detail_json.get('detail', e.response.text)}"
+        except Exception:
+            detail += f" Response: {e.response.text[:500]}"
         results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission Failed: {detail}", 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 "Submission Failed: The request timed out.", 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
+        return f"An unexpected error occurred during submission: {e}", results_df
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio UI ---
 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.
+    gr.Markdown(
         """
+**Instructions:**
+1. Log in to your Hugging Face account using the button below.
+2. Click **Run Evaluation & Submit All Answers**.
+
+**Notes:**
+- This will run 20 questions and submit answers for scoring.
+- Exact match: the agent must output ONLY the answer (no extra words).
+"""
     )
 
     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)
+    demo.launch(debug=True, share=False)