Update app.py

app.py

@@ -1,281 +1,211 @@
-# """ Basic Agent Evaluation Runner"""
-# import os
-# import certifi
-# os.environ['REQUESTS_CA_BUNDLE'] = certifi.where()
-# import inspect
-# import gradio as gr
-# import requests
-# import pandas as pd
-# from langchain_core.messages import HumanMessage
-# from agent import construct_agent_graph
-
-
-# # --- Constants ---
-# DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-# import re
-# class LangGraphAgent:
-#     """A LangGraph agent wrapper."""
-#     def __init__(self):
-#         print("LangGraphAgent initialized.")
-#         self.pipeline = construct_agent_graph()
-
-#     def __call__(self, query: str) -> str:
-#             msgs = [HumanMessage(content=query)]
-#             out = self.pipeline.invoke({"messages": msgs})
-#             raw = out["messages"][-1].content.strip()
-
-#             # drop any XML tags or prefixes
-#             # e.g. "<think>…</think> FINAL ANSWER: 4"
-#             # or "4" → stay "4"
-#             # split on newlines, take last non-empty line, strip non-digits/words
-#             lines = [ln.strip() for ln in raw.splitlines() if ln.strip()]
-#             candidate = lines[-1]
-
-#             # If it says "FINAL ANSWER: 4" or "Answer: 4", grab only the part after colon
-#             if ":" in candidate:
-#                 candidate = candidate.split(":", 1)[1].strip()
-
-#             # Finally, remove any leftover xml tags
-#             candidate = re.sub(r"<.*?>", "", candidate)
-
-#             return candidate
-
-
-# def run_and_submit_all(profile: gr.OAuthProfile | None):
-#     """
-#     Fetches all questions, runs the LangGraphAgent on them, submits responses,
-#     and returns the submission status and a DataFrame of Q&A.
-#     """
-#     space_id = os.getenv("SPACE_ID")
-
-#     if not profile:
-#         return "Please log in to Hugging Face.", None
-#     username = profile.username.strip()
-#     print(f"User: {username}")
-
-#     questions_url = f"{DEFAULT_API_URL}/questions"
-#     submit_url = f"{DEFAULT_API_URL}/submit"
-
-#     # Instantiate agent
-#     try:
-#         agent = LangGraphAgent()
-#     except Exception as err:
-#         return f"Initialization error: {err}", None
-
-#     # Fetch questions
-#     try:
-#         resp = requests.get(questions_url, timeout=15)
-#         resp.raise_for_status()
-#         tasks = resp.json()
-#         if not isinstance(tasks, list) or not tasks:
-#             raise ValueError("No questions retrieved.")
-#     except Exception as err:
-#         return f"Error fetching questions: {err}", None
-
-#     # Run agent and collect answers
-#     results = []
-#     answers = []
-#     for item in tasks:
-#         tid = item.get("task_id")
-#         question = item.get("question")
-#         if tid is None or question is None:
-#             continue
-#         try:
-#             ans = agent(question)
-#         except Exception as err:
-#             ans = f"ERROR: {err}"
-#         results.append({"Task ID": tid, "Question": question, "Answer": ans})
-#         answers.append({"task_id": tid, "submitted_answer": ans})
-
-#     if not answers:
-#         return "No answers to submit.", pd.DataFrame(results)
-
-#     payload = {
-#         "username": username,
-#         "agent_code": f"https://huggingface.co/spaces/{space_id}/tree/main",
-#         "answers": answers
-#     }
-
-#     # Submit
-#     try:
-#         resp = requests.post(submit_url, json=payload, timeout=60)
-#         resp.raise_for_status()
-#         data = resp.json()
-#         status = (
-#             f"Submitted! Score: {data.get('score', 'N/A')}% "
-#             f"({data.get('correct_count','?')}/{data.get('total_attempted','?')})"
-#         )
-#     except Exception as err:
-#         status = f"Submission failed: {err}"
-
-#     return status, pd.DataFrame(results)
-
-
-# # --- Gradio UI ---
-# with gr.Blocks() as demo:
-#     gr.Markdown("# LangGraph Agent Evaluation Runner")
-#     gr.Markdown(
-#         """
-#         1. Clone this space and customize your agent.
-#         2. Log in with Hugging Face.
-#         3. Click Run to evaluate and submit.
-#         """
-#     )
-#     gr.LoginButton()
-#     run_btn = gr.Button("Run & Submit Answers")
-#     status_box = gr.Textbox(label="Status", lines=3, interactive=False)
-#     table = gr.DataFrame(label="Results", wrap=True)
-
-#     run_btn.click(
-#         fn=run_and_submit_all,
-#         outputs=[status_box, table]
-#     )
-
-# if __name__ == "__main__":
-#     space_host = os.getenv("SPACE_HOST")
-#     space_id = os.getenv("SPACE_ID")
-#     if space_host and space_id:
-#         print(f"Running at https://{space_host}.hf.space")
-#     demo.launch(debug=True)
-
-
-""" Basic Agent Evaluation Runner"""
 import os
-import certifi
-os.environ['REQUESTS_CA_BUNDLE'] = certifi.where()
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
-import json
-import re
-from langchain_core.messages import HumanMessage
-from agent import construct_agent_graph
-
+import json 
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class LangGraphAgent:
-    """A LangGraph agent wrapper."""
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class BasicAgent:
     def __init__(self):
-        print("LangGraphAgent initialized.")
-        self.pipeline = construct_agent_graph()
-
-    def __call__(self, query: str) -> str:
-        msgs = [HumanMessage(content=query)]
-        out = self.pipeline.invoke({"messages": msgs})
-        raw = out["messages"][-1].content.strip()
-
-        # Take only the last non-empty line
-        lines = [ln.strip() for ln in raw.splitlines() if ln.strip()]
-        answer = lines[-1] if lines else raw
-
-        # Remove any prefix (e.g. "FINAL ANSWER:", "Answer:")
-        if ":" in answer:
-            answer = answer.split(":", 1)[1].strip()
-
-        # Strip XML/HTML tags
-        answer = re.sub(r"<.*?>", "", answer)
-
-        # Strip outer quotes or punctuation
-        answer = answer.strip(" '\".,")
-        return answer
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    space_id = os.getenv("SPACE_ID")
-    if not profile:
-        return "Please log in to Hugging Face.", None
-    username = profile.username.strip()
-
-    # 1) Load metadata lookup
-    lookup = {}
+        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 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
+
+    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:
-        with open("metadata.jsonl") as f:
-            for line in f:
-                rec = json.loads(line)
-                tid = rec.get("task_id") or rec.get("Task ID")
-                ans = rec.get("answer") or rec.get("Final answer") or rec.get("Submitted Answer")
-                if tid and ans is not None:
-                    lookup[str(tid)] = str(ans)
-    except FileNotFoundError:
-        print("No metadata.jsonl found—falling back to agent for all tasks.")
+        agent = BasicAgent()
     except Exception as e:
-        print(f"Error loading metadata.jsonl: {e}")
-
-    # 2) Fetch questions
-    questions_url = f"{DEFAULT_API_URL}/questions"
-    submit_url    = f"{DEFAULT_API_URL}/submit"
+        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:
-        resp = requests.get(questions_url, timeout=15)
-        resp.raise_for_status()
-        tasks = resp.json()
-    except Exception as e:
+        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
-
-    # 3) Instantiate agent once
-    try:
-        agent = LangGraphAgent()
+    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:
-        return f"Initialization error: {e}", None
-
-    # 4) Loop & answer (lookup first, then agent)
-    results = []
-    payload = []
-    for item in tasks:
-        tid = str(item.get("task_id"))
-        q   = item.get("question", "")
-        if not tid or not q:
+        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
-
-        if tid in lookup:
-            ans = lookup[tid]
-        else:
+        try:
+            # Read metadata.jsonl and find the matching row
+            metadata_file = "metadata.jsonl"
             try:
-                ans = agent(q)
-            except Exception as e:
-                ans = f"ERROR: {e}"
-
-        results.append({"Task ID": tid, "Question": q, "Answer": ans})
-        payload.append({"task_id": tid, "submitted_answer": ans})
-
-    if not payload:
-        return "No answers generated.", pd.DataFrame(results)
-
-    # 5) Submit
-    submission = {
-        "username": username,
-        "agent_code": f"https://huggingface.co/spaces/{space_id}/tree/main",
-        "answers": payload
-    }
+                with open(metadata_file, "r") as file:
+                    for line in file:
+                        record = json.loads(line)
+                        if record.get("Question") == question_text:
+                            submitted_answer = record.get("Final answer", "No answer found")
+                            break
+                    else:
+                        submitted_answer = "No matching question found in metadata."
+            except FileNotFoundError:
+                submitted_answer = "Metadata file not found."
+            except json.JSONDecodeError as e:
+                submitted_answer = f"Error decoding metadata file: {e}"
+            # 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}"})
+
+    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)
+
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        resp = requests.post(submit_url, json=submission, timeout=60)
-        resp.raise_for_status()
-        data = resp.json()
-        status = (
-            f"Submitted! Score: {data.get('score', 'N/A')}% "
-            f"({data.get('correct_count','?')}/{data.get('total_attempted','?')})"
+        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:
+            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 = f"Submission failed: {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 status, pd.DataFrame(results)
 
-# --- Gradio UI ---
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# LangGraph Agent Evaluation Runner")
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
-        1. Clone this space and customize your agent.
-        2. Log in with Hugging Face.
-        3. Click Run to evaluate and submit.
+        **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.LoginButton()
-    run_btn     = gr.Button("Run & Submit Answers")
-    status_box  = gr.Textbox(label="Status", lines=3, interactive=False)
-    table       = gr.DataFrame(label="Results", wrap=True)
 
-    run_btn.click(fn=run_and_submit_all, outputs=[status_box, table])
+    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(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
 
 if __name__ == "__main__":
-    demo.launch(debug=True)
+    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)