import os import gradio as gr import requests import inspect import pandas as pd from dotenv import load_dotenv from agent import build_graph from langchain_core.messages import HumanMessage load_dotenv() # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the LangGraph 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 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 try: # Use the build_graph function from agent.py agent_graph = build_graph() print("LangGraph agent initialized.") except Exception as e: print(f"Error instantiating agent graph: {e}") return f"Error initializing agent graph: {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" if space_id else "Agent code link unavailable (SPACE_ID not set)" # Added a check for SPACE_ID print(f"Agent code link: {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...") # Removed the problematic print statement from here 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 # Moved the print statement inside the loop, after task_id and question_text are assigned print(f"--- Starting processing Task ID: {task_id}, Question: {question_text[:100]}...") try: # Invoke the LangGraph agent result_state = agent_graph.invoke({"messages": [HumanMessage(content=question_text)]}) # Extract the final answer from the last message submitted_answer = "Error: Agent did not provide a response." # Default in case extraction fails if result_state and "messages" in result_state and result_state["messages"]: last_message = result_state["messages"][-1] # The final content is typically in the content attribute of the last message if hasattr(last_message, 'content') and last_message.content: submitted_answer = last_message.content # else: Handle cases where the last message might be a tool message etc., # for simplicity, we just use the default error message if content is missing. # Ensure submitted_answer is a string if not isinstance(submitted_answer, str): submitted_answer = str(submitted_answer) 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}) # Moved this print statement inside the loop as well print(f"--- Finished processing Task ID: {task_id}") # Moved this print statement inside the loop as well print(f"--- Extracted answer for Task ID: {task_id}: {submitted_answer[:100]}...") except Exception as e: print(f"Error running agent graph on task {task_id}: {e}") results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"}) # Note: If an error occurs, the 'Finished' and 'Extracted answer' prints for this specific task won't happen, # which is reasonable behavior. if not answers_payload: print("Agent did not produce any answers to submit.") # Even if no answers, show the log of errors 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: 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_message = f"An unexpected error occurred during submission: {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df # --- Build Gradio Interface using Blocks --- with gr.Blocks() as demo: gr.Markdown("# LangGraph Agent Evaluation Runner") # Updated title gr.Markdown( """ **Instructions:** 1. Please clone this space, then modify the code in `agent.py` and `app.py` to define your agent's logic, the tools, the necessary packages, etc ... 2. **Make sure you have your `DEEPSEEK_API_KEY` set as a Space Secret.** 3. Log in to your Hugging Face account using the button below. This uses your HF username for submission. 4. 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_button = gr.Button("Run Evaluation & Submit All Answers") status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, 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] ) 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 LangGraph Agent Evaluation...") # Updated message demo.launch(debug=True, share=False, auth=None)