import os import gradio as gr import requests import inspect import pandas as pd # from agents import LlamaIndexAgent from langraph_agent import build_graph import asyncio import aiohttp from langfuse.langchain import CallbackHandler # Initialize Langfuse CallbackHandler for LangGraph/Langchain (tracing) langfuse_handler = CallbackHandler() # (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 ------ class BasicAgent: def __init__(self): self.agent = build_graph() print("BasicAgent initialized.") async def aquery(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") response = await self.agent.run_query(question, config={"callbacks": [langfuse_handler]}) print(f"Agent returning fixed answer: {response}") return response # Global cache for answers (in-memory) cached_answers = None cached_results_log = None cached_questions = None async def generate_answers(profile: gr.OAuthProfile | None, progress=gr.Progress(track_tqdm=True)): """ Fetches all questions, runs the BasicAgent on them asynchronously, and returns the answers and log. """ global cached_answers, cached_results_log, cached_questions space_id = os.getenv("SPACE_ID") 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, gr.update(interactive=False), gr.update(value=0, visible=False) api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" 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, gr.update(interactive=False), gr.update(value=0, visible=False) print(f"Fetched {len(questions_data)} questions.") except Exception as e: print(f"Error fetching questions: {e}") return f"Error fetching questions: {e}", None, gr.update(interactive=False), gr.update(value=0, visible=False) agent = BasicAgent() results_log = [] answers_payload = [] cached_questions = questions_data total = len(questions_data) progress(0, desc="Starting answer generation...") semaphore = asyncio.Semaphore(3) # Limit concurrency to 3 async def answer_one(item): async with semaphore: 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}") return {"Task ID": task_id, "Question": question_text, "Submitted Answer": "SKIPPED"}, None try: submitted_answer = await agent.aquery(question_text) return {"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}, {"task_id": task_id, "submitted_answer": submitted_answer} except Exception as e: print(f"Error running agent on task {task_id}: {e}") return {"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"}, None tasks = [answer_one(item) for item in questions_data] results_log = [] answers_payload = [] for idx, coro in enumerate(asyncio.as_completed(tasks)): log, answer = await coro results_log.append(log) if answer: answers_payload.append(answer) progress(int((idx+1)/total*100), desc=f"Answered {idx+1}/{total}") cached_answers = answers_payload cached_results_log = results_log progress(100, desc="Done.") results_df = pd.DataFrame(results_log) return "Answer generation complete. Review and submit.", results_df, gr.update(interactive=True), gr.update(value=100, visible=True) def submit_answers(profile: gr.OAuthProfile | None): """ Submits cached answers and returns the result. """ global cached_answers, cached_results_log, cached_questions space_id = os.getenv("SPACE_ID") 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 if not cached_answers: print("No answers to submit.") return "No answers to submit. Please generate answers first.", None api_url = DEFAULT_API_URL submit_url = f"{api_url}/submit" agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": cached_answers} print(f"Submitting {len(cached_answers)} 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.')}" ) results_df = pd.DataFrame(cached_results_log) return final_status, results_df except Exception as e: print(f"Submission error: {e}") results_df = pd.DataFrame(cached_results_log) return f"Submission Failed: {e}", results_df # --- 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 'Generate Answers' to fetch questions and run your agent. Review the answers, then click 'Submit Answers' to submit them and see your score. --- **Disclaimers:** Generating answers may take some time. This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance, you could cache the answers and submit in a separate action or answer the questions asynchronously. """ ) gr.LoginButton() with gr.Row(): generate_button = gr.Button("Generate Answers") submit_button = gr.Button("Submit Answers", interactive=False) status_output = gr.Textbox(label="Status / Submission Result", lines=5, interactive=False) results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True) generate_button.click( fn=generate_answers, inputs=[], outputs=[status_output, results_table, submit_button], api_name="generate_answers" ) submit_button.click( fn=submit_answers, inputs=[], outputs=[status_output, results_table], api_name="submit_answers" ) 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)