import os import gradio as gr import requests import pandas as pd import time import re from langchain_openai import ChatOpenAI from langchain.prompts import PromptTemplate from langchain.agents import AgentExecutor, create_react_agent from langchain.memory import ConversationSummaryMemory from typing import List, Optional # === TOOL IMPORTS === from helper import repl_tool, file_saver_tool, audio_transcriber_tool, gemini_multimodal_tool, wikipedia_search_tool2 # Constants DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Prompt --- prompt = PromptTemplate( input_variables=["input", "agent_scratchpad", "chat_history", "tool_names"], template=""" You are a smart and helpful AI Agent/Assistant that excels at fact-based reasoning. You are allowed and encouraged to use one or more tools as needed to answer complex questions and perform tasks. [ ...cut for brevity: insert your strict format rules and examples here ... ] {chat_history} New input: {input} --- {agent_scratchpad} """ ) # === AGENT DEFINITION === class BasicAgent: def __init__( self, agent, tools: List, verbose: bool = False, handle_parsing_errors: bool = True, max_iterations: int = 9, memory: Optional[ConversationSummaryMemory] = None ): self.agent = agent self.tools = tools self.verbose = verbose self.handle_parsing_errors = handle_parsing_errors self.max_iterations = max_iterations self.memory = memory self.agent_obj = AgentExecutor( agent=self.agent, tools=self.tools, verbose=self.verbose, handle_parsing_errors=self.handle_parsing_errors, max_iterations=self.max_iterations, memory=self.memory ) def __call__(self, question: str) -> str: result = self.agent_obj.invoke( {"input": question}, config={"configurable": {"session_id": "test-session"}}, ) return result['output'] def run_and_submit_all(profile: gr.OAuthProfile | None): 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 api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" # OpenAI API key only! openai_api_key = os.getenv("OPENAI_API_KEY") if not openai_api_key: print("OpenAI API key not found in environment variables.") return "OpenAI API key not found. Please set OPENAI_API_KEY environment variable.", None # Use GPT-4o (or another allowed OpenAI model) llm_client = ChatOpenAI(model='gpt-4o', temperature=0, api_key=openai_api_key) # Tools: only offline/tools not requiring other APIs tools = [ repl_tool, file_saver_tool, audio_transcriber_tool, gemini_multimodal_tool, # If this is purely local or adapted for OpenAI images, otherwise remove! wikipedia_search_tool2 ] summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history") summary_react_agent = create_react_agent( llm=llm_client, tools=tools, prompt=prompt ) # 1. Instantiate Agent try: agent = BasicAgent(summary_react_agent, tools, True, True, 30, summary_memory) except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None 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.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 Exception as e: print(f"Error fetching questions: {e}") 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") file_name = item.get("file_name") full_question_for_agent = question_text if file_name: attachment_url = f"{DEFAULT_API_URL}/files/{task_id}" full_question_for_agent += f"\n\nAttachment '{file_name}' available at EXACT URL: {attachment_url}" print(f"Running agent on task {task_id}: {full_question_for_agent}", flush=True) try: submitted_answer = agent(full_question_for_agent) 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}) time.sleep(2) # Decrease or remove if not rate-limited! 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) 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) 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.')}" ) cleaned_final_status = re.sub(r'[^\x20-\x7E\n\r\t]+', '', final_status).strip() results_df = pd.DataFrame(results_log) return cleaned_final_status, results_df except Exception as e: print(f"Error submitting answers: {e}") results_df = pd.DataFrame(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. Log in to your Hugging Face account using the button below. 2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score. --- **Note:** Only OpenAI API key is needed! """ ) 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) space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") 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(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)