import asyncio import os import requests from typing import Annotated, TypedDict import gradio as gr from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_core.messages import AnyMessage, HumanMessage from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint from langgraph.graph import START, StateGraph from langgraph.graph.message import add_messages from langgraph.prebuilt import ToolNode, tools_condition import pandas as pd from yaml import safe_load from tools import ( add, divide, modulus, multiply, subtract, wikipedia_search, arxiv_search, search_tool, ) from utilities import build_human_message, prepare_questions # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" PROMPT_TEMPLATE_FILE = "prompts.yaml" # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ class BasicAgent: def __init__(self): llm = HuggingFaceEndpoint( repo_id="meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", huggingfacehub_api_token=os.environ["HF_TOKEN"], temperature=0, provider="together" ) chat = ChatHuggingFace(llm=llm, verbose=True) tools = [ add, divide, modulus, multiply, subtract, wikipedia_search, search_tool, arxiv_search ] chat_with_tools = chat.bind_tools(tools) with open(PROMPT_TEMPLATE_FILE, 'r') as stream: prompt_data = safe_load(stream) system_message = prompt_data["system_prompt"] system_prompt = ChatPromptTemplate.from_messages([ ("system", system_message), MessagesPlaceholder("messages"), # inject state messages ]) llm_with_tools = system_prompt | chat_with_tools # Generate the AgentState and Agent graph class AgentState(TypedDict): messages: Annotated[list[AnyMessage], add_messages] async def assistant(state: AgentState): new_message = await llm_with_tools.ainvoke(state["messages"]) return { "messages": [new_message], } ## The graph builder = StateGraph(AgentState) # Define nodes: these do the work builder.add_node("assistant", assistant) builder.add_node("tools", ToolNode(tools)) # Define edges: these determine how the control flow moves builder.add_edge(START, "assistant") builder.add_conditional_edges( "assistant", # If the latest message requires a tool, route to tools # Otherwise, provide a direct response tools_condition, ) builder.add_edge("tools", "assistant") #checkpointer = MemorySaver() self.agent = builder.compile() async def run( self, question: str, image_b64: str | None = None, audio_b64: str | None = None, ) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") messages = [build_human_message(question, image_b64, audio_b64)] fixed_answer = await self.agent.ainvoke({"messages": messages}) print(f"Agent returning fixed answer: {fixed_answer}") print(f"Type of fixed_answer: {type(fixed_answer)}") print(f"Dir of fixed_answer: {dir(fixed_answer)}") print(f"Repr of fixed_answer: {fixed_answer}") final_answer = fixed_answer['messages'][-1].content marker = "FINAL ANSWER:" if marker in final_answer: return final_answer.split(marker, 1)[1].strip() return final_answer.strip() async def answer_all_questions(agent: BasicAgent, questions: list[dict]) -> list[str]: """ Uses the provided agent to answer a question. Args: agent: The agent instance to use for answering. questions: The questions to be answered. Returns: The answers generated by the agent. """ question_infos = prepare_questions(questions) tasks = [agent.run(*question_info) for question_info in question_infos] results = await asyncio.gather(*tasks, return_exceptions=True) failed_tasks = any(isinstance(result, Exception) for result in results) while failed_tasks: for result_index, result in enumerate(results): if isinstance(result, Exception): print(f"Retrying failed task {result_index + 1}/{len(results)}...") try: new_result = await agent.run(*question_infos[result_index]) results[result_index] = new_result print(f"Task {result_index + 1} succeeded on retry.") except Exception as e: print(f"Task {result_index + 1} failed again: {e}") failed_tasks = any(isinstance(result, Exception) for result in results) # Run all coroutines concurrently return results async 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: 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 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...") try: answers = await answer_all_questions(agent, questions_data) except Exception as e: print(f"Error running agent asynchronously: {e}") answer_counter = 0 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: answers_payload.append({"task_id": task_id, "submitted_answer": answers[answer_counter]}) results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": answers[answer_counter]}) answer_counter += 1 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: 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("# 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.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 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 Basic Agent Evaluation...") demo.launch(debug=True, share=False)