import os import getpass import regex as re import gradio as gr import requests import pandas as pd import base64 import librosa import chess from typing import TypedDict, Annotated from langchain_core.messages import AnyMessage, SystemMessage, HumanMessage from langchain_community.tools import DuckDuckGoSearchRun from langchain.tools import Tool from langgraph.graph import START, StateGraph from langgraph.graph.message import add_messages from langgraph.prebuilt import ToolNode, tools_condition from langchain_deepseek import ChatDeepSeek import cv2 import getpass import os if "DS_AGENT_API" not in os.environ: os.environ["DS_AGENT_API"] = getpass.getpass("Enter your DS API key: ") chat1 = ChatDeepSeek( model="deepseek-chat", temperature=0.01, max_retries=6, api_key = os.getenv("DS_AGENT_API") ) print(f"Model {chat1.model_name} downloaded!") chat2 = ChatDeepSeek( model="deepseek-reasoner", temperature=0.01, max_retries=6, api_key = os.getenv("DS_AGENT_API") ) print(f"Model {chat2.model_name} downloaded!") # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" def get_file_path(question: str) -> str: """Retrieves reference file path.""" if isinstance(question, dict): return question['file_path'] elif isinstance(question, str): for q in question_dataset: if q['Question'] == question: return q['file_path'] def get_ref_content(path: str) -> str | object: """Retrieves content from the reference path provided.""" if path.endswith('.mp3') or path.startswith('https://www.youtube.com/'): file = librosa.load(path) elif path.endswith(".jpg") or path.endswith(".jpeg"): file = cv2.imread(path) cv2.imshow('image', file) elif path.endswith('.xlsx') or path.endswith('.xls'): file = pd.read_excel(path).to_dict() elif path.startswith('http'): file = requests.get(path, timeout=10).text else: with open(path, "rb") as f: file = f.readlines() return file def search_web(query: str) -> str: """Retrieves information about the topic.""" results = DuckDuckGoSearchRun().invoke(query) if results: return "\n\n".join([doc.text for doc in results[:2]]) else: return "No matching content found." def extract_text_from_image(img_path: str) -> str: """Extracts text from image""" try: # Read image and encode as base64 with open(img_path, "rb") as image_file: image_bytes = image_file.read() image_base64 = base64.b64encode(image_bytes).decode("utf-8") return image_base64 except Exception as e: # A butler should handle errors gracefully error_msg = f"Error extracting text: {str(e)}" print(error_msg) return "" def play_chess(): board = chess.Board() return board def run_code(code: str): return exec(code) # Initialize the tool get_file_path_tool = Tool( name="file_path_retriever", func=get_file_path, description="Retrieves path to the reference file." ) get_content_tool = Tool( name="ref_content_retriever", func=get_ref_content, description="Retrieves reference file content." ) search_web_tool = Tool( name="search_web_retriever", func=search_web, description="Retrieves online info about a specific topic." ) extract_text_tool = Tool( name="extract_text_retriever", func=extract_text_from_image, description="Retrieves text from an image." ) play_chess_tool = Tool( name="chess_board_retriever", func=play_chess, description="Sets a chess board." ) run_code_tool = Tool( name="run_code_retriever", func=run_code, description="Executes a python code." ) # Generate the AgentState and Agent graph class AgentState(TypedDict): messages: Annotated[list[AnyMessage], add_messages] def build_agent(chat): tools = [get_file_path_tool, get_content_tool, search_web_tool, extract_text_tool, play_chess_tool, run_code_tool] chat_with_tools = chat.bind_tools(tools, parallel_tool_calls=False) # The graph builder = StateGraph(AgentState) def assistant(state: AgentState): return { "messages": chat.invoke(state["messages"]), } # Define nodes: these do the work builder.add_node("assistant", assistant) builder.add_node("tools", ToolNode([get_file_path_tool])) # 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") alfred = builder.compile() return alfred class BasicAgent: def __init__(self): print("BasicAgent initialized.") def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") system_prompt = SystemMessage( content="You are a general AI assistant. \ I will ask you a question. Report your thoughts shortly, and finish your answer with the following template: \ FINAL ANSWER: YOUR FINAL ANSWER \ YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. \ If you are asked for a number, use only digits in your final answer. Don't use comma nor brackets to write your number neither use units such as $ or percent sign unless specified otherwise. \ If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. \ If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string. \ If there is a file attached, open the file and read it. \ If you don't have enough references to answer, use your tools, search the web, run your code or convert data to a data frame, whatever helps. \ If the question refers to an external content and there is no reference file attached, perform a web search and retrieve relevant information from the internet. \ If there is a code, execute it. \ Make sure that each final answer is preceded with 'FINAL ANSWER:' and is short: it should contain a number (without full stop at the end), a string (one or two words only, without full stop at the end) or a comma-separated list (without full stops at the end), nothing else. " ) message = HumanMessage(content=question) print(message) answer = None wrong_answers = ["Requests rate limit exceeded", "", " ", " ", "insufficient information"] while not answer or answer in wrong_answers or answer.lower().startswith("error"): try: alfred = build_agent(chat1) answer = alfred.invoke(input={"messages": [system_prompt, message]},config={"recursion_limit": 6})['messages'][-1].content except: alfred = build_agent(chat2) answer = alfred.invoke(input={"messages": [system_prompt, message]},config={"recursion_limit": 6})['messages'][-1].content if answer: answer_fin = "".join(re.findall(r'(FINAL ANSWER.*)', answer, flags=re.M)) answer_fin = answer_fin.replace('FINAL ANSWER:', '') answer_fin = answer_fin.replace('FINAL ANSWER', '') answer_fin = answer_fin.replace('YOUR ', '') answer_fin = answer_fin.replace('*', '') print(f"Agent returning fixed answer: {answer_fin}") return answer_fin 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 ( useful 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...") 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: 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: 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 separate 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)