import os import gradio as gr import requests import inspect import pandas as pd from typing import TypedDict, Annotated, Sequence, Dict, Any, List, Optional from langchain_core.messages import BaseMessage, HumanMessage from langchain_core.tools import tool from langchain_openai import ChatOpenAI from langgraph.graph import END, StateGraph from langgraph.prebuilt import ToolNode from langchain_community.tools import DuckDuckGoSearchResults from langchain_community.utilities import WikipediaAPIWrapper from langchain.agents import create_tool_calling_agent, AgentExecutor from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder import operator from langchain_experimental.utilities import PythonREPL from functools import wraps import logging # (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 ------ # --- Configure logging --- logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" DEFAULT_MODEL = "gpt-3.5-turbo" MAX_RESPONSE_LENGTH = 2000 # Prevent overly long responses def handle_errors(func): """Decorator to handle common errors in agent operations.""" @wraps(func) def wrapper(*args, **kwargs): try: return func(*args, **kwargs) except Exception as e: logger.error(f"Error in {func.__name__}: {str(e)}") return {"error": str(e)} return wrapper class AgentState(TypedDict): messages: Annotated[Sequence[BaseMessage], operator.add] sender: str @tool def wikipedia_search(query: str) -> str: """Search Wikipedia for information. Useful for historical facts, scientific concepts, and general knowledge.""" try: return WikipediaAPIWrapper().run(query)[:MAX_RESPONSE_LENGTH] except Exception as e: return f"Wikipedia search failed: {str(e)}" @tool def web_search(query: str, num_results: int = 3) -> list: """Search the web for current information. Useful for news, recent events, and up-to-date data.""" try: results = DuckDuckGoSearchResults(num_results=num_results).run(query) return [str(r)[:500] for r in results][:num_results] # Limit result size except Exception as e: return [f"Web search failed: {str(e)}"] @tool def calculate(expression: str) -> str: """Evaluate mathematical expressions. Supports basic arithmetic and complex formulas.""" try: python_repl = PythonREPL() result = python_repl.run(expression) return str(result)[:100] # Limit numeric output length except Exception as e: return f"Calculation failed: {str(e)}" class BasicAgent: """An enhanced LangGraph agent with better error handling and response processing.""" def __init__(self, model_name: str = DEFAULT_MODEL, temperature: float = 0.7): """Initialize the agent with tools and workflow.""" self.model_name = model_name self.temperature = temperature self.tools = [wikipedia_search, web_search, calculate] self.llm = ChatOpenAI(model=model_name, temperature=temperature) self.agent_executor = self._build_agent_executor() self.workflow = self._build_workflow() logger.info(f"AdvancedAgent initialized with model: {model_name}") def _build_agent_executor(self) -> AgentExecutor: """Build the agent executor with proper prompt and tools.""" prompt = ChatPromptTemplate.from_messages([ ("system", self._get_system_prompt()), MessagesPlaceholder(variable_name="messages"), MessagesPlaceholder(variable_name="agent_scratchpad"), ]) agent = create_tool_calling_agent(self.llm, self.tools, prompt) return AgentExecutor( agent=agent, tools=self.tools, verbose=True, handle_parsing_errors=True ) def _get_system_prompt(self) -> str: """Return a comprehensive system prompt for the agent.""" return """You are an advanced AI assistant with access to tools. Follow these rules: 1. Be precise and factual 2. Use tools when needed 3. Cite your sources 4. Break complex problems into steps 5. Admit when you don't know something""" def _build_workflow(self) -> StateGraph: """Build and compile the agent workflow.""" workflow = StateGraph(AgentState) workflow.add_node("agent", self._run_agent) workflow.add_node("tools", ToolNode(self.tools)) workflow.set_entry_point("agent") workflow.add_conditional_edges( "agent", self._should_continue, {"continue": "tools", "end": END} ) workflow.add_edge("tools", "agent") return workflow.compile() @handle_errors def _run_agent(self, state: AgentState) -> Dict[str, Any]: """Execute the agent with error handling.""" response = self.agent_executor.invoke({"messages": state["messages"]}) return {"messages": [response["output"]]} def _should_continue(self, state: AgentState) -> str: """Determine if the workflow should continue based on tool calls.""" last_message = state["messages"][-1] return "continue" if last_message.additional_kwargs.get("tool_calls") else "end" @handle_errors def __call__(self, query: str) -> Dict[str, Any]: """Process a user query and return a structured response.""" if not query or len(query.strip()) == 0: return {"error": "Empty query provided"} logger.info(f"Processing query: {query[:50]}...") state = AgentState(messages=[HumanMessage(content=query)], sender="user") for output in self.workflow.stream(state): for key, value in output.items(): if key == "messages": for message in value: if isinstance(message, BaseMessage): response = message.content[:MAX_RESPONSE_LENGTH] return { "response": response, "sources": self._extract_sources(state["messages"]), "steps": self._extract_steps(state["messages"]), "model": self.model_name } return {"response": "No response generated", "sources": [], "steps": []} def _extract_sources(self, messages: Sequence[BaseMessage]) -> List[str]: """Extract and format sources from tool messages.""" sources = [] for msg in messages: if hasattr(msg, 'additional_kwargs') and 'name' in msg.additional_kwargs: source_name = msg.additional_kwargs.get('name', 'unknown') content = str(msg.content)[:200] # Truncate long content sources.append(f"{source_name}: {content}") return sources def _extract_steps(self, messages: Sequence[BaseMessage]) -> List[str]: """Extract and format the reasoning steps.""" steps = [] for msg in messages: if hasattr(msg, 'additional_kwargs') and 'tool_calls' in msg.additional_kwargs: for call in msg.additional_kwargs['tool_calls']: tool_name = call['function']['name'] args = call['function']['arguments'][:100] # Truncate long args steps.append(f"Used {tool_name} with args: {args}") return steps 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...") 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 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)