import os import gradio as gr import requests import inspect import pandas as pd from smolagents import tool, Tool, CodeAgent, DuckDuckGoSearchTool, HfApiModel, VisitWebpageTool, SpeechToTextTool, FinalAnswerTool from dotenv import load_dotenv import heapq from collections import Counter import re from io import BytesIO from youtube_transcript_api import YouTubeTranscriptApi from langchain_community.tools.tavily_search import TavilySearchResults from langchain_community.document_loaders import WikipediaLoader from langchain_community.utilities import WikipediaAPIWrapper from langchain_community.document_loaders import ArxivLoader # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" #Load environment variables load_dotenv() from langgraph.graph import END, StateGraph from langchain_core.prompts import ChatPromptTemplate from langchain_core.messages import HumanMessage, AIMessage, ToolMessage from langchain_core.tools import tool from typing import Dict, List, TypedDict, Annotated import operator from langchain_community.llms import HuggingFaceHub from langchain_community.chat_models import ChatHuggingFace from langchain.schema import HumanMessage # Or your framework's equivalent def init_state(question: str): return { "question": question, "history": [HumanMessage(content=question)], "context": {} # <- Add this line } # ====== Tool Definitions ====== @tool def duckduckgo_search(query: str) -> str: """Search web using DuckDuckGo. Returns top 3 results.""" from duckduckgo_search import DDGS with DDGS() as ddgs: return "\n\n".join( f"Title: {res['title']}\nURL: {res['href']}\nSnippet: {res['body']}" for res in ddgs.text(query, max_results=3) ) @tool def wikipedia_search(query: str) -> str: """Get Wikipedia summaries. Returns first 3 sentences.""" import wikipedia try: return wikipedia.summary(query, sentences=3) except wikipedia.DisambiguationError as e: return f"Disambiguation options: {', '.join(e.options[:3])}" except wikipedia.PageError: return "Page not found" @tool def arxiv_search(query: str) -> str: """Search academic papers on arXiv. Returns top 3 results.""" import arxiv results = arxiv.Search( query=query, max_results=3, sort_by=arxiv.SortCriterion.Relevance ).results() return "\n\n".join( f"Title: {r.title}\nAuthors: {', '.join(a.name for a in r.authors)}\n" f"Published: {r.published.strftime('%Y-%m-%d')}\nSummary: {r.summary[:250]}..." for r in results ) @tool def document_qa(input_str: str) -> str: """Answer questions from documents. Input format: 'document_text||question'""" from transformers import pipeline if '||' not in input_str: return "Invalid format. Use: 'document_text||question'" context, question = input_str.split('||', 1) qa_model = pipeline('question-answering', model='deepset/roberta-base-squad2') return qa_model(question=question, context=context)['answer'] @tool def python_execution(code: str) -> str: """Execute Python code and return output.""" try: # Create isolated environment env = {} exec(f"def __exec_fn__():\n {indent_code(code)}\nresult = __exec_fn__()", env) return str(env.get('result', 'No output')) except Exception as e: return f"Error: {str(e)}" def indent_code(code: str) -> str: return '\n '.join(code.splitlines()) # ====== Agent State ====== class AgentState(TypedDict): question: str history: Annotated[List[Dict], operator.add] context: str reasoning: str iterations: int # ====== Graph Components ====== def init_state(question: str) -> AgentState: return { "question": question, "history": [], "context": f"User question: {question}", "reasoning": "", "iterations": 0 } def should_continue(state: AgentState) -> str: """Determine if agent should continue or finish""" last_msg = state['history'][-1] # Stop conditions if state['iterations'] >= 5: return "end" if "FINAL ANSWER:" in last_msg.get('content', ''): return "end" if last_msg['role'] == 'tool': return "reason" return "continue" def reasoning_node(state: AgentState) -> AgentState: """Agent reasoning and tool selection""" # Get Hugging Face API token from environment token = os.environ.get("HF_TOKEN") if not token: raise ValueError("Hugging Face API token not found in environment variables") history = state["history"] # FIX: Add a HumanMessage if the last message is not one if not isinstance(history[-1], HumanMessage): raise ValueError("Last message in history must be a HumanMessage") # Create the underlying LLM model llm = HuggingFaceHub( repo_id="HuggingFaceH4/zephyr-7b-beta", huggingfacehub_api_token=token, model_kwargs={ "temperature": 0.1, "max_new_tokens": 500 } ) # Wrap the LLM in ChatHuggingFace chat_model = ChatHuggingFace(llm=llm) # Build prompt prompt = ChatPromptTemplate.from_messages([ ("system", ( "You're an expert problem solver. Analyze the question, select the best tool, " "and provide reasoning. Available tools: duckduckgo_search, wikipedia_search, " "arxiv_search, document_qa, python_execution.\n\n" "Current Context:\n{context}\n\n" "Reasoning Steps:\n{reasoning}\n\n" "Response Format:\nReasoning: [Your analysis]\nAction: [Tool name OR 'Final Answer']\n" "Action Input: [Input for tool OR final response]" )), *state['history'] ]) chain = prompt | chat_model response = chain.invoke({ "context": state['context'], "reasoning": state['reasoning'], "question": state['question'] }) # Parse response content = response.content reasoning, action, action_input = parse_agent_response(content) # Update state state['history'].append(AIMessage(content=content)) state['reasoning'] += f"\nStep {state['iterations']+1}: {reasoning}" if "final answer" in action.lower(): state['history'].append(AIMessage(content=f"FINAL ANSWER: {action_input}")) else: state['history'].append({ "tool": action, "input": action_input, "role": "action_request" }) return state def tool_node(state: AgentState) -> AgentState: """Execute selected tool and update state""" last_action = state['history'][-1] tool_name = last_action['tool'] tool_input = last_action['input'] # Tool mapping tools = { "duckduckgo_search": duckduckgo_search, "wikipedia_search": wikipedia_search, "arxiv_search": arxiv_search, "document_qa": document_qa, "python_execution": python_execution } # Execute tool tool_result = tools[tool_name].invoke(tool_input) # Update state state['history'].append(ToolMessage( content=tool_result, tool_call_id=tool_name )) state['context'] = f"Tool Result ({tool_name}): {tool_result}" state['iterations'] += 1 return state def parse_agent_response(response: str) -> tuple: """Extract reasoning, action, and input from response""" reasoning = response.split("Reasoning:")[1].split("Action:")[0].strip() action_part = response.split("Action:")[1].strip() if "Action Input:" in action_part: action, action_input = action_part.split("Action Input:", 1) action = action.strip() action_input = action_input.strip() else: action = action_part action_input = "" return reasoning, action, action_input # ====== Agent Graph ====== def create_agent_workflow(): workflow = StateGraph(AgentState) # Define nodes workflow.add_node("reason", reasoning_node) workflow.add_node("action", tool_node) # Set entry point workflow.set_entry_point("reason") # Define edges workflow.add_conditional_edges( "reason", should_continue, { "continue": "action", "reason": "reason", "end": END } ) workflow.add_edge("action", "reason") return workflow.compile() # ====== Agent Interface ====== class BasicAgent: def __init__(self): self.workflow = create_agent_workflow() self.tools = [ duckduckgo_search, wikipedia_search, arxiv_search, document_qa, python_execution ] def __call__(self, question: str) -> str: print(f"Agent received question: {question[:50]}{'...' if len(question) > 50 else ''}") # Ensure proper HumanMessage in history state = init_state(question) final_state = self.workflow.invoke(state) print(f"Final state keys: {list(final_state.keys())}") if 'history' in final_state: print(f"History length: {len(final_state['history'])}") for i, msg in enumerate(final_state['history']): print(f"Message {i}: {type(msg).__name__} - {msg.content[:100]}...") for msg in reversed(final_state['history']): if isinstance(msg, AIMessage) and "FINAL ANSWER:" in msg.content: answer = msg.content.split("FINAL ANSWER:")[1].strip() print(f"Agent returning answer: {answer}") return answer raise ValueError("No FINAL ANSWER found in agent history.") 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)