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 duckduckgo_search import DDGS import wikipedia import arxiv from transformers import pipeline import os import re import ast import subprocess import sys # ===== Search Tools ===== class DuckDuckGoSearchTool: def __init__(self, max_results=3): self.description = "Search web using DuckDuckGo. Input: search query" self.max_results = max_results def run(self, query: str) -> str: try: with DDGS() as ddgs: results = [r for r in ddgs.text(query, max_results=self.max_results)] return "\n\n".join( f"Title: {res['title']}\nURL: {res['href']}\nSnippet: {res['body']}" for res in results ) except Exception as e: return f"Search error: {str(e)}" class WikiSearchTool: def __init__(self, sentences=3): self.description = "Get Wikipedia summaries. Input: search phrase" self.sentences = sentences def run(self, query: str) -> str: try: return wikipedia.summary(query, sentences=self.sentences) except wikipedia.DisambiguationError as e: return f"Disambiguation error. Options: {', '.join(e.options[:5])}" except wikipedia.PageError: return "Page not found" except Exception as e: return f"Wikipedia error: {str(e)}" class ArxivSearchTool: def __init__(self, max_results=3): self.description = "Search academic papers on arXiv. Input: search query" self.max_results = max_results def run(self, query: str) -> str: try: results = arxiv.Search( query=query, max_results=self.max_results, sort_by=arxiv.SortCriterion.Relevance ).results() output = [] for r in results: output.append( f"Title: {r.title}\n" f"Authors: {', '.join(a.name for a in r.authors)}\n" f"Published: {r.published.strftime('%Y-%m-%d')}\n" f"Summary: {r.summary[:250]}...\n" f"URL: {r.entry_id}" ) return "\n\n".join(output) except Exception as e: return f"arXiv error: {str(e)}" # ===== QA Tools ===== class HuggingFaceDocumentQATool: def __init__(self): self.description = "Answer questions from documents. Input: 'document_text||question'" self.model = pipeline( 'question-answering', model='deepset/roberta-base-squad2', tokenizer='deepset/roberta-base-squad2' ) def run(self, input_str: str) -> str: try: if '||' not in input_str: return "Invalid format. Use: 'document_text||question'" context, question = input_str.split('||', 1) result = self.model(question=question, context=context) return result['answer'] except Exception as e: return f"QA error: {str(e)}" # ===== Code Execution ===== class PythonCodeExecutionTool: def __init__(self): self.description = "Execute Python code. Input: valid Python code" def run(self, code: str) -> str: try: # Isolate code in a clean environment env = {} exec(f"def __temp_func__():\n {indent_code(code)}", env) output = env['__temp_func__']() return str(output) except Exception as e: return f"Execution error: {str(e)}" def indent_code(code: str) -> str: """Add proper indentation for multiline code""" return '\n '.join(code.splitlines()) # ===== Answer Formatting ===== class FinalAnswerTool: def __init__(self): self.description = "Format final answer. Input: answer content" def run(self, answer: str) -> str: return f"FINAL ANSWER: {answer}" class BasicAgent: def __init__(self): token = os.environ.get("HF_API_TOKEN") model = HfApiModel( temperature=0.0, # Reduced for deterministic output token=token ) # Curated toolset - remove redundant/conflicting tools search_tool = DuckDuckGoSearchTool() wiki_search_tool = WikiSearchTool() arxiv_search_tool = ArxivSearchTool() doc_qa_tool = HuggingFaceDocumentQATool() python_tool = PythonCodeExecutionTool() final_answer_tool = FinalAnswerTool() # Strategic tool selection tools = [ search_tool, wiki_search_tool, arxiv_search_tool, doc_qa_tool, python_tool, final_answer_tool ] # Enhanced system prompt system_prompt = """ You are a precision question-answering AI. Follow this protocol: 1. Analyze the question type: factual, computational, or multi-step 2. Select the optimal tool: - Use Search/Wiki/Arxiv for factual queries - Use Python tool for calculations - Use DocQA for document-based questions 3. Execute necessary actions 4. Verify answer matches question requirements 5. Output FINAL ANSWER using this format: "FINAL ANSWER: [EXACT_RESULT]" Answer rules: - Numbers: Plain format (e.g., 1000000) - Strings: No articles/abbreviations (e.g., "Paris" not "city of Paris") - Lists: Comma-separated (e.g., "red,blue,green") - Never include units ($, kg, etc.) unless explicitly required - For true/false: Use "true" or "false" lowercase """ self.agent = CodeAgent( model=model, tools=tools, add_base_tools=False # Prevent tool conflicts ) # Force strict prompt template self.agent.prompt_templates["system_prompt"] = system_prompt def __call__(self, question: str) -> str: print(f"Processing: {question[:50]}...") try: result = self.agent.run(question) # Extract final answer using regex import re match = re.search(r"FINAL ANSWER:\s*(.+)", result, re.IGNORECASE) return match.group(1).strip() if match else result except Exception as e: print(f"Error: {str(e)}") return "Unable to determine answer" 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)