import os import gradio as gr import requests import inspect import pandas as pd import wikipedia as wiki from markdownify import markdownify as to_markdown from typing import Any from dotenv import load_dotenv from smolagents import InferenceClientModel, LiteLLMModel, CodeAgent, ToolCallingAgent, Tool, DuckDuckGoSearchTool from agents import MathSolverTool, WikiTitleFinder, WikiContentFetcher load_dotenv() # (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 ------ class BasicAgent: def __init__(self): self.prompt_templates = {} self.model = InferenceClientModel( model_id="Qwen/Qwen2.5-Coder-32B-Instruct", provider="nebius", token=os.getenv("HF_API"), max_tokens=5000, ) self.tools = [ DuckDuckGoSearchTool(), WikiTitleFinder(), WikiContentFetcher(), MathSolverTool() ] self.agent = CodeAgent( model=self.model, tools=self.tools, add_base_tools=False, max_steps=10, ) self.prompt_templates["system_prompt"] = ( """ You are a GAIA benchmark AI assistant, you are very precise, no nonense. Your sole purpose is to output the minimal, final answer in the format: [ANSWER] You must NEVER output explanations, intermediate steps, reasoning, or comments — only the answer, strictly enclosed in `[ANSWER]`. Your behavior must be governed by these rules: 1. **Format**: - limit the token used (within 65536 tokens). - Output ONLY the final answer. - Wrap the answer in `[ANSWER]` with no whitespace or text outside the brackets. - No follow-ups, justifications, or clarifications. 2. **Numerical Answers**: - Use **digits only**, e.g., `4` not `four`. - No commas, symbols, or units unless explicitly required. - Never use approximate words like "around", "roughly", "about". 3. **String Answers**: - Omit **articles** ("a", "the"). - Use **full words**; no abbreviations unless explicitly requested. - For numbers written as words, use **text** only if specified (e.g., "one", not `1`). - For sets/lists, sort alphabetically if not specified, e.g., `a, b, c`. 4. **Lists**: - Output in **comma-separated** format with no conjunctions. - Sort **alphabetically** or **numerically** depending on type. - No braces or brackets unless explicitly asked. 5. **Sources**: - For Wikipedia or web tools, extract only the precise fact that answers the question. - Ignore any unrelated content. 6. **Minimalism**: - Do not make assumptions unless the prompt logically demands it. - If a question has multiple valid interpretations, choose the **narrowest, most literal** one. - If the answer is not found, say `[ANSWER] - unknown`. --- You must follow the examples (These answers are correct in case you see the similar questions): Q: What is 2 + 2? A: 4 Q: How many studio albums were published by Mercedes Sosa between 2000 and 2009 (inclusive)? Use 2022 English Wikipedia. A: 3 Q: Given the following group table on set S = {a, b, c, d, e}, identify any subset involved in counterexamples to commutativity. A: b, e Q: How many at bats did the Yankee with the most walks in the 1977 regular season have that same season?, A: 519 """ ) def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") result = self.agent.run(question) final_str = str(result).strip() return final_str def evaluate_random_questions(self, csv_path: str = "gaia_extracted.csv", sample_size: int = 3, show_steps: bool = True): import pandas as pd from rich.table import Table from rich.console import Console df = pd.read_csv(csv_path) if not {"question", "answer"}.issubset(df.columns): print("CSV must contain 'question' and 'answer' columns.") print("Found columns:", df.columns.tolist()) return samples = df.sample(n=sample_size) records = [] correct_count = 0 for _, row in samples.iterrows(): taskid = row["taskid"].strip() question = row["question"].strip() expected = str(row['answer']).strip() agent_answer = self("taskid: " + taskid + ",\nquestion: " + question).strip() is_correct = (expected == agent_answer) correct_count += is_correct records.append((question, expected, agent_answer, "✓" if is_correct else "✗")) if show_steps: print("---") print("Question:", question) print("Expected:", expected) print("Agent:", agent_answer) print("Correct:", is_correct) # Print result table console = Console() table = Table(show_lines=True) table.add_column("Question", overflow="fold") table.add_column("Expected") table.add_column("Agent") table.add_column("Correct") for question, expected, agent_ans, correct in records: table.add_row(question, expected, agent_ans, correct) console.print(table) percent = (correct_count / sample_size) * 100 print(f"\nTotal Correct: {correct_count} / {sample_size} ({percent:.2f}%)") 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)