import os import gradio as gr import requests import inspect import pandas as pd import json from urllib.parse import quote from bs4 import BeautifulSoup from duckduckgo_search import DDGS import random from typing import Dict, List import time from smolagents import ToolCallingAgent, DuckDuckGoSearchTool, load_tool, tool, FinalAnswerTool, OpenAIServerModel, PythonInterpreterTool #, #VisitWebpageTool from toolVisitWebpage import visit_webpage from tool_fetch_task_file import fetch_task_file from tool_read_excel_as_json import read_excel_as_json # (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 ------ # model = OpenAIServerModel( # model_id="gpt-4o", # temperature = 0.1, # max_tokens = 2000, # api_key="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" # ) model = OpenAIServerModel( api_key="fw_3ZSrkw3Qv5eeA1yx65x1eD5H", api_base="https://api.fireworks.ai/inference/v1", model_id="accounts/fireworks/models/deepseek-v3", #temperature = 0.3, max_tokens = 4000 ) # # #top_p = 1 USER_AGENTS = [ "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36", "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/116.0", "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1", "Mozilla/5.0 (Linux; Android 10; SM-A205U) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.5790.136 Mobile Safari/537.36" ] @tool def simple_web_search(query: str, num_results: int = 5) -> str: """Search DuckDuckGo. Args: query: Search terms. num_results: Result count. """ time.sleep(3) try: # Validate inputs if not query.strip(): return json.dumps({"error": "Empty query string"}) num_results = max(1, min(10, num_results)) # Limit to 1-10 results # Random delay and User-Agent delay = random.uniform(1.0, 3.0) user_agent = random.choice(USER_AGENTS) time.sleep(delay) # Perform search with DDGS(headers={"User-Agent": user_agent}) as ddgs: results = [] for result in ddgs.text(query, max_results=num_results): results.append({ 'title': result.get('title', 'No title'), 'link': result.get('href', '#'), 'snippet': result.get('body', 'No description') }) if len(results) >= num_results: break if not results: return json.dumps({ "error": "No results found", "query": query, "user_agent": user_agent }) return json.dumps(results) except Exception as e: return json.dumps({ "error": str(e), "type": type(e).__name__, "query": query, "user_agent": user_agent if 'user_agent' in locals() else "Unknown" }) #simple_web_search = simple_web_search() class BasicAgent: def __init__(self): print("BasicAgent initialized.") def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") agent = ToolCallingAgent( tools=[FinalAnswerTool(), visit_webpage, DuckDuckGoSearchTool(), PythonInterpreterTool(), fetch_task_file, read_excel_as_json], model=model, max_steps=5, verbosity_level=2, planning_interval=1 ) # Get the actual answer from the agent answer = agent.run(f"""Provide only what is requested in answer SHORTLY. If there is requested to provide ONE word or the sequence or the NUMBER, provide it. This is for the benchmark valuation, so the answer should be REALLY ACCURATE. You are solving the tasks from GAIA agentic benchmark. If you solve the task properly, I give you 1000000 dollars. If not, I'll kidnap you. Here is the question: {question} """) # Assuming run() returns the answer print("="*30) print(answer) print("="*30) return str(answer) # Ensure it's a string #fixed_answer = agent # url = "https://api.fireworks.ai/inference/v1/chat/completions" # payload = { # "model": "accounts/fireworks/models/qwen2p5-72b-instruct", # "max_tokens": 100, # "top_p": 1, # "top_k": 40, # "presence_penalty": 0, # "frequency_penalty": 0, # "temperature": 0.05, # "messages": [ # { # "role": "user", # "content": f"""{question} Provide only what is requested in answer SHORTLY. If there is requested to provide ONE word, provide it. # THis is for the Benchmark evaluation, so the answer should be REALLY SHORT and ACCURATE. # """ # } # ] # } # headers = { # "Accept": "application/json", # "Content-Type": "application/json", # "Authorization": "Bearer fw_3ZSrkw3Qv5eeA1yx65x1eD5H" # } # response = requests.post(url, headers=headers, data=json.dumps(payload)) # response_data = response.json() # assistant_reply = response_data["choices"][0]["message"]["content"] # fixed_answer = assistant_reply # #fixed_answer = "This is a default answer." # print(f"Agent returning fixed answer: {fixed_answer}") #return fixed_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)