Spaces:
Starting
Starting
| import os | |
| from dotenv import load_dotenv | |
| import gradio as gr | |
| import requests | |
| from typing import List, Dict, Union | |
| import pandas as pd | |
| import wikipediaapi | |
| import requests | |
| import requests | |
| from bs4 import BeautifulSoup | |
| import random | |
| import re | |
| from typing import Optional | |
| load_dotenv() | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # --- Basic Agent Definition --- | |
| class BasicAgent: | |
| def __init__(self): | |
| self.headers = { | |
| 'User-Agent': random.choice([ | |
| 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36', | |
| 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15) AppleWebKit/605.1.15' | |
| ]), | |
| 'Accept-Language': 'en-US,en;q=0.9' | |
| } | |
| self.answer_patterns = [ | |
| (r'(?:is|are|was|were) (?:about|approximately)? (\d+[\d,\.]+\s*\w+)', 0), # Quantities | |
| (r'(?:is|are) (.{5,30}?\b(?:ing|tion|ment)\b)', 1), # Definitions | |
| (r'\b(?:located in|found in|from) (.{10,30})', 1), # Locations | |
| (r'\b(?:born on|died on) (.{8,15}\d{4})', 1) # Dates | |
| ] | |
| def __call__(self, query: str) -> str: | |
| """Get concise answer with improved accuracy""" | |
| try: | |
| # Try Google's direct answer boxes first | |
| direct_answer = self._get_direct_answer(query) | |
| if direct_answer and len(direct_answer.split()) <= 8: | |
| return self._clean_answer(direct_answer) | |
| # Fallback to featured snippet extraction | |
| snippet = self._get_featured_snippet(query) | |
| if snippet: | |
| best_answer = self._extract_best_fragment(snippet, query) | |
| if best_answer: | |
| return best_answer | |
| # Final fallback to first result summary | |
| return self._get_first_result_summary(query) or "No concise answer found" | |
| except Exception: | |
| return "Search error" | |
| def _get_direct_answer(self, query: str) -> Optional[str]: | |
| """Extract Google's instant answer""" | |
| url = f"https://www.google.com/search?q={requests.utils.quote(query)}" | |
| html = requests.get(url, headers=self.headers, timeout=3).text | |
| soup = BeautifulSoup(html, 'html.parser') | |
| for selector in ['.LGOjhe', '.kno-rdesc span', '.hgKElc', '.Z0LcW']: | |
| element = soup.select_one(selector) | |
| if element: | |
| return element.get_text() | |
| return None | |
| def _get_featured_snippet(self, query: str) -> Optional[str]: | |
| """Get featured snippet text""" | |
| url = f"https://www.google.com/search?q={requests.utils.quote(query)}" | |
| html = requests.get(url, headers=self.headers, timeout=3).text | |
| soup = BeautifulSoup(html, 'html.parser') | |
| snippet = soup.select_one('.xpdopen .kno-rdesc span, .ifM9O') | |
| return snippet.get_text() if snippet else None | |
| def _extract_best_fragment(self, text: str, query: str) -> Optional[str]: | |
| """Extract most relevant sentence fragment""" | |
| sentences = re.split(r'[\.\!\?]', text) | |
| query_words = set(query.lower().split()) | |
| for pattern, group_idx in self.answer_patterns: | |
| for sentence in sentences: | |
| match = re.search(pattern, sentence, re.IGNORECASE) | |
| if match: | |
| return self._clean_answer(match.group(group_idx)) | |
| # Fallback to shortest meaningful sentence | |
| return min([s.strip() for s in sentences if 5 < len(s.split()) < 15], | |
| key=len, default=None) | |
| def _get_first_result_summary(self, query: str) -> Optional[str]: | |
| """Extract summary from first result""" | |
| url = f"https://www.google.com/search?q={requests.utils.quote(query)}" | |
| html = requests.get(url, headers=self.headers, timeout=3).text | |
| soup = BeautifulSoup(html, 'html.parser') | |
| first_result = soup.select_one('.tF2Cxc') | |
| if first_result: | |
| snippet = first_result.select_one('.IsZvec, .VwiC3b') | |
| return self._clean_answer(snippet.get_text()) if snippet else None | |
| return None | |
| def _clean_answer(self, text: str) -> str: | |
| """Clean and shorten the answer""" | |
| text = re.sub(r'\[\d+\]', '', text) # Remove citations | |
| text = re.sub(r'\s+', ' ', text).strip() | |
| return text[:120] # Limit length | |
| 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) |