Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| import time | |
| import json | |
| from typing import Dict, List, Union, Optional | |
| # (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): | |
| print("BasicAgent initialized.") | |
| # Initialize the Hugging Face API client | |
| self.hf_api_url = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct" | |
| self.hf_api_token = os.getenv("HF_API_TOKEN") | |
| if not self.hf_api_token: | |
| print("WARNING: HF_API_TOKEN not found. Using default fallback methods.") | |
| self.headers = {"Authorization": f"Bearer {self.hf_api_token}"} if self.hf_api_token else {} | |
| self.max_retries = 3 | |
| self.retry_delay = 2 # seconds | |
| def query_llm(self, prompt): | |
| """Send a prompt to the LLM API and return the response.""" | |
| if not self.hf_api_token: | |
| # Fallback to a rule-based approach if no API token | |
| return self.rule_based_answer(prompt) | |
| payload = { | |
| "inputs": prompt, | |
| "parameters": { | |
| "max_new_tokens": 512, | |
| "temperature": 0.7, | |
| "top_p": 0.9, | |
| "do_sample": True | |
| } | |
| } | |
| for attempt in range(self.max_retries): | |
| try: | |
| response = requests.post(self.hf_api_url, headers=self.headers, json=payload, timeout=30) | |
| response.raise_for_status() | |
| result = response.json() | |
| # Extract the generated text from the response | |
| if isinstance(result, list) and len(result) > 0: | |
| generated_text = result[0].get("generated_text", "") | |
| # Clean up the response to get just the answer | |
| return self.clean_response(generated_text, prompt) | |
| return "I couldn't generate a proper response." | |
| except Exception as e: | |
| print(f"Attempt {attempt+1}/{self.max_retries} failed: {str(e)}") | |
| if attempt < self.max_retries - 1: | |
| time.sleep(self.retry_delay) | |
| else: | |
| # Fall back to rule-based method on failure | |
| return self.rule_based_answer(prompt) | |
| def clean_response(self, response, prompt): | |
| """Clean up the LLM response to extract the answer.""" | |
| # Remove the prompt from the beginning if it's included | |
| if response.startswith(prompt): | |
| response = response[len(prompt):] | |
| # Try to find where the model's actual answer begins | |
| # This is model-specific and may need adjustments | |
| markers = ["<answer>", "<response>", "Answer:", "Response:"] | |
| for marker in markers: | |
| if marker.lower() in response.lower(): | |
| parts = response.lower().split(marker.lower(), 1) | |
| if len(parts) > 1: | |
| response = parts[1].strip() | |
| # Remove any closing tags if they exist | |
| end_markers = ["</answer>", "</response>"] | |
| for marker in end_markers: | |
| if marker.lower() in response.lower(): | |
| response = response.lower().split(marker.lower())[0].strip() | |
| return response.strip() | |
| def rule_based_answer(self, question): | |
| """Fallback method using rule-based answers for common question types.""" | |
| question_lower = question.lower() | |
| # Simple pattern matching for common question types | |
| if "what is" in question_lower or "define" in question_lower: | |
| if "agent" in question_lower: | |
| return "An agent is an autonomous entity that observes and acts upon an environment using sensors and actuators, usually to achieve specific goals." | |
| if "gaia" in question_lower: | |
| return "GAIA (General AI Assistant) is a framework for creating and evaluating AI assistants that can perform a wide range of tasks." | |
| if "how to" in question_lower: | |
| return "To accomplish this task, you should first understand the requirements, then implement a solution step by step, and finally test your implementation." | |
| if "example" in question_lower: | |
| return "Here's an example implementation that demonstrates the concept in a practical manner." | |
| # Default response for unmatched questions | |
| return "Based on my understanding, the answer involves analyzing the context carefully and applying the relevant principles to arrive at a solution." | |
| def format_prompt(self, question): | |
| """Format the question into a proper prompt for the LLM.""" | |
| return f"""You are an intelligent AI assistant. Please answer the following question accurately and concisely: | |
| Question: {question} | |
| Answer:""" | |
| def __call__(self, question: str) -> str: | |
| print(f"Agent received question (first 50 chars): {question[:50]}...") | |
| try: | |
| # Format the question as a prompt | |
| prompt = self.format_prompt(question) | |
| # Query the LLM | |
| answer = self.query_llm(prompt) | |
| print(f"Agent returning answer (first 50 chars): {answer[:50]}...") | |
| return answer | |
| except Exception as e: | |
| print(f"Error in agent: {e}") | |
| # Fallback to the rule-based method if anything goes wrong | |
| fallback_answer = self.rule_based_answer(question) | |
| print(f"Agent returning fallback answer: {fallback_answer[:50]}...") | |
| return fallback_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) |