Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| from smolagents import FinalAnswerTool, Tool, tool, OpenAIServerModel, DuckDuckGoSearchTool, CodeAgent, VisitWebpageTool | |
| from dotenv import load_dotenv | |
| load_dotenv() | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| OPENAI_TOKEN = os.getenv("OPENAPI_KEY") | |
| # --- Basic Agent Definition --- | |
| # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ | |
| class SlpMultiAgent: | |
| def __init__(self): | |
| print("BasicAgent initialized.") | |
| def __call__(self, question: str) -> str: | |
| print(f"Agent received question (first 50 chars): {question[:50]}...") | |
| fixed_answer = "This is a default answer." | |
| print(f"Agent returning fixed answer: {fixed_answer}") | |
| # Increase max_tokens to allow for complete responses | |
| model = OpenAIServerModel( | |
| model_id="gpt-3.5-turbo", | |
| temperature=0.0, | |
| max_tokens=1500 | |
| ) | |
| # Here you can implement your agent logic, tools, and model calls | |
| web_agent = CodeAgent( | |
| tools=[DuckDuckGoSearchTool(), VisitWebpageTool()], | |
| model=model, | |
| additional_authorized_imports=["pandas"], | |
| max_steps=10, | |
| name="WebAgent", | |
| verbosity_level=0, | |
| description="An agent that can search the web, visit webpages, and calculate cargo travel times between locations." | |
| ) | |
| manager_agent = CodeAgent( | |
| model=OpenAIServerModel("gpt-3.5-turbo"), | |
| tools=[], | |
| managed_agents=[web_agent], | |
| name="ManagerAgent", | |
| description="A manager agent that can delegate tasks to other agents and manage their execution.", | |
| additional_authorized_imports=[ | |
| "pandas", | |
| ], | |
| planning_interval=5, | |
| verbosity_level=2, | |
| max_steps=15, | |
| final_answer_checks=[check_reasoning] | |
| ) | |
| manager_agent.run(""" | |
| You are a question answering agent. That specializes in complex questions that require multiple steps to answer. | |
| Take a few steps and think about the question before answering. | |
| You can use the tools available to you, but you should not use them unless necessary. | |
| You should always try to answer the question using your own knowledge and reasoning. | |
| If you need to use a tool, you should explain why you are using it and what you expect to find. | |
| If you are not sure about something, you should say so and explain why you are not sure. | |
| You should always try to provide a complete and accurate answer to the question. | |
| If you are not able to answer the question, you should say so and explain why | |
| Never try to process strings using code: when you have a string to read, just print it and you'll see it. | |
| Here is the question: {question} | |
| Thoughts: [your reasoning about how to solve the problem] | |
| Code: | |
| ```py | |
| # Your Python code here | |
| ```<end_code> | |
| The code block MUST start with ```py on its own line and end with ```<end_code> on its own line. | |
| """) | |
| return fixed_answer | |
| def check_reasoning(final_answer, agent_memory): | |
| multimodal_model = OpenAIServerModel("gpt-4", | |
| max_tokens=1500) | |
| prompt = ( | |
| f"Here is a user-given task and the agent steps: {agent_memory.get_succinct_steps()}. Now here is the plot that was made." | |
| "Please check that the reasoning process and plot are correct: do they correctly answer the given task?" | |
| "First list reasons why yes/no, then write your final decision: PASS in caps lock if it is satisfactory, FAIL if it is not." | |
| "Don't be harsh: if the plot mostly solves the task, it should pass." | |
| "To pass the question should be answered correctly and the reasoning should be sound." | |
| "The final answer is: {final_answer}. " | |
| ) | |
| messages = [ | |
| { | |
| "role": "user", | |
| "content": [ | |
| { | |
| "type": "text", | |
| "text": prompt, | |
| } | |
| ], | |
| } | |
| ] | |
| output = multimodal_model(messages).content | |
| print("Reasoning and plot check output:", output) | |
| if "fail" in output.lower(): | |
| print("Reasoning check failed. Please review the agent's reasoning.") | |
| 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 = SlpMultiAgent() | |
| 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) |