Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| from langgraph.prebuilt import ToolNode, tools_condition | |
| from langgraph.graph.message import add_messages | |
| from langchain_core.messages import AnyMessage, HumanMessage | |
| from langgraph.graph import START, StateGraph | |
| from langchain_google_genai import ChatGoogleGenerativeAI | |
| from ToolSet import toolset | |
| from utils.final_answer import extract_final_answer | |
| from utils.handle_file import handle_attachment | |
| from fetch_question import get_all_questions, get_one_random_question, submit | |
| # (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 ------ | |
| gemini_api_key = os.getenv("GEMINI_API_KEY") | |
| tivaly_api_key = os.getenv("TAVILY_API_KEY") | |
| llm = ChatGoogleGenerativeAI( | |
| model="gemini-2.0-flash", | |
| temperature=0, | |
| google_api_key = gemini_api_key | |
| ) | |
| llm_with_tools = llm.bind_tools(toolset) | |
| sys_prompt_file = open("sys_prompt.txt") | |
| sys_prompt = sys_prompt_file.read() | |
| class AgentState(TypedDict): | |
| messages: Annotated[list[AnyMessage], add_messages] | |
| def assistant(state: AgentState): | |
| return { | |
| "messages": [llm_with_tools.invoke([sys_prompt]+state["messages"])], | |
| } | |
| builder = StateGraph(AgentState) | |
| builder.add_node("assistant", assistant) | |
| builder.add_node("tools", ToolNode(available_tools)) | |
| builder.add_edge(START, "assistant") | |
| builder.add_conditional_edges( | |
| "assistant", | |
| tools_condition | |
| ) | |
| builder.add_edge("tools","assistant") | |
| gaia_agent = builder.compile() | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the agent on them, submits all answers, | |
| and displays the results. Handles attachments if present. | |
| """ | |
| # --- 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 | |
| # 1. Instantiate Agent (modify this part to create your agent) | |
| try: | |
| agent = my_agent | |
| 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 (useful for others so please keep it public) | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| print(agent_code) | |
| # 2. Fetch Questions | |
| questions_data = get_all_questions() | |
| # 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 | |
| # 2.2 Handle attachment if present | |
| attachment_info = None | |
| if "file_name" in item and item["file_name"]: | |
| file_name = item.get("file_name") | |
| attachment_info = handle_attachment(task_id, file_name) | |
| print(f"Attachment handling result: {attachment_info['status']}") | |
| try: | |
| # Prepare messages based on attachment handling | |
| messages = [ | |
| SystemMessage(content=SYSTEM_PROMPT), | |
| SystemMessage(content=f"Current task id: {task_id}") | |
| ] | |
| # If we have an attachment that Claude can process directly | |
| if attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "direct": | |
| # Encode content for direct inclusion | |
| encoded_content = base64.b64encode(attachment_info["raw_content"]).decode('utf-8') | |
| content_type = attachment_info["content_type"] | |
| # Create multimodal message | |
| if content_type.startswith('image/'): | |
| multimodal_content = [ | |
| {"type": "text", "text": question_text}, | |
| { | |
| "type": "image", | |
| "source": { | |
| "type": "base64", | |
| "media_type": content_type, | |
| "data": encoded_content | |
| } | |
| } | |
| ] | |
| elif content_type == "application/pdf" or "spreadsheet" in content_type or "excel" in content_type or "csv" in content_type: | |
| multimodal_content = [ | |
| {"type": "text", "text": question_text}, | |
| { | |
| "type": "file", | |
| "source": { | |
| "type": "base64", | |
| "media_type": content_type, | |
| "data": encoded_content | |
| }, | |
| "name": attachment_info["file_name"] | |
| } | |
| ] | |
| messages.append(HumanMessage(content=multimodal_content)) | |
| # If we have an attachment that needs tool processing | |
| elif attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "tool": | |
| # Add info about the file to the question | |
| file_info = ( | |
| f"{question_text}\n\n" | |
| f"Note: This task has an attached file that can be accessed at: {attachment_info['file_path']}\n" | |
| f"File type: {attachment_info['content_type']}" | |
| ) | |
| messages.append(HumanMessage(content=file_info)) | |
| # If no attachment or error with attachment | |
| else: | |
| messages.append(HumanMessage(content=question_text)) | |
| # Invoke the agent with the prepared messages | |
| agent_answer = agent.invoke({"messages": messages},{"recursion_limit": 50}) | |
| submitted_answer = extract_final_answer(agent_answer['messages'][-1].content) | |
| 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 | |
| return submit(submission_data, results_log) | |
| def run_and_submit_one( profile: gr.OAuthProfile | None): | |
| # --- 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 | |
| # 1. Instantiate Agent ( modify this part to create your agent) | |
| try: | |
| agent = my_agent | |
| 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 | |
| questions_data = get_one_random_question() | |
| print("questions_data:", questions_data) | |
| # 2.2 Handle attachment if present | |
| attachment_info = None | |
| if "file_name" in questions_data and questions_data["file_name"]: | |
| task_id = questions_data.get("task_id") | |
| file_name = questions_data.get("file_name") | |
| attachment_info = handle_attachment(task_id, file_name) | |
| print(f"Attachment handling result: {attachment_info['status']}") | |
| # 3. Run your Agent | |
| results_log = [] | |
| answers_payload = [] | |
| print(f"Running agent on {len(questions_data)} questions...") | |
| task_id = questions_data.get("task_id") | |
| question_text = questions_data.get("question") | |
| if not task_id or question_text is None: | |
| print(f"Skipping item with missing task_id or question") | |
| try: | |
| # Prepare messages based on attachment handling | |
| messages = [ | |
| SystemMessage(content=SYSTEM_PROMPT), | |
| SystemMessage(content=f"Current task id: {task_id}") | |
| ] | |
| # If we have an attachment that Claude can process directly | |
| if attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "direct": | |
| # Encode content for direct inclusion | |
| encoded_content = base64.b64encode(attachment_info["raw_content"]).decode('utf-8') | |
| content_type = attachment_info["content_type"] | |
| # Create multimodal message | |
| if content_type.startswith('image/'): | |
| multimodal_content = [ | |
| {"type": "text", "text": question_text}, | |
| { | |
| "type": "image", | |
| "source": { | |
| "type": "base64", | |
| "media_type": content_type, | |
| "data": encoded_content | |
| } | |
| } | |
| ] | |
| elif content_type == "application/pdf" or "spreadsheet" in content_type or "excel" in content_type or "csv" in content_type: | |
| multimodal_content = [ | |
| {"type": "text", "text": question_text}, | |
| { | |
| "type": "file", | |
| "source": { | |
| "type": "base64", | |
| "media_type": content_type, | |
| "data": encoded_content | |
| }, | |
| "name": attachment_info["file_name"] | |
| } | |
| ] | |
| messages.append(HumanMessage(content=multimodal_content)) | |
| # If we have an attachment that needs tool processing | |
| elif attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "tool": | |
| # Add info about the file to the question | |
| file_info = ( | |
| f"{question_text}\n\n" | |
| f"Note: This task has an attached file that can be accessed at: {attachment_info['file_path']}\n" | |
| f"File type: {attachment_info['content_type']}" | |
| ) | |
| messages.append(HumanMessage(content=file_info)) | |
| # If no attachment or error with attachment | |
| else: | |
| messages.append(HumanMessage(content=question_text)) | |
| # Invoke the agent with the prepared messages | |
| agent_answer = agent.invoke({"messages": messages},{"recursion_limit": 50}) | |
| submitted_answer = extract_final_answer(agent_answer['messages'][-1].content) | |
| 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) | |
| return submit(submission_data, results_log) | |
| # --- 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") | |
| run_one_button = gr.Button("Run one question and submit") | |
| 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] | |
| ) | |
| run_one_button.click( | |
| fn=run_and_submit_one, | |
| 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) |