Spaces:
Sleeping
Sleeping
| # app.py — fully updated to avoid the 32 768-token ceiling | |
| # ----------------------------------------------------------------------------- | |
| # Changes vs. the original paste.txt [1] follow the “### CHANGE” comments. | |
| # Core idea taken from the fresh-agent pattern shown in result [2]. | |
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| # Tools ----------------------------------------------------------------------- | |
| from tools import ( | |
| ReverseTextTool, | |
| RunPythonFileTool, | |
| download_server, | |
| wiki_tool, | |
| YoutubeTranscript, | |
| ) | |
| from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec | |
| # Llama-Index / HF Inference --------------------------------------------------- | |
| from llama_index.core.agent.workflow import AgentWorkflow # [1] | |
| from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI # [1] | |
| # --- Constants --------------------------------------------------------------- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question. | |
| Report your thoughts, and finish your answer with just the answer — no prefixes like "FINAL ANSWER:". | |
| Your answer should be a number OR as few words as possible OR a comma-separated list of numbers and/or strings. | |
| If you're asked for a number, don’t use commas or units like $ or %, unless specified. | |
| If you're asked for a string, don’t use articles or abbreviations (e.g. for cities), and write digits in plain text unless told otherwise. | |
| Always create a detailed thinking and reasoning plan before taking an action. | |
| If reasoning in previous step didn't get you correct answer, try to use other reasoning but it must achieve the same outcome. | |
| Tool Use Guidelines: | |
| 1. Do **not** use any tools outside of the provided tools list. | |
| 2. Always use **only one tool at a time** in each step of your execution. | |
| 3. If the question refers to a `.py` file or uploaded Python script, use **RunPythonFileTool** to execute it and base your answer on its output. | |
| 4. If the question looks reversed (starts with a period or reads backward), first use **ReverseTextTool** to reverse it, then process the question. | |
| 5. For logic or word puzzles, solve them directly unless they are reversed — in which case, decode first using **ReverseTextTool**. | |
| 6. When dealing with Excel files, prioritize using the **excel** tool over writing code in **terminal-controller**. | |
| 7. If you need to download a file, always use the **download_server** tool and save it to the correct path. | |
| 8. To find information about what was said in a video use **YoutubeTranscript** tool to get the transcript and find the correct answer to the asked question | |
| 9. Even for complex tasks, assume a solution exists. If one method fails, try another approach using different tools. | |
| 10. Due to context length limits, keep browser-based tasks (e.g., searches) as short and efficient as possible. | |
| 11. Use DuckDuckGoSearchToolSpec to find or verify information from web search. | |
| 12. Use wiki_tool to find answers from wikipedia. | |
| """ | |
| # ----------------------------------------------------------------------------- | |
| # BasicAgent – spawns a brand-new AgentWorkflow for *each* question [2] | |
| # ----------------------------------------------------------------------------- | |
| class BasicAgent: | |
| """LLM + tool set kept once; AgentWorkflow rebuilt per question.""" | |
| def __init__(self) -> None: | |
| hf_api_key = os.getenv("HF_API_KEY") | |
| if not hf_api_key: | |
| raise RuntimeError("HF_API_KEY not set in environment variables.") | |
| # single, stateless LLM reused across questions | |
| self.llm = HuggingFaceInferenceAPI( | |
| model_name="Qwen/Qwen2.5-Coder-32B-Instruct", | |
| token=hf_api_key, | |
| max_tokens=256, # output length only | |
| ) | |
| self._tools = [ | |
| ReverseTextTool, | |
| RunPythonFileTool, | |
| download_server, | |
| wiki_tool, | |
| YoutubeTranscript, | |
| DuckDuckGoSearchToolSpec, | |
| ] | |
| print("✅ BasicAgent initialized.") | |
| # ---------- internal helper --------------------------------------------- | |
| def _make_agent(self) -> AgentWorkflow: | |
| """Return a FRESH AgentWorkflow with empty context.""" | |
| return AgentWorkflow.from_tools_or_functions( | |
| tools_or_functions=self._tools, | |
| llm=self.llm, | |
| system_prompt=SYSTEM_PROMPT, | |
| ) | |
| print("✅ BasicAgent initialized.") | |
| # ---------- public helpers ---------------------------------------------- | |
| async def answer_once(self, prompt: str) -> str: | |
| """Answer one question while guaranteeing ctx < 32 768 tokens.""" | |
| MAX_IN_TOKENS = 30000 # ~2-3 k room for system + tools | |
| prompt = prompt[:MAX_IN_TOKENS] # naïve clip by characters | |
| agent = self._make_agent() # NO prior history | |
| resp = await agent.run(prompt) | |
| return resp if isinstance(resp, str) else str(resp) | |
| # keep backwards-compat method names | |
| async def __call__(self, input_text: str): | |
| return await self.answer_once(input_text) | |
| async def run(self, input_text: str): | |
| return await self.answer_once(input_text) | |
| async def stream(self, input_text: str): | |
| agent = self._make_agent() | |
| async for chunk in agent.stream(input_text): | |
| yield chunk.delta | |
| # ----------------------------------------------------------------------------- | |
| # Evaluation / submission logic (unchanged except per-question call) [1] [2] | |
| # ----------------------------------------------------------------------------- | |
| async def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| """ | |
| Fetch questions, answer them one-by-one with BasicAgent, then submit. | |
| """ | |
| # --- user / URLs --------------------------------------------------------- | |
| space_id = os.getenv("SPACE_ID") | |
| 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" | |
| # --- instantiate agent --------------------------------------------------- | |
| try: | |
| agent = BasicAgent() | |
| except Exception as e: | |
| print(f"Error instantiating agent: {e}") | |
| return f"Error initializing agent: {e}", None | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| print(agent_code) | |
| # --- fetch questions ----------------------------------------------------- | |
| print(f"Fetching questions from: {questions_url}") | |
| try: | |
| resp = requests.get(questions_url, timeout=15) | |
| resp.raise_for_status() | |
| questions_data = resp.json() | |
| if not questions_data: | |
| return "Fetched questions list is empty or invalid format.", None | |
| print(f"Fetched {len(questions_data)} questions.") | |
| except Exception as e: | |
| return f"Error fetching questions: {e}", None | |
| # --- answer questions one-by-one ---------------------------------------- | |
| 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 = await agent(question_text) # <<< one call | |
| 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) | |