import os, sys from enum import Enum import gradio as gr import requests import inspect import subprocess import dateparser from bs4 import BeautifulSoup import regex import pandas as pd import torch from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, BitsAndBytesConfig from smolagents import CodeAgent, VisitWebpageTool, WebSearchTool, WikipediaSearchTool, PythonInterpreterTool from smolagents.models import ChatMessage from custom_tools import WebpageStructureAnalyzerTool subprocess.run(["playwright", "install"], check=True) # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # MODEL_ID = "Qwen/Qwen3-32B" MODEL_ID = "Qwen/Qwen2.5-Coder-32B-Instruct" class CachedWebSearchTool(WebSearchTool): @lru_cache(maxsize=128) def run(self, query: str): # identical queries return instantly return super().run(query) class CachedWikiTool(WikipediaSearchTool): @lru_cache(maxsize=128) def run(self, page: str): return super().run(page) class PreloadedPythonTool(PythonInterpreterTool): """ A PythonInterpreterTool that automatically prepends the necessary imports (bs4, BeautifulSoup, regex) so you never hit NameError inside your code blocks. """ def run(self, code: str) -> str: preamble = ( "import bs4\n" "from bs4 import BeautifulSoup\n" "import regex\n" ) return super().run(preamble + code) def check_token_access(): token = os.environ.get("HF_TOKEN", "") if not token: print("❌ No token found") return headers = {"Authorization": f"Bearer {token}"} url = f"https://huggingface.co/{MODEL_ID}/resolve/main/config.json" try: r = requests.get(url, headers=headers, timeout=10) print(f"🔍 Token test response: {r.status_code}") if r.status_code == 200: print("✅ Token access confirmed for gated model.") elif r.status_code == 403: print("❌ 403 Forbidden: Token does not have access.") else: print("⚠️ Unexpected status:", r.status_code) except Exception as e: print("❌ Token check failed:", e) # --- Basic Model Definition --- # ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------ class BasicModel: def __init__(self, model_id, hf_token=""): print("BasicAgent initialized.") print("ENV-HF_TOKEN-LEN", len(hf_token), file=sys.stderr) check_token_access() # Initialize the model # model = HfApiModel(model_id=model_id, # # format="text-generation", # token=os.environ["HF_TOKEN"], # max_tokens=2048, # temperature=0.0 # ) # Download the model weights to the local machine and build the pipeline quantization_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.float16, bnb_4bit_use_double_quant=True, ) tok = AutoTokenizer.from_pretrained(model_id, token=hf_token) mod = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto", ## auto-distributes to GPU token=hf_token, trust_remote_code=True, ## <- Use the custom code that isn't part of the base transformers library yet quantization_config=quantization_config ## <- Load 4-bit quantization because vRAM is not big enough ) self.pipe = pipeline( "text-generation", model=mod, tokenizer=tok, max_new_tokens=2048, return_full_text=False, # <— only get the completion, not the prompt + completion # temperature=1.0, ) def _serialize_messages(self, messages): # This serialization might need adjustment based on how CodeAgent sends prompts. # It needs to handle both initial strings and potential chat histories (as a list of ChatMessage objects). if isinstance(messages, str): return f"<|im_start|>user\n\n{messages}<|im_end|><|im_start|>assistant<|im_end|>\n\n" prompt = [] for m in messages: ## <- For each ChatMessage object # Read the roles role = m.role if hasattr(m, 'role') else m.get('role', 'user') role = role.value if isinstance(role, Enum) else role # Read the content texts content = list(m.values())[1] content_text = "" if isinstance(content, list): ## <- If m.content is a list of dicts, e.g. [{'type':'text', 'text': ...}] content_text = "".join([c.get('text', '') for c in content if c.get('type') == 'text']) elif isinstance(content, str): ## <- If m.content is simply a string content_text = content prompt.append(f"<|im_start|>{role}\n\n{content_text}<|im_end|>") # Qwen3 format print(f"{role}: {content_text}") ## <- Print the last message in log # Add the assistant prompt start prompt.append("<|im_start|>assistant\n\n") return "".join(prompt) def generate(self, prompt: str | list, stop_sequences=None, **kwargs) -> str: ## <- 'prompt' is either a string or a list of ChatMessages # 1. Build the HF kwargs allowed = {"max_new_tokens", "temperature", "top_k", "top_p"} gen_kwargs = {k: v for k, v in kwargs.items() if k in allowed} # 2. Get the response terminators = [ self.pipe.tokenizer.eos_token_id, self.pipe.tokenizer.convert_tokens_to_ids("<|endoftext|>") ] prompt_str = self._serialize_messages(prompt) outputs = self.pipe(prompt_str, eos_token_id=terminators, **gen_kwargs) response = outputs[0]["generated_text"] assert isinstance(response, str) # 3. Optionally map SmolAgents’ stop_sequences → HF pipeline’s 'stop' if stop_sequences: # find the earliest occurrence of any stop token cuts = [response.find(s) for s in stop_sequences if response.find(s) != -1] if cuts: response = response[: min(cuts)] # wrap back into a chat message dict return ChatMessage(role="assistant", content=response) # return { # "role": 'assistant', # "content": [{"type": "text", "text": response}], # } __call__ = generate 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 hf_token = os.getenv("HF_TOKEN") 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: # (1) Create the LLM wrapper llm_model = BasicModel(model_id=MODEL_ID, hf_token=hf_token) # (2) Create the tools web_structure_analyzer_tool = WebpageStructureAnalyzerTool() wiki_tool = CachedWikiTool() search_tool = CachedWebSearchTool() python_tool = PythonInterpreterTool() html_parse_tool = VisitWebpageTool() #(3) Create the CodeAgent, passing the LLM wrapper and tools agent = CodeAgent(model=llm_model, tools=[web_structure_analyzer_tool, wiki_tool, search_tool, python_tool, html_parse_tool], max_steps=5, add_base_tools=True, additional_authorized_imports=["dateparser", "bs4", "regex"]) 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 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 # questions_data = questions_data[:5] # 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.run(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)