Spaces:
Sleeping
Sleeping
| import os | |
| import re | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from langchain_openai import ChatOpenAI | |
| from langchain_community.tools import DuckDuckGoSearchResults | |
| from langchain_experimental.tools import PythonREPLTool | |
| from langchain_core.tools import tool | |
| from langchain_core.messages import SystemMessage, HumanMessage, ToolMessage | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| SYSTEM_PROMPT = """You are a general AI assistant. Answer GAIA benchmark questions accurately. | |
| Available tools: | |
| - duckduckgo_search: returns search results WITH URLs. Each result has a link field. | |
| - read_webpage: reads FULL text of a URL. ALWAYS call this after finding a relevant link in search results. | |
| - Python_REPL: calculations and data analysis. ALWAYS use print() to output results. | |
| MANDATORY research strategy: | |
| 1. Search with duckduckgo_search — look for a link to a Wikipedia page, database, or article. | |
| 2. Call read_webpage on the most relevant link from results — get full page content. | |
| 3. Extract the precise answer from page content. | |
| 4. If Wikipedia has an article: read it directly — e.g. read_webpage("https://en.wikipedia.org/wiki/Topic"). | |
| Special rules: | |
| - Reversed/encoded text: decode it yourself, no tools needed. | |
| - YouTube: search the video ID + key terms from the question. | |
| - Attached files not available: search web for the answer instead. | |
| - If question asks for IOC code: return the IOC code. If question asks for country name: return full name. | |
| When done, output ONLY: | |
| FINAL ANSWER: [your answer] | |
| STRICT format rules (exact match): | |
| - Numbers: digits only, no $, no commas, no units unless asked | |
| - Strings: no surrounding quotes, no trailing punctuation, no articles (a/an/the) | |
| - Lists: comma-separated, no spaces after commas | |
| - Always give an answer — never output "No answer found\"""" | |
| def read_webpage(url: str) -> str: | |
| """Read the full text content of a webpage. Use after finding a relevant URL via search to get precise information.""" | |
| try: | |
| headers = {"User-Agent": "Mozilla/5.0 (compatible; research-agent/1.0)"} | |
| resp = requests.get(url, headers=headers, timeout=15, allow_redirects=True) | |
| if resp.status_code != 200: | |
| return f"Could not fetch page: HTTP {resp.status_code}" | |
| text = re.sub(r"<[^>]+>", " ", resp.text) | |
| text = re.sub(r"\s+", " ", text).strip() | |
| return text[:6000] | |
| except Exception as e: | |
| return f"Error reading page: {e}" | |
| class BasicAgent: | |
| def __init__(self): | |
| self.llm = ChatOpenAI(model="gpt-4o", temperature=0) | |
| self.tools = [ | |
| DuckDuckGoSearchResults(num_results=5), | |
| read_webpage, | |
| PythonREPLTool(), | |
| ] | |
| self.tools_map = {t.name: t for t in self.tools} | |
| self.llm_with_tools = self.llm.bind_tools(self.tools, parallel_tool_calls=False) | |
| print("BasicAgent initialized with OpenAI (gpt-4o).") | |
| def __call__(self, question: str, task_id: str = "") -> str: | |
| full_question = f"[Task ID: {task_id}]\n\n{question}" if task_id else question | |
| print(f"Running agent on task {task_id}: {question[:80]}...") | |
| messages = [ | |
| SystemMessage(content=SYSTEM_PROMPT), | |
| HumanMessage(content=full_question), | |
| ] | |
| last_response = None | |
| for iteration in range(10): | |
| response = self.llm_with_tools.invoke(messages) | |
| messages.append(response) | |
| last_response = response | |
| if not response.tool_calls: | |
| break | |
| for tool_call in response.tool_calls: | |
| tool_name = tool_call["name"] | |
| tool_args = tool_call["args"] | |
| tool_id = tool_call["id"] | |
| first_arg = str(list(tool_args.values())[0])[:60] if tool_args else "" | |
| print(f" [{iteration+1}] Tool: {tool_name}({first_arg})") | |
| if tool_name in self.tools_map: | |
| try: | |
| result = self.tools_map[tool_name].invoke(tool_args) | |
| except Exception as e: | |
| result = f"Tool error: {e}" | |
| else: | |
| result = f"Unknown tool: {tool_name}" | |
| messages.append(ToolMessage(content=str(result)[:3000], tool_call_id=tool_id)) | |
| raw_answer = last_response.content if last_response else "" | |
| # If loop ended without FINAL ANSWER (hit limit or empty content), force one | |
| if "FINAL ANSWER:" not in raw_answer: | |
| messages.append(HumanMessage( | |
| content="Based on all information gathered above, give your FINAL ANSWER now. Format: FINAL ANSWER: [answer]" | |
| )) | |
| forced = self.llm.invoke(messages) | |
| raw_answer = forced.content | |
| if "FINAL ANSWER:" in raw_answer: | |
| answer = raw_answer.split("FINAL ANSWER:")[-1].strip() | |
| else: | |
| answer = raw_answer.strip() | |
| answer = self._clean_answer(answer) | |
| print(f"Answer for {task_id}: {answer[:100]}") | |
| return answer | |
| def _clean_answer(self, answer: str) -> str: | |
| # Strip surrounding quotes | |
| answer = answer.strip('"\'') | |
| # Strip trailing sentence punctuation | |
| answer = answer.rstrip('.') | |
| # Remove currency symbols | |
| answer = answer.replace('$', '').replace('€', '').replace('£', '') | |
| # Remove placeholder text | |
| if answer in ('[answer]', '[Answer]', '[YOUR ANSWER]', '[your answer]'): | |
| return "" | |
| # Normalize list spacing: "a, b, c" → "a,b,c" | |
| if ',' in answer and not any(c.isdigit() for c in answer.split(',')[0]): | |
| answer = ','.join(part.strip() for part in answer.split(',')) | |
| # Strip surrounding brackets | |
| if answer.startswith('[') and answer.endswith(']') and answer.count('[') == 1: | |
| answer = answer[1:-1] | |
| return answer.strip() | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the BasicAgent on them, submits all answers, | |
| and displays the results. | |
| """ | |
| 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" | |
| # 1. 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) | |
| # 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 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, task_id) | |
| 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. Submit | |
| 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) | |
| 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.") | |
| return final_status, pd.DataFrame(results_log) | |
| 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) | |
| return status_message, pd.DataFrame(results_log) | |
| except requests.exceptions.Timeout: | |
| status_message = "Submission Failed: The request timed out." | |
| print(status_message) | |
| return status_message, pd.DataFrame(results_log) | |
| except requests.exceptions.RequestException as e: | |
| status_message = f"Submission Failed: Network error - {e}" | |
| print(status_message) | |
| return status_message, pd.DataFrame(results_log) | |
| except Exception as e: | |
| status_message = f"An unexpected error occurred during submission: {e}" | |
| print(status_message) | |
| return status_message, pd.DataFrame(results_log) | |
| # --- Gradio Interface --- | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Agent Evaluation Runner — Groq + Tool Binding") | |
| gr.Markdown( | |
| """ | |
| **Instructions:** | |
| 1. Log in to your Hugging Face account using the button below. | |
| 2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the agent, and submit. | |
| **Agent:** Custom ReAct loop — OpenAI gpt-4o | |
| **Tools:** DuckDuckGo search, Python REPL, File fetcher (text + Excel) | |
| --- | |
| *Note: Running 20 questions takes several minutes.* | |
| """ | |
| ) | |
| gr.LoginButton() | |
| run_button = gr.Button("Run Evaluation & Submit All Answers") | |
| status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False) | |
| 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) | |
| space_host_startup = os.getenv("SPACE_HOST") | |
| space_id_startup = os.getenv("SPACE_ID") | |
| 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 not found (running locally?).") | |
| if space_id_startup: | |
| print(f"✅ SPACE_ID found: {space_id_startup}") | |
| print(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}") | |
| else: | |
| print("ℹ️ SPACE_ID not found (running locally?).") | |
| print("-" * (60 + len(" App Starting ")) + "\n") | |
| demo.launch(debug=True, share=False) | |