Spaces:
Sleeping
Sleeping
| import os | |
| import json | |
| from dotenv import load_dotenv | |
| load_dotenv() | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| from tools import web_search, wikipedia_search, python_repl, download_and_read_file | |
| from tools.file_handler import prefetch_file | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| TOOL_FUNCTIONS = { | |
| "web_search": web_search, | |
| "wikipedia_search": wikipedia_search, | |
| "python_repl": python_repl, | |
| "download_and_read_file": download_and_read_file, | |
| } | |
| TOOL_SCHEMAS = [ | |
| { | |
| "type": "function", | |
| "function": { | |
| "name": "web_search", | |
| "description": "Search Google for current information. Use for factual questions, recent events, or any topic requiring web search.", | |
| "parameters": { | |
| "type": "object", | |
| "properties": {"query": {"type": "string", "description": "Search query"}}, | |
| "required": ["query"], | |
| }, | |
| }, | |
| }, | |
| { | |
| "type": "function", | |
| "function": { | |
| "name": "wikipedia_search", | |
| "description": "Search Wikipedia for encyclopedic or historical information about a topic.", | |
| "parameters": { | |
| "type": "object", | |
| "properties": {"query": {"type": "string", "description": "Topic to search"}}, | |
| "required": ["query"], | |
| }, | |
| }, | |
| }, | |
| { | |
| "type": "function", | |
| "function": { | |
| "name": "python_repl", | |
| "description": "Execute Python code for math, calculations, data analysis, or logic. Use print() to output results.", | |
| "parameters": { | |
| "type": "object", | |
| "properties": {"code": {"type": "string", "description": "Python code to execute"}}, | |
| "required": ["code"], | |
| }, | |
| }, | |
| }, | |
| { | |
| "type": "function", | |
| "function": { | |
| "name": "download_and_read_file", | |
| "description": "Download and read a file attachment (CSV, Excel, text) for a given task_id from the question.", | |
| "parameters": { | |
| "type": "object", | |
| "properties": {"task_id": {"type": "string", "description": "The task_id of the question"}}, | |
| "required": ["task_id"], | |
| }, | |
| }, | |
| }, | |
| ] | |
| SYSTEM_PROMPT = ( | |
| "You are a precise research assistant. Solve each question step by step using tools.\n\n" | |
| "STRICT RULES:\n" | |
| "1. NEVER search for 'GAIA benchmark', 'GAIA answer', 'HuggingFace discussion', or any meta-search for pre-solved answers. Solve the problem yourself.\n" | |
| "2. For ANY text manipulation (reversing, encoding, counting characters, etc.), ALWAYS use python_repl — never guess by eye.\n" | |
| "3. Keep search queries SHORT and targeted (under 8 words). Never enumerate values (e.g. years) in one query.\n" | |
| "4. If you have an [Attached file content] section, read it directly — do NOT call download_and_read_file again.\n" | |
| "5. OUTPUT FORMAT: Your ENTIRE response must be ONLY the final answer — no explanation, no reasoning, no 'The answer is', no preamble. A single word, number, or comma-separated list. Nothing else.\n" | |
| "6. Numbers: digits only (e.g. '42', not 'forty-two'). Names: as they appear in the source.\n" | |
| "7. If a question involves reversing or encoding text, use python_repl to decode it first before reasoning.\n" | |
| "8. Lists: output as plain comma-separated values (e.g. 'apple, banana, cherry') — NO brackets, NO quotes, NO Python syntax.\n" | |
| "9. If the question has a [Task ID: xxx] prefix, use that exact value when calling download_and_read_file.\n" | |
| "10. If an attached file is audio/image/video (marked [UNSUPPORTED]), do NOT call download_and_read_file — use web_search to find the answer instead.\n" | |
| ) | |
| # --- Basic Agent Definition --- | |
| # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ | |
| class BasicAgent: | |
| def __init__(self): | |
| self.api_key = os.getenv("DEEPSEEK_API_KEY") | |
| self.model = os.getenv("DEEPSEEK_MODEL", "deepseek-chat") | |
| self.api_url = "https://www.ggwk1.online/v1/chat/completions" | |
| print("BasicAgent initialized with DeepSeek (native HTTP).") | |
| def _call_llm(self, messages: list) -> dict: | |
| headers = { | |
| "Authorization": f"Bearer {self.api_key}", | |
| "Content-Type": "application/json", | |
| } | |
| payload = { | |
| "model": self.model, | |
| "messages": messages, | |
| "tools": TOOL_SCHEMAS, | |
| "tool_choice": "auto", | |
| "temperature": 0, | |
| } | |
| response = requests.post( | |
| self.api_url, headers=headers, json=payload, timeout=60, | |
| proxies={"http": None, "https": None} | |
| ) | |
| response.raise_for_status() | |
| return response.json() | |
| def __call__(self, question: str) -> str: | |
| print(f"Agent received question (first 50 chars): {question[:50]}...") | |
| messages = [ | |
| {"role": "system", "content": SYSTEM_PROMPT}, | |
| {"role": "user", "content": question}, | |
| ] | |
| for _ in range(15): # max iterations | |
| result = self._call_llm(messages) | |
| choice = result["choices"][0] | |
| message = choice["message"] | |
| messages.append(message) | |
| if choice["finish_reason"] == "tool_calls": | |
| for tool_call in message.get("tool_calls", []): | |
| fn_name = tool_call["function"]["name"] | |
| fn_args = json.loads(tool_call["function"]["arguments"]) | |
| print(f" -> Tool: {fn_name}({fn_args})") | |
| tool_result = TOOL_FUNCTIONS[fn_name](**fn_args) | |
| print(f" <- Result (first 200): {str(tool_result)[:200]}") | |
| messages.append({ | |
| "role": "tool", | |
| "tool_call_id": tool_call["id"], | |
| "content": str(tool_result), | |
| }) | |
| else: | |
| answer = message.get("content", "") | |
| print(f"Agent answer: {answer}") | |
| return answer | |
| return "Max iterations reached without a final answer." | |
| 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 = BasicAgent() | |
| 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, proxies={"http": None, "https": None}) | |
| 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: | |
| # Pre-fetch file attachment and embed content directly in question | |
| file_content = prefetch_file(task_id) | |
| if file_content: | |
| full_question = f"[Task ID: {task_id}]\n{question_text}\n\n[Attached file content]:\n{file_content}" | |
| else: | |
| full_question = f"[Task ID: {task_id}]\n{question_text}" | |
| submitted_answer = agent(full_question) | |
| 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, proxies={"http": None, "https": None}) | |
| 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) |