import requests import os import gradio as gr import pandas as pd import time import re import json import wikipedia import speech_recognition as sr from pydub import AudioSegment from langchain_openai import ChatOpenAI from langchain.agents import AgentExecutor, create_react_agent from langchain.memory import ConversationSummaryMemory from langchain.tools import Tool from langchain.tools.python.tool import PythonREPLTool from langchain_community.document_loaders import WikipediaLoader from langchain.prompts import PromptTemplate # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # === TOOL: python_repl === repl_tool = PythonREPLTool( name="python_repl", description="A Python REPL for calculations and parsing. Input must be valid Python code, use print() to output results." ) # === TOOL: file_saver === def download_and_save_file(args: dict) -> str: try: if isinstance(args, str): args = json.loads(args) url = args.get("url") local_filename = args.get("local_filename") if not url or not local_filename: return "Error: Both 'url' and 'local_filename' must be provided." response = requests.get(url, stream=True, timeout=30) response.raise_for_status() os.makedirs(os.path.dirname(local_filename) or '.', exist_ok=True) with open(local_filename, 'wb') as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) return f"File downloaded successfully to {local_filename}" except Exception as e: return f"Error downloading file: {e}" file_saver_tool = Tool( name="file_saver", description="Downloads a file from a URL and saves it as the given local filename. Input: JSON with 'url' and 'local_filename'.", func=download_and_save_file, ) # === TOOL: audio_transcriber_tool === def transcribe_audio_from_path(local_audio_path: str, language: str = "en-US") -> str: r = sr.Recognizer() temp_wav_path = "temp_audio_to_transcribe.wav" transcribed_text = "" try: if local_audio_path.startswith("http://") or local_audio_path.startswith("https://"): return "Error: Only local file paths allowed. Use 'file_saver' first." if not os.path.exists(local_audio_path): return f"Error: File not found: '{local_audio_path}'." audio = AudioSegment.from_file(local_audio_path) audio.export(temp_wav_path, format="wav") with sr.AudioFile(temp_wav_path) as source: audio_listened = r.record(source) try: transcribed_text = r.recognize_google(audio_listened, language=language) except sr.UnknownValueError: return "Could not understand audio." except sr.RequestError as e: return f"Could not request results from Google Speech Recognition; {e}" except Exception as e: return f"Error: {e}" finally: if os.path.exists(temp_wav_path): os.remove(temp_wav_path) return transcribed_text.strip() audio_transcriber_tool = Tool( name="audio_transcriber_tool", description="Transcribes audio from a local file path to text. Input: path to audio file (e.g., 'myfile.mp3'). Use 'file_saver' to download first. Optionally set language.", func=transcribe_audio_from_path, ) # === TOOL: wikipedia_search_tool2 === def wiki_search(query: str) -> str: search_docs = WikipediaLoader(query=query, load_max_docs=2).load() formatted_search_docs = "\n\n---\n\n".join( [ f'\n{doc.page_content}\n' for doc in search_docs ]) return formatted_search_docs wikipedia_search_tool2 = Tool( name="wikipedia_search_tool2", description="Search Wikipedia for a query and return up to 2 results. Input: query string.", func=wiki_search, ) # === PROMPT === prompt = PromptTemplate( input_variables=["input", "agent_scratchpad", "chat_history", "tool_names"], template=""" You are a smart and helpful AI Agent/Assistant that excels at fact-based reasoning. You are allowed and encouraged to use one or more tools as needed to answer complex questions and perform tasks. STRICT FINAL ANSWER RULES: - Final Answer must be a number, a few words, or a comma-separated list, as requested. - No units or extra punctuation unless asked. Your response must start with 'Thought:' and finish with 'Final Answer:'. You have access to the following tools: {tools} Use this format: Thought: [thinking] Action: [tool_name] Action Input: [input] Observation: [result] ... Thought: [done] Final Answer: [concise answer] {chat_history} New input: {input} --- {agent_scratchpad} """ ) # === AGENT === class BasicAgent: def __init__( self, agent, tools, verbose=False, handle_parsing_errors=True, max_iterations=9, memory=None ): self.agent_obj = AgentExecutor( agent=agent, tools=tools, verbose=verbose, handle_parsing_errors=handle_parsing_errors, max_iterations=max_iterations, memory=memory ) def __call__(self, question: str) -> str: result = self.agent_obj.invoke( {"input": question}, config={"configurable": {"session_id": "test-session"}}, ) return result['output'] def run_and_submit_all(profile: gr.OAuthProfile | None): 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" openai_api_key = os.getenv("OPENAI_API_KEY") if not openai_api_key: print("OpenAI API key not found in environment variables.") return "OpenAI API key not found. Please set OPENAI_API_KEY environment variable.", None print(f"Using OpenAI API key: {openai_api_key[:4]}... (truncated for security)") llm_client = ChatOpenAI(model='gpt-4o', temperature=0, api_key=openai_api_key) summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history") summary_react_agent = create_react_agent( llm=llm_client, tools=[repl_tool, file_saver_tool, audio_transcriber_tool, wikipedia_search_tool2], prompt=prompt ) try: agent = BasicAgent(summary_react_agent, [repl_tool, file_saver_tool, audio_transcriber_tool, wikipedia_search_tool2], True, True, 30, summary_memory) 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) 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 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") file_name = item.get("file_name") full_question_for_agent = question_text if file_name: attachment_url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}" full_question_for_agent += f"\n\nAttachment '{file_name}' available at EXACT URL: {attachment_url}" print(f"Running agent on task {task_id}: {full_question_for_agent}",flush=True) try: submitted_answer = agent(full_question_for_agent) 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}) time.sleep(1) 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) 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.") cleaned_final_status = re.sub(r'[^\x20-\x7E\n\r\t]+', '', final_status) cleaned_final_status = cleaned_final_status.strip() results_df = pd.DataFrame(results_log) return cleaned_final_status, results_df except Exception as e: status_message = f"Submission Failed: {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df # --- Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Clone this space and modify the code as needed. 2. Log in to your Hugging Face account below. 3. Click 'Run Evaluation & Submit All Answers' to see your score! """ ) 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 environment variable 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}") 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)