import os from dotenv import load_dotenv import requests import pandas as pd import base64 import mimetypes import tempfile from smolagents import CodeAgent, OpenAIServerModel, tool from dotenv import load_dotenv from openai import OpenAI from markdownify import markdownify from requests.exceptions import RequestException from typing import Optional, List from langchain_core.tools import BaseTool, tool from langchain_community.tools import DuckDuckGoSearchResults from langchain_experimental.tools import PythonREPLTool import requests from bs4 import BeautifulSoup import markdownify import pandas as pd from io import BytesIO #import pytesseract from PIL import Image from youtube_transcript_api import YouTubeTranscriptApi import re # Load environment variables load_dotenv() # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # Initialize the OpenAI model using environment variable for API key model = OpenAIServerModel( model_id="o4-mini-2025-04-16", api_base="https://api.openai.com/v1", api_key=os.getenv("openai"), ) # Initialize OpenAI client openAiClient = OpenAI(api_key=os.getenv("OPENAI_API_KEY")) @tool def arvix_search(query: str) -> str: """Search Arxiv for a query and return maximum 3 result. Args: query: The search query.""" search_docs = ArxivLoader(query=query, load_max_docs=3).load() formatted_search_docs = "\n\n---\n\n".join( [ f'\n{doc.page_content[:1000]}\n' for doc in search_docs ]) return {"arvix_results": formatted_search_docs} @tool def analyze_image(image_url: str) -> str: """ Analyze an image using OpenAI's vision model and return a description. Args: image_url: URL of the image to analyze Returns: A detailed description of the image """ api_key = os.getenv("OPENAI_API_KEY") if not api_key: return "Error: OpenAI API key not set in environment variables" # Download the image try: response = requests.get(image_url) response.raise_for_status() image_data = response.content base64_image = base64.b64encode(image_data).decode('utf-8') except Exception as e: return f"Error downloading image: {str(e)}" # Call OpenAI API api_url = "https://api.openai.com/v1/chat/completions" headers = { "Content-Type": "application/json", "Authorization": f"Bearer {api_key}" } payload = { "model": "gpt-4.1-2025-04-14", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in detail. Include any text, objects, people, actions, and overall context." }, { "type": "image_url", "image_url": { "url": f"data:image/jpeg;base64,{base64_image}" } } ] } ], "max_tokens": 500 } try: response = requests.post(api_url, headers=headers, json=payload) response.raise_for_status() data = response.json() if "choices" in data and len(data["choices"]) > 0: return data["choices"][0]["message"]["content"] else: return "No description generated" except Exception as e: return f"Error analyzing image: {str(e)}" @tool def analyze_sound(audio_url: str) -> str: """ Transcribe an audio file using OpenAI's Whisper model. Args: audio_url: the url of the audio Returns: A transcription of the audio content """ api_key = os.getenv("OPENAI_API_KEY") if not api_key: return "Error: OpenAI API key not set in environment variables" # Download the audio file try: response = requests.get(audio_url) response.raise_for_status() import tempfile with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as temp_file: temp_file.write(response.content) temp_file_path = temp_file.name audio_file= open(temp_file_path, "rb") except Exception as e: return f"Error downloading audio: {str(e)}" try: transcription = openAiClient.audio.transcriptions.create( model="gpt-4o-transcribe", file=audio_file ) return transcription.text except Exception as e: return f"Error transcribing audio: {str(e)}" @tool def analyze_excel(excel_url: str) -> str: """ Process an Excel file and convert it to a text-based format. Args: excel_url: URL of the Excel file to analyze Returns: A text representation of the Excel data """ try: # Download the Excel file response = requests.get(excel_url) response.raise_for_status() # Save to a temporary file with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as temp_file: temp_file.write(response.content) temp_file_path = temp_file.name # Read the Excel file df = pd.read_excel(temp_file_path) # Convert to a text representation result = [] # Add sheet information result.append(f"Excel file with {len(df)} rows and {len(df.columns)} columns") # Add column names result.append("\nColumns:") for i, col in enumerate(df.columns, 1): result.append(f"{i}. {col}") # Add data summary result.append("\nData Summary:") result.append(df.describe().to_string()) # Add first few rows as a sample result.append("\nFirst 5 rows:") result.append(df.head().to_string()) # Clean up os.unlink(temp_file_path) return "\n".join(result) except Exception as e: return f"Error processing Excel file: {str(e)}" @tool def analyze_text(text_url: str) -> str: """ Process a text file and return its contents. Args: text_url: URL of the text file to analyze Returns: The contents of the text file """ try: # Download the text file response = requests.get(text_url) response.raise_for_status() # Get the text content text_content = response.text # For very long files, truncate with a note if len(text_content) > 10000: return f"Text file content (truncated to first 10000 characters):\n\n{text_content[:10000]}\n\n... [content truncated]" return f"Text file content:\n\n{text_content}" except Exception as e: return f"Error processing text file: {str(e)}" @tool def transcribe_youtube(youtube_url: str) -> str: """ Extract the transcript from a YouTube video. Args: youtube_url: URL of the YouTube video Returns: The transcript of the video """ try: # Extract video ID from URL import re video_id_match = re.search(r'(?:v=|\/)([0-9A-Za-z_-]{11}).*', youtube_url) if not video_id_match: return "Error: Invalid YouTube URL" video_id = video_id_match.group(1) # Use youtube_transcript_api to get the transcript from youtube_transcript_api import YouTubeTranscriptApi try: transcript_list = YouTubeTranscriptApi.get_transcript(video_id) # Combine all transcript segments into a single text full_transcript = "" for segment in transcript_list: full_transcript += segment['text'] + " " return f"YouTube Video Transcript:\n\n{full_transcript.strip()}" except Exception as e: return f"Error extracting transcript: {str(e)}" except Exception as e: return f"Error processing YouTube video: {str(e)}" @tool def process_file(task_id: str, file_name: str) -> str: """ Fetch and process a file based on task_id and file_name. For images, it will analyze them and return a description of the image. For audio files, it will transcribe them. For Excel files, it will convert them to a text format. For text files, it will return the file contents. Other file types can be ignored for this tool. Args: task_id: The task ID to fetch the file for file_name: The name of the file to process Returns: A description or transcription of the file content """ if not task_id or not file_name: return "Error: task_id and file_name are required" # Construct the file URL file_url = f"{DEFAULT_API_URL}/files/{task_id}" try: # Fetch the file response = requests.get(file_url) response.raise_for_status() # Determine file type mime_type, _ = mimetypes.guess_type(file_name) # Process based on file type if mime_type and mime_type.startswith('image/'): # For images, use the analyze_image tool return analyze_image(file_url) elif file_name.lower().endswith('.mp3') or (mime_type and mime_type.startswith('audio/')): # For audio files, use the analyze_sound tool return analyze_sound(file_url) elif file_name.lower().endswith('.xlsx') or (mime_type and mime_type == 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'): # For Excel files, use the analyze_excel tool return analyze_excel(file_url) elif file_name.lower().endswith(('.txt', '.py', '.js', '.html', '.css', '.json', '.md')) or (mime_type and mime_type.startswith('text/')): # For text files, use the analyze_text tool return analyze_text(file_url) else: # For other file types, return basic information return f"File '{file_name}' of type '{mime_type or 'unknown'}' was fetched successfully. Content processing not implemented for this file type." except Exception as e: return f"Error processing file: {str(e)}" class BasicAgent: """ A simple agent that uses smolagents.CodeAgent with multiple specialized tools: - Tavily search tool for web searches - Image analysis tool for processing images - Audio transcription tool for processing sound files - Excel analysis tool for processing spreadsheet data - Text file analysis tool for processing code and text files - YouTube transcription tool for processing video content - File processing tool for handling various file types The CodeAgent is instantiated once and reused for each question to reduce overhead. """ def __init__(self): print("BasicAgent initialized.") # Reuse a single CodeAgent instance for all queries self.agent = CodeAgent(tools=[arvix_search, analyze_image, analyze_sound, analyze_excel, analyze_text, transcribe_youtube, process_file], model=model) def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") return self.agent.run(question) 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) 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: submitted_answer = agent(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)