I have several images of animals in the same directory as the script. How can I modify the following script to process an image but force the output to only be a single selection from a list: from pathlib import Path import base64 import requests def encode_image_to_base64(image_path): """Convert an image file to base64 string.""" return base64.b64encode(image_path.read_bytes()).decode('utf-8') def extract_text_from_image(image_path): """Send image to local Llama API and get text description.""" base64_image = encode_image_to_base64(image_path) payload = { "model": "llama3.2-vision", "stream": False, "messages": [ { "role": "user", "content": ( "With just one word, classify this image into one of these exact categories:\n" "- dog\n" "- cat\n" "- butterfly\n" ), "images": [base64_image] } ] } response = requests.post( "http://localhost:11434/api/chat", json=payload, headers={"Content-Type": "application/json"} ) return response.json().get('message', {}).get('content', 'No text extracted') def process_directory(): """Process all images in current directory and create text files.""" for image_path in Path('.').glob('*'): if image_path.suffix.lower() in {'.png', '.jpg', '.jpeg', '.gif', '.bmp', '.webp'}: print(f"\nProcessing {image_path}...") text = extract_text_from_image(image_path) image_path.with_suffix('.txt').write_text(text, encoding='utf-8') print(f"Created {image_path.with_suffix('.txt')}") process_directory() However, despite different prompt engineering, I get some answers that will do more than just select from a list. For example, it may occassionally output "From the image, there is a winged insect, therefore my guess is "butterfly." ANSWER: Butterfly." If I define the list as allowed_options = ['dog', 'cat', 'butterfly'] I only want it to output a single string from that list and nothing else. Continue reading...
