Evaluate how well this image matches the search term: [tagword] . Provide a concise reason and assign a 0–5 relevance score:

Scoring (0–5):
0 – Not Relevant: No connection.
1 – Barely Relevant: Very weak or vague link.
2 – Minimally Relevant: Hints but lacks clarity.
3 – Moderately Relevant: Noticeable link, not the main focus.
4 – Highly Relevant: Strong, clear representation.
5 – Perfectly Relevant: Ideal example.

Content Relevance: Does it clearly relate?
Context & Setting: Does its overall style fit the theme?
Visual Appeal & User Satisfaction: Would users find this image useful or satisfying based on the search term?

from unsloth import FastVisionModel
import base64
import json
import re
from io import BytesIO
from PIL import Image
import torch

# --- Model Initialization ---
model, tokenizer = FastVisionModel.from_pretrained(
    model_name="Pixuai/Llama-3.2-11B-Vision-Instruct-TagRater",
    load_in_4bit=True,
    max_seq_length=150,
)
FastVisionModel.for_inference(model)

# --- Input Preparation ---
# Replace these variables with your actual prompt and base64 encoded image string.
prompt = "Evaluate how well this image matches the search term: space explorer . Provide a concise reason and assign a 0–5 relevance score: Scoring (0–5): 0 – Not Relevant: No connection. 1 – Barely Relevant: Very weak or vague link. 2 – Minimally Relevant: Hints but lacks clarity. 3 – Moderately Relevant: Noticeable link, not the main focus. 4 – Highly Relevant: Strong, clear representation. 5 – Perfectly Relevant: Ideal example. - Content Relevance: Does it clearly relate? - Context & Setting: Does its overall style fit the theme? - Visual Appeal & User Satisfaction: Would users find this image useful or satisfying based on the search term?"
image_b64 = "base64_string_here"  # Replace with a valid base64 encoded image string

try:
    image_data = base64.b64decode(image_b64)
    image = Image.open(BytesIO(image_data)).convert("RGB")
except Exception as e:
    print(f"Error decoding image: {str(e)}")
    exit()

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": prompt}
        ],
    }
]

input_text = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
inputs = tokenizer(
    image,
    input_text,
    add_special_tokens=False,
    return_tensors="pt",
).to("cuda")

# --- Inference ---
gen_tokens = model.generate(
    **inputs,
    max_new_tokens=100,
    use_cache=True,
    temperature=0.1,
    min_p=0.1,
)

# --- Decoding Output ---
output_text = tokenizer.decode(gen_tokens[0], skip_special_tokens=True)

json_match = re.search(r'({.*})', output_text, re.DOTALL)
if json_match:
    json_str = json_match.group(1)
    try:
        json_obj = json.loads(json_str)
    except json.JSONDecodeError:
        print("Invalid JSON output.")
        exit()
    print("JSON Output:", json_obj)
else:
    print("No JSON object found in the output.")