src/models/imageCaptioning.py

# import requests
# import base64
# import os


# hf_token = os.environ.get("HUGGINGFACE_API_TOKEN")

# API_URL = "https://api-inference.huggingface.co/models/nlpconnect/vit-gpt2-image-captioning" 
# headers = {
#     "Authorization": f"Bearer {hf_token}"
# }

# def generateCaption(image_path):
#     with open(image_path, "rb") as image_file:
#         image_bytes = image_file.read()

#     response = requests.post(API_URL, headers=headers, files={"file": image_bytes})
    
#     if response.status_code == 200:
#         result = response.json()
#         return result[0]['generated_text']
#     else:
#         return f"Error generating caption: {response.text}"


from PIL import Image
from transformers import BlipProcessor , BlipForConditionalGeneration
import torch


processor = BlipProcessor.from_pretrained("src/models/Caption")
model = BlipForConditionalGeneration.from_pretrained("src/models/Caption")


def generateCaption(image_path):
    image = Image.open(image_path).convert("RGB")
    inputs = processor(images = image , return_tensors="pt")
    output = model.generate(**inputs)
    caption = processor.decode(output[0], skip_special_tokens = True)
    return caption