app.py

import os
import io
import base64 
import gradio as gr 
from dotenv import load_dotenv, find_dotenv
load_dotenv(find_dotenv()) 
hf_api_key = os.environ['HF_API_KEY']

# Helper functions
import requests, json

API_URL = "https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-base"

#Image-to-text endpoint
def get_completion(inputs, parameters=None, ENDPOINT_URL=API_URL):
    headers = {
      "Authorization": f"Bearer {hf_api_key}",
      "Content-Type": "application/json"
    }
    data = { "inputs": inputs }
    if parameters is not None:
        data.update({"parameters": parameters})
    response = requests.request("POST", ENDPOINT_URL, headers=headers,data=json.dumps(data))
    return json.loads(response.content.decode("utf-8"))


def image_to_base64_str(pil_image):
    byte_arr = io.BytesIO()
    pil_image.save(byte_arr, format='PNG')
    byte_arr = byte_arr.getvalue()
    return str(base64.b64encode(byte_arr).decode('utf-8'))

def captioner(image):
    base64_image = image_to_base64_str(image)
    result = get_completion(base64_image)
    return result[0]['generated_text']

def loadGUI():
     gr.close_all()
     demo = gr.Interface(fn=captioner,
                         inputs=[gr.Image(label="Upload image", type="pil")],
                         outputs=[gr.Textbox(label="Caption")],
                         title="Image Captioning with BLIP",
                         description="Caption any image using the BLIP model",
                         allow_flagging="never",
                         examples=["images/helicopter.jpg","images/maxresdefault.jpg","images/police-heli.jpg"])

     demo.launch(share=True)
     
def main():
     loadGUI()
     
     
if __name__ == "__main__":
     main()