Update app.py

app.py

@@ -1,90 +1,47 @@
-from dotenv import load_dotenv, find_dotenv
-import os
+# app.py
+
 import io
-from io import BytesIO
 from PIL import Image
-import base64
 import requests
-import json
 import warnings
 import gradio as gr
+from transformers import pipeline
 
-# Suppress specific warnings
+# Suppress warnings
 warnings.filterwarnings("ignore", message=".*Using the model-agnostic default `max_length`.*")
 
-# Load environment variables from .env file
-load_dotenv(find_dotenv())
-hf_api_key = os.getenv('HF_API_KEY')
-endpoint_url = os.getenv('HF_API_ITT_BASE')
-
-# Helper function for image-to-text API
-
-def get_completion(image, parameters=None, endpoint_url=endpoint_url):
-    headers = {
-        "Authorization": f"Bearer {hf_api_key}",
-        "Content-Type": "application/json"
-    }
-    # Convert image to base64 format
-    buffered = BytesIO()
-    image.save(buffered, format="JPEG")
-    image_base64 = base64.b64encode(buffered.getvalue()).decode("utf-8")
-
-    data = {"inputs": {"image": image_base64}}
-    if parameters is not None:
-        data.update({"parameters": parameters})
-
-    response = requests.post(endpoint_url, headers=headers, data=json.dumps(data))
-
-    if response.status_code != 200:
-        return {"error": response.text}
+# Load BLIP image captioning model via Hugging Face pipeline
+captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
 
-    try:
-        # Try parsing the response as JSON
-        response_data = json.loads(response.content.decode("utf-8"))
-
-        # Check if it's a list and extract the first item
-        if isinstance(response_data, list) and len(response_data) > 0:
-            return response_data[0]
-        elif isinstance(response_data, dict):
-            return response_data
-        else:
-            return {"error": "Unexpected response format"}
-    except json.JSONDecodeError:
-        return {"error": "Failed to decode API response"}
-
-
-# Helper function to download and process the image from a URL
+# Helper function to download/process image and generate caption
 def caption_image(image_url):
     try:
+        # Load image from URL
         response = requests.get(image_url)
         response.raise_for_status()
-        image = Image.open(BytesIO(response.content)).convert("RGB")
-        
-        # Get caption from API
-        caption_response = get_completion(image)
-
-        # Handle API response
-        if "error" in caption_response:
-            return f"Error: {caption_response['error']}"
+        image = Image.open(io.BytesIO(response.content)).convert("RGB")
 
-        return caption_response.get("generated_text", "No caption generated.")
+        # Generate caption using the pipeline
+        caption = captioner(image)[0]["generated_text"]
+        return caption
 
     except Exception as e:
         return f"Error processing image: {str(e)}"
 
-# Gradio interface
+# Gradio interface with JPEG examples
 demo = gr.Interface(
     fn=caption_image,
     inputs=gr.Textbox(label="Image URL"),
     outputs="text",
     title="Image Captioning App",
     description=(
-        "Upload an image or use one of the predefined samples to generate a caption. "
-        "This app uses a Hugging Face Inference Endpoint for the `Salesforce/blip-image-captioning-base` model."
+        "Upload an image or use one of the predefined examples to generate a caption. "
+        "This app uses `Salesforce/blip-image-captioning-base`."
     ),
-    #article="Free images are available on: [https://free-images.com/](https://free-images.com/)"
-    article="Free images are available on: [https://free-images.com/](https://free-images.com/), [https://unsplash.com/](https://unsplash.com/), [https://pixabay.com/](https://pixabay.com/)"
-
+    examples=[
+        ['https://free-images.com/lg/9e46/white_bengal_tiger_tiger_0.jpg']
+    ],
+    flagging_mode="never"
 )
 
 if __name__ == "__main__":