Create app.py

app.py

@@ -0,0 +1,50 @@
+# -*- coding: utf-8 -*-
+"""app.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1_HQHDuRl3mgto6slVIJGSlZ5DZeSs4El
+"""
+
+import torch
+from transformers import pipeline
+import gradio as gr
+
+# Choose device: GPU if available, otherwise CPU. On Hugging Face Spaces, unless you explicitly pick a GPU runtime, you’re on CPU only
+if torch.cuda.is_available():
+    vqa = pipeline(
+        task="visual-question-answering",
+        model="Salesforce/blip-vqa-base",
+        torch_dtype=torch.float16,#newer versions of TRANSFORMERS in Hugging face is torch_dtype not dtype. dtype is still working fine in Google Colab space
+        device=0,          # GPU
+        use_fast=False,
+    )
+else:
+    vqa = pipeline(
+        task="visual-question-answering",
+        model="Salesforce/blip-vqa-base",
+        device=-1,         # CPU
+        use_fast=False,
+    )
+
+def answer_question(image, question):
+    if not question:
+        return "Please type a question about the image."
+    # vqa returns a list of dicts like [{'score':..., 'answer':...}]
+    result = vqa(question=question, image=image)
+    return result[0]["answer"]
+
+demo = gr.Interface(
+    fn=answer_question,
+    inputs=[
+        gr.Image(type="pil", label="Upload an image"),
+        gr.Textbox(label="Question", placeholder="e.g. What is the weather in this image?"),
+    ],
+    outputs=gr.Textbox(label="Answer"),
+    title="BLIP Visual Question Answering",
+    description="Ask a question about the uploaded image using Salesforce/blip-vqa-base.",
+)
+
+if __name__ == "__main__":
+    demo.launch()