create app.py

app.py

@@ -0,0 +1,22 @@
+from transformers import BlipForQuestionAnswering 
+model = BlipForQuestionAnswering.from_pretrained(
+    "Salesforce/blip-vqa-base")
+from transformers import AutoProcessor
+from PIL import Image
+import gradio as gr
+
+def answer_question(image, question):
+    inputs = processor(image, question, return_tensors="pt")
+    out = model.generate(**inputs)
+    answer = processor.decode(out[0], skip_special_tokens=True)
+    return answer
+
+# Create Gradio interface
+image_input = gr.Image(label="Upload Image")
+question_input = gr.Textbox(label="Ask a Question")
+output = gr.Textbox(label="Answer")
+
+interface = gr.Interface(fn=answer_question, inputs=[image_input, question_input], outputs=output, title="Multimodal Question Answering")
+
+interface.launch()
+