Add application file

app.py

@@ -0,0 +1,54 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoProcessor
+from datasets import load_dataset
+
+import gradio as g
+
+
+# Initialize the processor and the model
+processor = AutoProcessor.from_pretrained("AkshaySiraswar/Florence-2-FT-DocVQA", trust_remote_code=True, force_download=True)
+model = AutoModelForCausalLM.from_pretrained("AkshaySiraswar/Florence-2-FT-DocVQA", trust_remote_code=True).to("cuda" if torch.cuda.is_available() else "cpu")
+r
+def generate_response(image, question):
+    try:
+        if image.mode != "RGB":
+            image = image.convert("RGB")
+
+        inputs = processor(text=question, images=image, return_tensors="pt")
+
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        model.to(device)
+        inputs = {key: value.to(device) for key, value in inputs.items()}
+
+        generated_ids = model.generate(
+            input_ids=inputs["input_ids"],
+            pixel_values=inputs["pixel_values"],
+            max_length=1024,
+            num_beams=3,
+            early_stopping=True
+        )
+
+        response = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+        return response
+    except Exception as e:
+        return f"Error processing image: {e}"
+
+# Example images for demonstration (update paths as needed)
+examples = [
+    ["demo.jpg", "what is the address in the page?"],
+    ["demo.jpg", "what is the phone number?"],
+    ["demo.jpg", "what is the email address?"]
+]
+
+# Gradio interface
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=[gr.Image(type="pil"), gr.Textbox(label="Question")],
+    outputs=gr.Textbox(label="Response"),
+    examples=examples,
+    title="Image to Text Extractor",
+    description="Upload an image and provide a question. This tool will extract the relevant information from the image based on your question."
+)
+
+# Launch the interface
+iface.launch()