Create v1.txt

v1.txt

@@ -0,0 +1,85 @@
+import gradio as gr
+import torch
+from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
+from qwen_vl_utils import process_vision_info
+import re
+
+# Load the model on CPU
+def load_model():
+    model = Qwen2VLForConditionalGeneration.from_pretrained(
+        "prithivMLmods/Qwen2-VL-OCR-2B-Instruct", 
+        torch_dtype=torch.float32,
+        device_map="cpu"
+    )
+    processor = AutoProcessor.from_pretrained("prithivMLmods/Qwen2-VL-OCR-2B-Instruct")
+    return model, processor
+
+# Function to extract medicine names
+def extract_medicine_names(image):
+    model, processor = load_model()
+    
+    # Prepare the message with the specific prompt for medicine extraction
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "image",
+                    "image": image,
+                },
+                {"type": "text", "text": "Extract and list ONLY the names of medicines/drugs from this prescription image. Output the medicine names as a numbered list without any additional information or descriptions."},
+            ],
+        }
+    ]
+    
+    # Prepare for inference
+    text = processor.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+    image_inputs, video_inputs = process_vision_info(messages)
+    inputs = processor(
+        text=[text],
+        images=image_inputs,
+        videos=video_inputs,
+        padding=True,
+        return_tensors="pt",
+    )
+    
+    # Generate output
+    generated_ids = model.generate(**inputs, max_new_tokens=256)
+    generated_ids_trimmed = [
+        out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    ]
+    output_text = processor.batch_decode(
+        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )[0]
+    
+    return output_text
+
+# Create Gradio interface
+with gr.Blocks(title="Medicine Name Extractor") as app:
+    gr.Markdown("# Medicine Name Extractor")
+    gr.Markdown("Upload a medical prescription image to extract the names of medicines.")
+    
+    with gr.Row():
+        with gr.Column():
+            input_image = gr.Image(type="pil", label="Upload Prescription Image")
+            extract_btn = gr.Button("Extract Medicine Names", variant="primary")
+        
+        with gr.Column():
+            output_text = gr.Textbox(label="Extracted Medicine Names", lines=10)
+    
+    extract_btn.click(
+        fn=extract_medicine_names,
+        inputs=input_image,
+        outputs=output_text
+    )
+    
+    gr.Markdown("### Notes")
+    gr.Markdown("- This tool uses the Qwen2-VL-OCR model to extract text from prescription images")
+    gr.Markdown("- For best results, ensure the prescription image is clear and readable")
+    gr.Markdown("- Processing may take some time as the model runs on CPU")
+
+# Launch the app
+if __name__ == "__main__":
+    app.launch()