| import gradio as gr | |
| from byaldi import RAGMultiModalModel | |
| model = RAGMultiModalModel.from_pretrained("vidore/colpali") | |
| def extract_and_search(image, keyword): | |
| extracted_text = model.predict(image) | |
| matching_lines = [line for line in extracted_text.splitlines() if keyword.lower() in line.lower()] | |
| return extracted_text, matching_lines | |
| interface = gr.Interface( | |
| fn=extract_and_search, | |
| inputs=[ | |
| gr.Image(type="pil", label="Upload Image"), | |
| gr.Textbox(label="Enter Keyword") | |
| ], | |
| outputs=[ | |
| gr.Textbox(label="Extracted Text"), | |
| gr.Textbox(label="Matching Lines") | |
| ], | |
| title="ColPali OCR with Keyword Search", | |
| description="Upload an image and enter a keyword to search within the extracted text." | |
| ) | |
| interface.launch(share=True) |