app.py

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
import streamlit as st

# default: Load the model on the available device(s)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
)

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "Qwen/Qwen2-VL-72B-Instruct",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# default processer
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")

# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
# min_pixels = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-72B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)

# Streamlit app title
st.title("OCR Image Text Extraction")

# File uploader for images
uploaded_file = st.file_uploader("Choose an image...", type=["png", "jpg", "jpeg"])

if uploaded_file is not None:
    # Open the uploaded image file
    image = Image.open(uploaded_file)
    st.image(image, caption="Uploaded Image", use_column_width=True)

    messages = [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": "image",
                },
                {"type": "text", "text": "Run Optical Character Recognition on the image."},
            ],
        }
    ]
    
    # Preparation 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",
    )
    inputs = inputs.to("cpu")
    
    # Inference: Generation of the output
    generated_ids = model.generate(**inputs, max_new_tokens=128)
    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
    )

    # Display extracted text
    st.subheader("Extracted Text:")
    st.write(output_text)

    # Keyword search functionality
    st.subheader("Keyword Search")
    search_query = st.text_input("Enter keywords to search within the extracted text")

    if search_query:
        # Check if the search query is in the extracted text
        if search_query.lower() in output_text.lower():
            highlighted_text = output_text.replace(search_query, f"**{search_query}**")
            st.write(f"Matching Text: {highlighted_text}")
        else:
            st.write("No matching text found.")