Update app.py

app.py

@@ -4,26 +4,16 @@ import streamlit as st
 import torch
 from PIL import Image
 
-# default: Load the model on the available device(s)
+# Default: Load the model on the available device(s)
 @st.cache_resource
 def init_qwen_model():
     _model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto")
     _processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
     return _model, _processor
-# 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-7B-Instruct",
-#     torch_dtype=torch.bfloat16,
-#     attn_implementation="flash_attention_2",
-#     device_map="auto",
-# )
-# 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-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
 
+# Modified function to use only the image as the argument
 @st.cache_data
-def get_qwen_text(uploaded_file):
+def get_qwen_text(uploaded_file, model, processor):
     if uploaded_file is not None:
         # Open the uploaded image file
         image = Image.open(uploaded_file)
@@ -69,23 +59,27 @@ def get_qwen_text(uploaded_file):
 # Streamlit app title
 st.title("OCR Image Text Extraction")
 
+# Initialize the model and processor
 MODEL, PROCESSOR = init_qwen_model()
 
 # File uploader for images
 uploaded_file = st.file_uploader("Choose an image...", type=["png", "jpg", "jpeg"])
 
-st.subheader("Extracted Text:")
-output = get_qwen_text(uploaded_file, MODEL, PROCESSOR)
-st.write(output)
+if uploaded_file:
+    st.subheader("Extracted Text:")
+    output = get_qwen_text(uploaded_file, MODEL, PROCESSOR)
+    st.write(output)
 
-# Keyword search functionality
-st.subheader("Keyword Search")
-search_query = st.text_input("Enter keywords to search within the extracted 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.lower():
-        highlighted_text = output.replace(search_query, f"**{search_query}**")
-        st.write(f"Matching Text: {highlighted_text}")
-    else:
-        st.write("No matching text found.")
+    if search_query:
+        # Check if the search query is in the extracted text
+        if search_query.lower() in output.lower():
+            highlighted_text = output.replace(search_query, f"**{search_query}**")
+            st.write(f"Matching Text: {highlighted_text}")
+        else:
+            st.write("No matching text found.")
+else:
+    st.info("Please upload an image to extract text.")