Update app.py

app.py

@@ -2,80 +2,80 @@ import os
 import streamlit as st
 from transformers import AutoModel, AutoTokenizer
 from PIL import Image
-import base64
 import uuid
-import time
-from pathlib import Path
 
-# Define a function to load the model
+# Cache the model loading function
+@st.cache_resource
 def load_model(model_name):
-    if model_name == "GOT_CPU":
+    if model_name == "OCR for english or hindi (runs on CPU)":
         tokenizer = AutoTokenizer.from_pretrained('srimanth-d/GOT_CPU', trust_remote_code=True)
         model = AutoModel.from_pretrained('srimanth-d/GOT_CPU', trust_remote_code=True, use_safetensors=True, pad_token_id=tokenizer.eos_token_id)
-        model = model.eval()  # Load model on CPU
-    elif model_name == "GOT_GPU":
+        model.eval()  # Load model on CPU
+    elif model_name == "OCR for english (runs on GPU)":
         tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
         model = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True, low_cpu_mem_usage=True, device_map='cuda', use_safetensors=True, pad_token_id=tokenizer.eos_token_id)
-        model = model.eval().cuda()  # Load model on GPU
+        model.eval().cuda()  # Load model on GPU
     return tokenizer, model
 
-# Define folders for uploads and results
-UPLOAD_FOLDER = "./uploads"
-RESULTS_FOLDER = "./results"
-
-for folder in [UPLOAD_FOLDER, RESULTS_FOLDER]:
-    if not os.path.exists(folder):
-        os.makedirs(folder)
-
-# Function to run the GOT model for plain text OCR
+# Function to run the GOT model for multilingual OCR
 def run_GOT(image, tokenizer, model):
     unique_id = str(uuid.uuid4())
-    image_path = os.path.join(UPLOAD_FOLDER, f"{unique_id}.png")
+    image_path = f"{unique_id}.png"
     
     image.save(image_path)
 
     try:
-        res = model.chat(tokenizer, image_path, ocr_type='ocr')  # Only using plain text OCR
+        # Use the model to extract text
+        res = model.chat(tokenizer, image_path, ocr_type='ocr')  # Extract plain text
         return res
     except Exception as e:
         return f"Error: {str(e)}"
     finally:
+        # Clean up the saved image
         if os.path.exists(image_path):
             os.remove(image_path)
 
-# Function to clean up old files
-def cleanup_old_files():
-    current_time = time.time()
-    for folder in [UPLOAD_FOLDER, RESULTS_FOLDER]:
-        for file_path in Path(folder).glob('*'):
-            if current_time - file_path.stat().st_mtime > 3600:  # 1 hour
-                file_path.unlink()
+# Function to highlight keyword in text
+def highlight_keyword(text, keyword):
+    if keyword:
+        highlighted_text = text.replace(keyword, f"<mark>{keyword}</mark>")
+        return highlighted_text
+    return text
 
 # Streamlit App
-st.set_page_config(page_title="GOT-OCR-2.0 Demo", layout="wide")
+st.set_page_config(page_title="GOT-OCR Multilingual Demo", layout="wide")
 
-uploaded_image = st.file_uploader("Upload your image", type=["png", "jpg", "jpeg"])
+# Creating two columns
+left_col, right_col = st.columns(2)
 
-# Create two columns for layout
-col1, col2 = st.columns(2)
+with left_col:
+    uploaded_image = st.file_uploader("Upload your image", type=["png", "jpg", "jpeg"])
 
-# Model selection
-model_option = st.selectbox("Select Model", ["GOT_CPU", "GOT_GPU"])
+with right_col:
+    # Model selection in the right column
+    model_option = st.selectbox("Select Model", ["OCR for english or hindi (runs on CPU)", "OCR for english (runs on GPU)"])
 
 if uploaded_image:
     image = Image.open(uploaded_image)
     
-    with col1:
+    with left_col:
         st.image(image, caption='Uploaded Image', use_column_width=True)
-
-    with col2:
-        if st.button("Run Plain Text OCR"):
+    
+    with right_col:
+        if st.button("Run OCR"):
             with st.spinner("Processing..."):
-                # Load the selected model
+                # Load the selected model (cached using @st.cache_resource)
                 tokenizer, model = load_model(model_option)
                 result_text = run_GOT(image, tokenizer, model)
-                st.text_area("GOT Output", result_text, height=200)
-
-# Cleanup old files
-cleanup_old_files()
-
+                
+                if "Error" not in result_text:
+                    # Keyword input for search
+                    keyword = st.text_input("Enter a keyword to highlight")
+                    
+                    # Highlight keyword in the extracted text
+                    highlighted_text = highlight_keyword(result_text, keyword)
+                    
+                    # Display the extracted text
+                    st.markdown(highlighted_text, unsafe_allow_html=True)
+                else:
+                    st.error(result_text)