Update app.py

app.py

@@ -1,6 +1,4 @@
 import os
-import zipfile
-import time
 import streamlit as st
 from PIL import Image as PILImage
 from PIL import Image as pilImage
@@ -45,14 +43,15 @@ def display_images(image_collection, query_text, max_distance=None, debug=False)
                 st.write(f"URI: {uri} - Distance: {distance}")
             try:
                 img = PILImage.open(uri)
-                img = img.resize((img.width // 2, img.height // 2))  # Resize image for better performance
                 st.image(img, width=300)
             except Exception as e:
                 st.error(f"Error loading image {uri}: {e}")
         else:
             if debug:
                 st.write(f"URI: {uri} - Distance: {distance} (Filtered out)")
+
             
+
 def display_videos_streamlit(video_collection, query_text, max_distance=None, max_results=5, debug=False):
     """
     Display videos in a Streamlit app based on a query.
@@ -171,8 +170,8 @@ def format_prompt_inputs(image_collection, text_collection, video_collection, us
     if image_candidates:
         image = image_candidates[0]
         with PILImage.open(image) as img:
-            img = img.resize((img.width // 2, img.height // 2))
-            # img = img.convert("L")
+            img = img.resize((img.width // 6, img.height // 6))
+            img = img.convert("L")
             with io.BytesIO() as output:
                 img.save(output, format="JPEG", quality=60)
                 compressed_image_data = output.getvalue()
@@ -182,56 +181,37 @@ def format_prompt_inputs(image_collection, text_collection, video_collection, us
         inputs["image_data_1"] = ""
 
     return inputs
-    
+
+import time  # To simulate delays during processing
+
 def page_1():
-    st.title("Page 1: Upload and Process PDFs")
-
-    # File uploader for PDF files
-    uploaded_pdf_files = st.file_uploader("Upload PDF files", type=["pdf"], accept_multiple_files=True)
-
-    # Button to trigger processing
-    if uploaded_pdf_files and st.button("Process Files"):
-        # Temporary folder to store extracted files
-        temp_folder = "/tmp/extracted_files"
-        os.makedirs(temp_folder, exist_ok=True)
-
-        # Progress bar
-        progress_bar = st.progress(0)
-        status_text = st.empty()
-
-        try:
-            total_files = len(uploaded_pdf_files)
-            files_processed = 0
-
-            # Process PDF files
-            for uploaded_pdf in uploaded_pdf_files:
-                pdf_path = f"/tmp/{uploaded_pdf.name}"
-                with open(pdf_path, "wb") as f:
-                    f.write(uploaded_pdf.getbuffer())
-
-                # Simulate PDF processing (replace with actual PDF processing logic)
-                files_processed += 1
-                progress_bar.progress(files_processed / total_files)  # Updated progress calculation
-                status_text.text(f"Processing PDF: {uploaded_pdf.name} ({files_processed}/{total_files})")
-                
-                # Call your actual PDF processing function here
-                image_collection, text_collection, video_collection = process_pdf(pdf_path)
+    st.title("Page 1: Upload and Process PDF")
+
+    uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
+    if uploaded_file:
+        pdf_path = f"/tmp/{uploaded_file.name}"
+        with open(pdf_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
 
-                # Save collections to session state
+        # Display a spinner while processing
+        with st.spinner("Processing PDF... Please wait."):
+            try:
+                # Simulate processing stages with a delay (this is just an example)
+                time.sleep(1)  # Simulate a step in the processing
+
+                # Step 1: Process images, texts, and videos
+                st.text("Extracting content from PDF...")
+                image_collection, text_collection, video_collection = process_pdf(pdf_path)
                 st.session_state.image_collection = image_collection
                 st.session_state.text_collection = text_collection
                 st.session_state.video_collection = video_collection
 
-            # Update status after processing
-            status_text.text("Processing completed successfully!")
+                # Simulate a delay for finalizing (if needed)
+                time.sleep(1)  # Simulate final step
 
-            st.success("PDFs processed successfully! Collections saved to session state.")
-
-        except Exception as e:
-            progress_bar.progress(0)
-            status_text.text("")
-            st.error(f"Error processing files: {e}")
-            st.write(f"Error details: {e}")
+                st.success("PDF processed successfully! Collections saved to session state.")
+            except Exception as e:
+                st.error(f"Error processing PDF: {e}")
 
 def page_2():
     st.title("Page 2: Query and Use Processed Collections")
@@ -258,11 +238,9 @@ def page_2():
             display_images(image_collection, query, max_distance=1.55, debug=True)
 
             st.markdown("### Videos")
-            display_videos_streamlit(video_collection, query_text=query, max_distance=None, max_results=5, debug=False)
             frame = inputs["frame"]
-            
             if frame:
-                video_path = f"video/StockVideos-CC0/{os.path.basename(frame).split('/')[0]}.mp4"
+                video_path = f"StockVideos-CC0/{os.path.basename(frame).split('/')[0]}.mp4"
                 if os.path.exists(video_path):
                     st.video(video_path)
                 else: