UI improvements: Remove confidence scores from display, make Document Preview collapsible, simplify HTML output formatting

app.py

@@ -364,8 +364,8 @@ with main_tab2:
     else:
         st.subheader("Previously Processed Documents")
         
-        # Display previous results in a selectable list, with default confidence of 85%
-        previous_files = [f"{i+1}. {result.get('file_name', 'Document')} ({result.get('confidence_score', 0.85):.1%} confidence)" 
+        # Display previous results in a selectable list
+        previous_files = [f"{i+1}. {result.get('file_name', 'Document')}" 
                          for i, result in enumerate(st.session_state.previous_results)]
         
         selected_index = st.selectbox("Select a previous document:", 
@@ -385,9 +385,7 @@ with main_tab2:
         with prev_tabs[0]:
             st.write(f"**File:** {selected_result.get('file_name', 'Document')}")
             
-            # Show confidence score (default to 85% if not available)
-            confidence = selected_result.get('confidence_score', 0.85)
-            st.write(f"**OCR Confidence:** {confidence:.1%}")
+            # Remove confidence score from display
             
             # Show languages if available
             if 'languages' in selected_result and selected_result['languages']:
@@ -551,78 +549,77 @@ with main_tab1:
     # Preview column
     with col2:
         if uploaded_file is not None:
-            st.subheader("Document Preview")
-            
-            file_ext = Path(uploaded_file.name).suffix.lower()
-            
-            # Show preview tabs for original and processed (if applicable)
-            if uploaded_file.type and uploaded_file.type.startswith('image/'):
-                # For image files
-                preview_tabs = st.tabs(["Original"])
+            with st.expander("Document Preview", expanded=False):
+                file_ext = Path(uploaded_file.name).suffix.lower()
                 
-                # Show original image preview
-                with preview_tabs[0]:
-                    try:
-                        image = safe_open_image(uploaded_file.getvalue())
-                        if image:
-                            # Display with controlled size
-                            st.image(image, caption=uploaded_file.name, width=400)
-                        else:
-                            st.info("Image preview not available")
-                    except Exception:
-                        st.info("Image preview could not be displayed")
+                # Show preview tabs for original and processed (if applicable)
+                if uploaded_file.type and uploaded_file.type.startswith('image/'):
+                    # For image files
+                    preview_tabs = st.tabs(["Original"])
                 
-                # Add processed preview if preprocessing options are selected
-                if any(preprocessing_options.values()):
-                    # Create a before-after comparison
-                    st.subheader("Preprocessing Preview")
-                    
-                    try:
-                        # Process the image with selected options
-                        processed_bytes = preprocess_image(uploaded_file.getvalue(), preprocessing_options)
-                        processed_image = safe_open_image(processed_bytes)
-                        
-                        # Show before/after in columns
-                        col1, col2 = st.columns(2)
-                        
-                        with col1:
-                            st.write("**Original**")
+                    # Show original image preview
+                    with preview_tabs[0]:
+                        try:
                             image = safe_open_image(uploaded_file.getvalue())
                             if image:
-                                st.image(image, width=300) 
-                        
-                        with col2:
-                            st.write("**Processed**")
-                            if processed_image:
-                                st.image(processed_image, width=300)
+                                # Display with controlled size
+                                st.image(image, caption=uploaded_file.name, width=400)
                             else:
-                                st.info("Processed preview not available")
-                    except Exception:
-                        st.info("Preprocessing preview could not be generated")
-            
-            elif file_ext == ".pdf":
-                # For PDF files
-                try:
-                    # Convert first page of PDF to image
-                    pdf_bytes = uploaded_file.getvalue()
-                    
-                    with st.spinner("Generating PDF preview..."):
-                        images = convert_from_bytes(pdf_bytes, first_page=1, last_page=1, dpi=150)
+                                st.info("Image preview not available")
+                        except Exception:
+                            st.info("Image preview could not be displayed")
                     
-                    if images:
-                        # Convert to JPEG for display
-                        first_page = images[0]
-                        img_bytes = io.BytesIO()
-                        first_page.save(img_bytes, format='JPEG')
-                        img_bytes.seek(0)
+                    # Add processed preview if preprocessing options are selected
+                    if any(preprocessing_options.values()):
+                        # Create a before-after comparison
+                        st.subheader("Preprocessing Preview")
                         
-                        # Display preview
-                        st.image(img_bytes, caption=f"PDF Preview: {uploaded_file.name}", width=400)
-                        st.info(f"PDF document with {len(convert_from_bytes(pdf_bytes, dpi=100))} pages")
-                    else:
-                        st.info(f"PDF preview not available: {uploaded_file.name}")
-                except Exception:
-                    st.info(f"PDF preview could not be displayed: {uploaded_file.name}")
+                        try:
+                            # Process the image with selected options
+                            processed_bytes = preprocess_image(uploaded_file.getvalue(), preprocessing_options)
+                            processed_image = safe_open_image(processed_bytes)
+                            
+                            # Show before/after in columns
+                            col1, col2 = st.columns(2)
+                            
+                            with col1:
+                                st.write("**Original**")
+                                image = safe_open_image(uploaded_file.getvalue())
+                                if image:
+                                    st.image(image, width=300) 
+                            
+                            with col2:
+                                st.write("**Processed**")
+                                if processed_image:
+                                    st.image(processed_image, width=300)
+                                else:
+                                    st.info("Processed preview not available")
+                        except Exception:
+                            st.info("Preprocessing preview could not be generated")
+                
+                elif file_ext == ".pdf":
+                    # For PDF files
+                    try:
+                        # Convert first page of PDF to image
+                        pdf_bytes = uploaded_file.getvalue()
+                        
+                        with st.spinner("Generating PDF preview..."):
+                            images = convert_from_bytes(pdf_bytes, first_page=1, last_page=1, dpi=150)
+                        
+                        if images:
+                            # Convert to JPEG for display
+                            first_page = images[0]
+                            img_bytes = io.BytesIO()
+                            first_page.save(img_bytes, format='JPEG')
+                            img_bytes.seek(0)
+                            
+                            # Display preview
+                            st.image(img_bytes, caption=f"PDF Preview: {uploaded_file.name}", width=400)
+                            st.info(f"PDF document with {len(convert_from_bytes(pdf_bytes, dpi=100))} pages")
+                        else:
+                            st.info(f"PDF preview not available: {uploaded_file.name}")
+                    except Exception:
+                        st.info(f"PDF preview could not be displayed: {uploaded_file.name}")
     
     # Results section - spans full width
     if 'process_button' in locals() and process_button:
@@ -656,9 +653,7 @@ with main_tab1:
                 # Display file info
                 st.write(f"**File:** {result.get('file_name', uploaded_file.name)}")
                 
-                # Show confidence score (default to 85% if not available)
-                confidence = result.get('confidence_score', 0.85)
-                st.write(f"**OCR Confidence:** {confidence:.1%}")
+                # Remove confidence score from display
                 
                 # Show languages if available
                 if 'languages' in result and result['languages']:
@@ -705,10 +700,9 @@ with main_tab1:
                                     if isinstance(item, str):
                                         st.markdown(f"* {item}")
                                     elif isinstance(item, dict):
-                                        # Create formatted display for dictionary items instead of raw JSON
-                                        with st.expander(f"Details {list(item.keys())[0] if item else ''}"):
-                                            for k, v in item.items():
-                                                st.markdown(f"**{k}:** {v}")
+                                        # Create formatted text display for dictionary items instead of raw JSON
+                                        st.markdown(f"* **{list(item.keys())[0] if item else 'Item'}**: " + 
+                                                 ", ".join([f"{k}: {v}" for k, v in item.items()]))
                             elif isinstance(content, dict):
                                 # Special handling for poem type
                                 if 'type' in content and content['type'] == 'poem' and 'lines' in content:
@@ -812,16 +806,10 @@ with main_tab1:
                                     if isinstance(item, str):
                                         html_content += f'<li>{item}</li>\n'
                                     elif isinstance(item, dict):
-                                        # Format dictionary items in the list
-                                        html_content += '<li>\n'
-                                        html_content += '<details>\n'
-                                        html_content += f'<summary>{list(item.keys())[0] if item else "Details"}</summary>\n'
-                                        html_content += '<dl>\n'
-                                        for k, v in item.items():
-                                            html_content += f'<dt>{k}</dt>\n<dd>{v}</dd>\n'
-                                        html_content += '</dl>\n'
-                                        html_content += '</details>\n'
-                                        html_content += '</li>\n'
+                                        # Format dictionary items in the list as simple text
+                                        key_item = list(item.keys())[0] if item else "Item"
+                                        value_text = ", ".join([f"{k}: {v}" for k, v in item.items()])
+                                        html_content += f'<li><strong>{key_item}</strong>: {value_text}</li>\n'
                                     else:
                                         html_content += f'<li>{str(item)}</li>\n'
                                 html_content += '</ul>\n'

process_file.py

@@ -54,16 +54,13 @@ def process_file(uploaded_file, use_vision=True, processor=None, custom_prompt=N
             "use_vision": use_vision
         })
         
-        # Always ensure confidence score is present (default to 85%)
-        if 'confidence_score' not in result:
-            result['confidence_score'] = 0.85
+        # No longer needed - removing confidence score
         
         return result
     except Exception as e:
         return {
             "error": str(e),
-            "file_name": uploaded_file.name,
-            "confidence_score": 0.85  # Add default confidence score even to error results
+            "file_name": uploaded_file.name
         }
     finally:
         # Clean up the temporary file

structured_ocr.py

@@ -308,8 +308,7 @@ class StructuredOCR:
                     'total': total_pages
                 }
                 
-            # Add confidence score
-            result['confidence_score'] = confidence_score
+            # Remove confidence score from results
                 
             # Store key parts of the OCR response for image rendering
             # First store the raw response for backwards compatibility
@@ -515,8 +514,7 @@ class StructuredOCR:
                 logger.info(f"Using text-only model: {TEXT_MODEL}")
                 result = self._extract_structured_data_text_only(image_ocr_markdown, file_path.name, custom_prompt)
                 
-            # Add confidence score
-            result['confidence_score'] = confidence_score
+            # Remove confidence score from results
                 
             # Store key parts of the OCR response for image rendering
             # First store the raw response for backwards compatibility
@@ -555,7 +553,6 @@ class StructuredOCR:
                 "file_name": file_path.name,
                 "topics": ["Document"],
                 "languages": ["English"],
-                "confidence_score": 0.0,
                 "error": str(e),
                 "ocr_contents": {
                     "error": f"Failed to process image: {str(e)}",