Update app.py

app.py

@@ -27,8 +27,8 @@ st.sidebar.markdown("## Settings")
 selected = st.sidebar.selectbox("Select a collection", list(collections.keys()))
 collection_path = collections[selected]
 
-# Updated: Use LOC Search API with partof filter
-collection_url = f"https://www.loc.gov/search/?q=&fa=partof:{collection_path}&fo=json"
+# Updated: Use LOC Search API with partof filter (URL encoding for colon)
+collection_url = f"https://www.loc.gov/search/?q=&fa=partof%3A{collection_path}&fo=json"
 st.sidebar.write(f"Selected Collection: {selected}")
 
 # Fetch data from LOC API
@@ -42,6 +42,7 @@ records = data.get("results", [])
 items = []
 for record in records:
     items.append({
+        "id": record.get("id"),
         "title": record.get("title"),
         "date": record.get("date"),
         "subject": record.get("subject"),
@@ -70,6 +71,13 @@ if not metadata_df.empty:
     incomplete_records = metadata_df[metadata_df.isnull().any(axis=1)]
     st.dataframe(incomplete_records)
 
+    # Show exact items that need updates
+    st.subheader("📌 Identifiers of Items Needing Metadata Updates")
+    if not incomplete_records.empty:
+        st.write(incomplete_records[['id', 'title']])
+    else:
+        st.success("All records are complete!")
+
     # Suggest metadata using text similarity (basic example)
     st.subheader("✨ Suggested Metadata Enhancements")
     filled_descriptions = metadata_df[metadata_df['description'].notnull()]['description'].astype(str)
@@ -80,7 +88,6 @@ if not metadata_df.empty:
     suggestions = []
     for idx, row in incomplete_records.iterrows():
         if pd.isna(row['subject']) and pd.notna(row['description']):
-            # Find most similar description
             desc_vec = tfidf.transform([str(row['description'])])
             sims = cosine_similarity(desc_vec, tfidf_matrix).flatten()
             top_idx = sims.argmax()