Update app.py

app.py

@@ -929,24 +929,108 @@ with gr.Blocks(title="Toxicology PDF → Grounded Extractor") as demo:
             chunk_chars = gr.Slider(1200, 9000, value=3200, step=100, label="Chunk size (chars)")
             max_context_chars = gr.Slider(5000, 45000, value=20000, step=1000, label="Max context sent to GPT (chars)")
 
+        # -------------------------
+        # Controlled Vocabulary (guided editor)
+        # -------------------------
         gr.Markdown("## Controlled Vocabulary (guided editor)")
-        vocab_mode = gr.Radio(choices=["Guided", "Advanced (Raw JSON)"], value="Guided", label="Vocab editor mode")
-
+        
+        vocab_mode = gr.Radio(
+            choices=["Guided", "Advanced (Raw JSON)"],
+            value="Guided",
+            label="Vocab editor mode"
+        )
+        
+        vocab_category = gr.Dropdown(label="Category (lists only)", choices=[], value=None)
+        
+        # NEW: Search box
+        vocab_search = gr.Textbox(
+            label="Search terms",
+            placeholder="Type to filter (e.g., 471, AMES, comet)",
+            lines=1
+        )
+        
         with gr.Row():
-            vocab_category = gr.Dropdown(label="Category (lists only)", choices=[], value=None)
             vocab_term_add = gr.Textbox(label="Add term", placeholder="type term and click Add")
             vocab_add_btn = gr.Button("Add")
+        
         with gr.Row():
             vocab_term_remove = gr.Textbox(label="Remove term", placeholder="type exact term and click Remove")
             vocab_remove_btn = gr.Button("Remove")
             vocab_apply_btn = gr.Button("Apply table changes to category")
             vocab_reset_btn = gr.Button("Reset vocab to defaults")
-
-        vocab_terms_df = gr.Dataframe(headers=["term"], label="Terms (edit directly)", interactive=True, wrap=True)
+        
+        # IMPORTANT: define vocab_terms_df BEFORE using it in any event wiring
+        vocab_terms_df = gr.Dataframe(
+            headers=["term"],
+            label="Terms (full list; edit directly)",
+            interactive=True,
+            wrap=True
+        )
+        
+        # NEW: filtered preview (read-only)
+        vocab_terms_filtered = gr.Dataframe(
+            headers=["term"],
+            label="Filtered preview (read-only)",
+            interactive=False,
+            wrap=True
+        )
+        
         vocab_status = gr.Textbox(label="Vocab status", interactive=False)
-
+        
         with gr.Accordion("Advanced: Raw vocab JSON (auto-generated)", open=False):
             vocab_json = gr.Textbox(label="Controlled vocab JSON", lines=12, interactive=False)
+        
+        # -------------------------
+        # Filtering helper + event
+        # -------------------------
+        def vocab_filter_preview(terms_df, search):
+            try:
+                df = terms_df if isinstance(terms_df, pd.DataFrame) else pd.DataFrame(terms_df, columns=["term"])
+            except Exception:
+                df = pd.DataFrame(columns=["term"])
+            return _filter_terms_df(df, search)
+        
+        # Wire events AFTER components exist
+        vocab_category.change(
+            fn=vocab_load_category,
+            inputs=[vocab_state, vocab_category, vocab_search],
+            outputs=[vocab_terms_df, vocab_terms_filtered, vocab_status]
+        )
+        
+        vocab_search.change(
+            fn=vocab_filter_preview,
+            inputs=[vocab_terms_df, vocab_search],
+            outputs=[vocab_terms_filtered]
+        )
+        
+        vocab_add_btn.click(
+            fn=vocab_add_term,
+            inputs=[vocab_state, vocab_category, vocab_term_add, vocab_search],
+            outputs=[vocab_terms_df, vocab_terms_filtered, vocab_term_add, vocab_status]
+        )
+        
+        vocab_remove_btn.click(
+            fn=vocab_remove_term,
+            inputs=[vocab_state, vocab_category, vocab_term_remove, vocab_search],
+            outputs=[vocab_terms_df, vocab_terms_filtered, vocab_term_remove, vocab_status]
+        )
+        
+        vocab_apply_btn.click(
+            fn=vocab_apply_df,
+            inputs=[vocab_state, vocab_category, vocab_terms_df, vocab_search],
+            outputs=[vocab_json, vocab_terms_filtered, vocab_status]
+        )
+        
+        vocab_reset_btn.click(
+            fn=vocab_reset_defaults,
+            inputs=None,
+            outputs=[vocab_state, vocab_category, vocab_terms_df, vocab_json, vocab_status]
+        ).then(
+            fn=vocab_load_category,
+            inputs=[vocab_state, vocab_category, vocab_search],
+            outputs=[vocab_terms_df, vocab_terms_filtered, vocab_status]
+        )
+
 
         gr.Markdown("## Extraction Spec (Field Builder)")
         with gr.Row():