Update app.py

app.py

@@ -62,6 +62,12 @@ def load_embedder(model_name, pool_strat):
         pooling_mode_max_tokens=("max" in pool_strat),
         pooling_mode_cls_token=("cls" in pool_strat)
     )
+
+    modules = [word_emb, pool_model]
+
+    # NEW MATH STEP: If user checked the box, append the Normalization layer!
+    if apply_normalization:
+        modules.append(models.Normalize())
     return SentenceTransformer(modules=[word_emb, pool_model])
 
 # ==========================================
@@ -105,6 +111,7 @@ st.header("⚙️ Model Configuration")
 with st.expander("1️⃣ Semantic Layer (Embeddings & Pooling)", expanded=True):
     ui_embedding = st.selectbox("Embedding Model", list(EMBEDDING_MAP.keys()))
     ui_pooling = st.selectbox("Pooling Strategy", list(POOLING_MAP.keys()))
+    ui_normalize = st.checkbox("Apply L2 Normalization (Recommended)", value=True, help="Forces all vectors to have a length of 1.0 so length doesn't bias the clustering.")
 
 with st.expander("2️⃣ Geometry Layer (Dimensionality Reduction)", expanded=True):
     ui_algo = st.selectbox("Algorithm", ["UMAP (Complex geometry)", "PCA (Fast/Deterministic)"])
@@ -171,7 +178,9 @@ if st.button("🚀 Run Topic Modeling Pipeline", type="primary", use_container_w
         
         vectorizer_model = CountVectorizer(stop_words=stop_w, ngram_range=ngram_range, max_df=0.85 if auto_noise and dataset_size > 10 else 1.0)
         
-        custom_embedder = load_embedder(EMBEDDING_MAP[ui_embedding], POOLING_MAP[ui_pooling])
+        #custom_embedder = load_embedder(EMBEDDING_MAP[ui_embedding], POOLING_MAP[ui_pooling])
+        # Ensure you pass the new variable into the function!
+        custom_embedder = load_embedder(EMBEDDING_MAP[ui_embedding], POOLING_MAP[ui_pooling], ui_normalize)
         embeddings = custom_embedder.encode(sentences)
         
         # Fallback Logic (Step 3 representation in code)