Update src/streamlit_app.py

src/streamlit_app.py

@@ -60,9 +60,15 @@ if st.button("Calculate Similarities"):
             st.stop()
 
         try:
-            st.info("Generating embeddings with MRL=256, ubinary")
-            primary_embedding = model.encode(primary_keyword, convert_to_tensor=False, normalize_embeddings=True, device="cpu", mrl=256, ubinary=True)
-            keyword_embeddings = model.encode(keyword_list, convert_to_tensor=False, normalize_embeddings=True, device="cpu", mrl=256, ubinary=True)
+            st.info("Generating embeddings...")
+            all_texts = [primary_keyword] + keyword_list
+            embeddings = model.encode(all_texts, normalize_embeddings=True)
+
+            # Apply Matryoshka Representation Learning: slice to 256 dims
+            mrl_embeddings = embeddings[:, :256]
+
+            primary_embedding = mrl_embeddings[0]
+            keyword_embeddings = mrl_embeddings[1:]
         except Exception as e:
             st.error(f"Embedding failed: {e}")
             st.stop()
@@ -90,8 +96,7 @@ if st.button("Calculate Similarities"):
         # 3D PCA Plot
         st.subheader("3D PCA of Embeddings")
         pca = PCA(n_components=3)
-        all_embeddings = np.vstack([primary_embedding] + keyword_embeddings)
-        pca_result = pca.fit_transform(all_embeddings)
+        pca_result = pca.fit_transform(mrl_embeddings)
 
         pca_df = pd.DataFrame(pca_result, columns=["PC1", "PC2", "PC3"])
         pca_df["Label"] = ["Primary"] + keyword_list
@@ -99,8 +104,8 @@ if st.button("Calculate Similarities"):
         st.plotly_chart(fig, use_container_width=True)
 
         with st.expander("🔧 Technical Details (click to expand)"):
-            st.write("Primary Embedding:", primary_embedding)
-            st.write("Keyword Embeddings:", keyword_embeddings)
+            st.write("Primary Embedding:", primary_embedding.tolist())
+            st.write("Keyword Embeddings:", keyword_embeddings.tolist())
 
 # Footer
 st.markdown("---")