Update app.py

app.py

@@ -50,19 +50,55 @@ def plot_interactive_embeddings(embeddings, phrases):
         st.error("Please add at least one more phrase to visualize.")
 
 def main():
+    st.set_page_config(layout="wide")
     st.title("Language Model Embeddings Visualization")
 
     st.markdown("""
     This application visualizes embeddings of words and phrases from BERT or RoBERTa language models. 
-    Here's how to use it:
-    1. Choose a model (BERT or RoBERTa) from the dropdown menu.
-    2. Enter words or phrases one at a time, or upload a CSV file with a 'phrase' column.
-    3. View the 2D or 3D plot of the embeddings.
-    4. Download the current database as a CSV file for later use.
     Explore how different words and phrases relate to each other in the embedding space!
     """)
 
-    model_choice = st.selectbox("Choose a model:", ["BERT", "RoBERTa"])
+    # Sidebar
+    with st.sidebar:
+        st.header("Controls")
+        model_choice = st.selectbox("Choose a model:", ["BERT", "RoBERTa"])
+        
+        new_phrase = st.text_input("Enter a new word or phrase:", "")
+        if st.button("Add Phrase"):
+            if new_phrase and new_phrase not in st.session_state.phrases:
+                embedding = get_embeddings([new_phrase], tokenizer, model)[0]
+                save_embeddings_to_db(new_phrase, embedding)
+                st.session_state.phrases.append(new_phrase)
+                st.experimental_rerun()
+        
+        uploaded_file = st.file_uploader("Upload CSV file", type="csv")
+        if uploaded_file is not None:
+            df = pd.read_csv(uploaded_file)
+            phrase_column = next((col for col in ['phrase', 'Phrase'] if col in df.columns), None)
+            if phrase_column:
+                new_phrases = df[phrase_column].dropna().unique().tolist()
+                for phrase in new_phrases:
+                    if phrase and phrase not in st.session_state.phrases:
+                        embedding = get_embeddings([phrase], tokenizer, model)[0]
+                        save_embeddings_to_db(phrase, embedding)
+                        st.session_state.phrases.append(phrase)
+                st.success(f"Successfully imported {len(new_phrases)} new phrases.")
+                st.experimental_rerun()
+            else:
+                st.error("The CSV file must contain a 'phrase' or 'Phrase' column.")
+        
+        if st.button("Clear All Entries"):
+            clear_all_entries()
+            st.session_state.phrases = [default_phrase]
+            embedding = get_embeddings([default_phrase], tokenizer, model)[0]
+            save_embeddings_to_db(default_phrase, embedding)
+            st.experimental_rerun()
+        
+        if st.button("Download Database as CSV"):
+            csv = fetch_data_as_csv()
+            st.download_button(label="Download CSV", data=csv, file_name='embeddings.csv', mime='text/csv')
+
+    # Main area
     tokenizer, model = load_model(model_choice)
 
     default_phrase = "example"
@@ -72,47 +108,15 @@ def main():
         embedding = get_embeddings([default_phrase], tokenizer, model)[0]
         save_embeddings_to_db(default_phrase, embedding)
 
-    st.write(f"Current phrases ({model_choice}):", ", ".join(st.session_state.phrases))
-
-    new_phrase = st.text_input("Enter a new word or phrase:", "")
-    if st.button("Add Phrase"):
-        if new_phrase and new_phrase not in st.session_state.phrases:
-            embedding = get_embeddings([new_phrase], tokenizer, model)[0]
-            save_embeddings_to_db(new_phrase, embedding)
-            st.session_state.phrases.append(new_phrase)
-            st.experimental_rerun()
-
-    uploaded_file = st.file_uploader("Upload CSV file", type="csv")
-    if uploaded_file is not None:
-        df = pd.read_csv(uploaded_file)
-        phrase_column = next((col for col in ['phrase', 'Phrase'] if col in df.columns), None)
-        if phrase_column:
-            new_phrases = df[phrase_column].dropna().unique().tolist()
-            for phrase in new_phrases:
-                if phrase and phrase not in st.session_state.phrases:
-                    embedding = get_embeddings([phrase], tokenizer, model)[0]
-                    save_embeddings_to_db(phrase, embedding)
-                    st.session_state.phrases.append(phrase)
-            st.success(f"Successfully imported {len(new_phrases)} new phrases.")
-            st.experimental_rerun()
-        else:
-            st.error("The CSV file must contain a 'phrase' or 'Phrase' column.")
-
-    if st.button("Clear All Entries"):
-        clear_all_entries()
-        st.session_state.phrases = [default_phrase]
-        embedding = get_embeddings([default_phrase], tokenizer, model)[0]
-        save_embeddings_to_db(default_phrase, embedding)
-        st.experimental_rerun()
-
-    if st.button("Download Database as CSV"):
-        csv = fetch_data_as_csv()
-        st.download_button(label="Download CSV", data=csv, file_name='embeddings.csv', mime='text/csv')
+    st.subheader(f"Current phrases ({model_choice}):")
+    st.write(", ".join(st.session_state.phrases))
 
     embeddings, phrases = get_all_embeddings()
     if len(embeddings) > 0:
         embeddings = np.array(embeddings)
         plot_interactive_embeddings(embeddings, phrases)
+    else:
+        st.info("Add phrases using the sidebar to visualize their embeddings.")
 
 if __name__ == "__main__":
     main()