def main()

in src/embeddings_streamlit.py [0:0]

• 38 lines of code
• 7 McCabe index (conditional complexity)

def main():
    st.title("Hugging Face Embeddings Visualization")

    # --- Model Selection ---
    model_name = st.text_input(
        "Enter Hugging Face Model Name",
        value="sentence-transformers/all-MiniLM-L6-v2"
    )

    # Load the model
    model = load_model(model_name)

    # --- Text Input ---
    user_input = st.text_area(
        "Enter one or more sentences (each on a new line):",
        "Hello world!\nStreamlit is awesome.\nHugging Face rocks!"
    )
    texts = [preprocess(line.strip()) for line in user_input.split('\n') if line.strip()]

    # --- Reduction Options ---
    method = st.radio("Dimensionality Reduction Method", ("PCA", "t-SNE"))
    dims = st.radio("Number of Dimensions to Display", (2, 3))

    # --- Button to Compute ---
    if st.button("Compute & Visualize Embeddings"):
        if len(texts) == 0:
            st.warning("Please enter some text.")
        else:
            # Get embeddings
            embeddings = get_embeddings(texts, model)
            # Reduce to 2D or 3D
            reduced_embeddings = reduce_dimensions(embeddings, method=method, n_components=dims)

            if dims == 2:
                # 2D Plot
                fig = px.scatter(
                    x=reduced_embeddings[:, 0],
                    y=reduced_embeddings[:, 1],
                    text=texts,
                    title=f"{method} Embeddings (2D)"
                )
                fig.update_traces(textposition='top center')
                st.plotly_chart(fig, use_container_width=True)
            else:
                # 3D Plot
                fig = px.scatter_3d(
                    x=reduced_embeddings[:, 0],
                    y=reduced_embeddings[:, 1],
                    z=reduced_embeddings[:, 2],
                    text=texts,
                    title=f"{method} Embeddings (3D)"
                )
                st.plotly_chart(fig, use_container_width=True)