main_streamlit.py

import streamlit as st
import pandas as pd
import txtai

@st.cache_resource
def load_data_and_embeddings():

    # Load same dataset
    df = pd.read_csv("seth-data.csv").dropna()

    # IMPORTANT: same sample as build_index.py
    sample = df.sample(1000, random_state=1)

    titles = sample["title"].values
    urls = sample["url"].values

    embeddings = txtai.Embeddings({
        "path": "sentence-transformers/all-MiniLM-L6-v2"
    })

    embeddings.load("embeddings_seth.tar.gz")

    return titles, urls, embeddings


titles, urls, embeddings = load_data_and_embeddings()

st.title("Seth Blog Search Engine")

query = st.text_input("Enter a search query")

if st.button("Search"):

    if query:

        results = embeddings.search(query, 5)

        for result in results:

            idx = result[0]

            st.write(f"### {titles[idx]}")
            st.write(urls[idx])

    else:
        st.write("Please enter a query")