app.py

import solara

# Clean up all the directories used in this notebook
import shutil

shutil.rmtree("./data", ignore_errors=True)

import polars as pl

df = pl.read_csv(
    "https://drive.google.com/uc?export=download&id=1uD3h7xYxr9EoZ0Ggoh99JtQXa3AxtxyU"
)

import string

df = df.with_columns(
    pl.Series("Album", [string.capwords(album) for album in df["Album"]])
)
df = df.with_columns(pl.Series("Song", [string.capwords(song) for song in df["Song"]]))
df = df.with_columns(pl.col("Lyrics").fill_null("None"))

df = df.with_columns(
    text=pl.lit("# ")
    + pl.col("Album")
    + pl.lit(": ")
    + pl.col("Song")
    + pl.lit("\n\n")
    + pl.col("Lyrics")
    # text = pl.col("Lyrics")
)

import lancedb

db = lancedb.connect("data/")

from lancedb.embeddings import get_registry

embeddings = (
    get_registry()
    .get("sentence-transformers")
    .create(name="TaylorAI/gte-tiny", device="cpu")
)

from lancedb.pydantic import LanceModel, Vector


class Songs(LanceModel):
    Song: str
    Lyrics: str
    Album: str
    Artist: str
    text: str = embeddings.SourceField()
    vector: Vector(embeddings.ndims()) = embeddings.VectorField()

table = db.create_table("Songs", schema=Songs)
table.add(data=df)

query = solara.reactive("Which song is about a boy who is having nightmares?")
@solara.component
def Page():
    with solara.Column(margin=10):
        solara.Markdown("# Metallica Song Finder")
        solara.InputText("Enter some query:", query, continuous_update=True)
        if query.value != "":
            df_results = table.search(query.value).limit(10).to_polars()
            df_results = df_results.select(['Song', 'Album', '_distance', 'Lyrics', 'Artist'])
            solara.DataFrame(df_results, items_per_page=10)