Add app

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.11
+
+# Set up a new user named "user" with user ID 1000 for permission
+RUN useradd -m -u 1000 user
+# Switch to the "user" user
+USER user
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Upgreade pip
+RUN pip install --no-cache-dir --upgrade pip
+
+COPY --chown=user requirements.txt requirements.txt
+
+# Install requirements
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user app.py app.py
+
+ENTRYPOINT ["solara", "run", "app.py", "--host=0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,67 @@
+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="cuda")
+)
+
+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)

requirements.txt

@@ -0,0 +1,4 @@
+solara==1.39.0
+polars==1.7.1
+lancedb==0.13.0
+sentence-transformers==3.1.1