import duckdb
import polars as pl
from datasets import load_dataset
from model2vec import StaticModel

# Load a model from the HuggingFace hub (in this case the potion-base-8M model)
model_name = "minishlab/potion-base-8M"
model = StaticModel.from_pretrained(model_name)

# Make embeddings
ds = load_dataset("fka/awesome-chatgpt-prompts")
df = ds["train"].to_polars()
embeddings = model.encode(df["act"])
df = df.with_columns(pl.Series(embeddings).alias("embeddings"))
vector = model.encode("An Ethereum Developer", show_progress_bar=True)
duckdb.sql(
    query=f"""
    SELECT *
    FROM df
    ORDER BY array_cosine_distance(embeddings, {vector.tolist()}::FLOAT[256])
    LIMIT 10
    """
).show()