# see https://github.com/asg017/sqlite-vec/issues/135
import sqlite3
import sqlite_vec
import streamlit as st
db = conn = sqlite3.connect(":memory:")
db.execute("CREATE TABLE movie(title, year, score)")
conn.enable_load_extension(True)
sqlite_vec.load(db)
# Instead of an unpatched load, we can use
#import os
#path = os.path.abspath(os.path.dirname(sqlite_vec.__file__))
#ext_path = os.path.join(path, "vec0.so")
#print(os.listdir(path))
#conn.load_extension(ext_path)
conn.execute("""
create virtual table vec_examples using vec0(
sample_embedding float[8]
);
""")
def out(r):
results = r.fetchall()
print("results", results)
for row in results:
print(row)
st.write(row)
out(conn.execute("""
-- vectors can be provided as JSON or in a compact binary format
insert into vec_examples(rowid, sample_embedding)
values
(1, '[-0.200, 0.250, 0.341, -0.211, 0.645, 0.935, -0.316, -0.924]'),
(2, '[0.443, -0.501, 0.355, -0.771, 0.707, -0.708, -0.185, 0.362]'),
(3, '[0.716, -0.927, 0.134, 0.052, -0.669, 0.793, -0.634, -0.162]'),
(4, '[-0.710, 0.330, 0.656, 0.041, -0.990, 0.726, 0.385, -0.958]');
"""))
out(conn.execute("""
select
rowid,
distance
from vec_examples
where sample_embedding match '[0.890, 0.544, 0.825, 0.961, 0.358, 0.0196, 0.521, 0.175]'
AND k = 3;
"""))
out(conn.execute("""
select
rowid,
distance
from vec_examples
where k = 3;
"""))