liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-05 20:20:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

Changed indices to start at 1 for sparse vectors to match SQL

Browse Source
This commit is contained in:
Andrew Kane
2024-04-06 14:02:07 -07:00
parent aec853dc68
commit 4450029bdc
13 changed files with 83 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -501,19 +501,21 @@ SELECT * FROM (
Use the `sparsevec` type to store sparse vectors
```sql
CREATE TABLE items (id bigserial PRIMARY KEY, embedding sparsevec(10));
CREATE TABLE items (id bigserial PRIMARY KEY, embedding sparsevec(5));
```
Insert vectors
```sql
INSERT INTO items (embedding) VALUES ('{0:1,1:2,2:3}/10'), ('{0:4,1:5,2:6}/10');
INSERT INTO items (embedding) VALUES ('{1:1,3:2,5:3}/5'), ('{1:4,3:5,5:6}/5');
```
Note: Indices start at 1 like SQL arrays
Get the nearest neighbors by L2 distance
```sql
SELECT * FROM items ORDER BY embedding <-> '{0:3,1:1,2:2}/10' LIMIT 5;
SELECT * FROM items ORDER BY embedding <-> '{1:3,3:1,5:2}/5' LIMIT 5;
```
## Hybrid Search