liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-01 02:02:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated binary vectors section [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2024-04-03 23:36:43 -07:00
parent 61e803a4dc
commit 7e5df3c9fe
1 changed files with 7 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
README.md
View File

@@ -421,9 +421,7 @@ CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(cate
## Binary Vectors
*Unreleased*
Use the `bit` type to store binary vectors
Use the `bit` type to store binary vectors ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/hash_image_search.py))
```sql
CREATE TABLE items (id bigserial PRIMARY KEY, embedding bit(3));
@@ -432,6 +430,12 @@ INSERT INTO items (embedding) VALUES ('000'), ('111');
Get the nearest neighbors by Hamming distance
```sql
SELECT * FROM items ORDER BY bit_count(embedding # '101') LIMIT 5;
```
Or (unreleased)
```sql
SELECT * FROM items ORDER BY embedding <~> '101' LIMIT 5;
```
@@ -678,18 +682,6 @@ and query with:
SELECT * FROM items ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
```
#### Are binary vectors supported?
You can store binary vectors and perform exact nearest neighbor search by Hamming distance in Postgres without an extension ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/hash_image_search.py)).
```tsql
CREATE TABLE items (id bigserial PRIMARY KEY, embedding bit(3));
INSERT INTO items (embedding) VALUES ('000'), ('111');
SELECT * FROM items ORDER BY bit_count(embedding # '101') LIMIT 5;
```
Indexing is not currently supported.
#### Do indexes need to fit into memory?
No, but like other index types, you’ll likely see better performance if they do. You can get the size of an index with: