liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-14 08:36:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improved performance section [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2024-03-15 17:54:14 -07:00
parent da0ff998e9
commit 4b2a7cc49d
1 changed files with 18 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@@ -410,13 +410,29 @@ You can use [Reciprocal Rank Fusion](https://github.com/pgvector/pgvector-python
## Performance ## Performance
### Loading
Use `COPY` for bulk loading data ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/bulk_loading.py)).
```sql
COPY items (embedding) FROM STDIN WITH (FORMAT BINARY);
```
Add any indexes *after* loading the data.
### Indexing
See index build time for [HNSW](#index-build-time) and [IVFFlat](#index-build-time-1).
### Querying
Use `EXPLAIN ANALYZE` to debug performance. Use `EXPLAIN ANALYZE` to debug performance.
```sql ```sql
EXPLAIN ANALYZE SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5; EXPLAIN ANALYZE SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5;
``` ```
### Exact Search #### Exact Search
To speed up queries without an index, increase `max_parallel_workers_per_gather`. To speed up queries without an index, increase `max_parallel_workers_per_gather`.
@@ -430,7 +446,7 @@ If vectors are normalized to length 1 (like [OpenAI embeddings](https://platform
SELECT * FROM items ORDER BY embedding <#> '[3,1,2]' LIMIT 5; SELECT * FROM items ORDER BY embedding <#> '[3,1,2]' LIMIT 5;
``` ```
### Approximate Search #### Approximate Search
To speed up queries with an IVFFlat index, increase the number of inverted lists (at the expense of recall). To speed up queries with an IVFFlat index, increase the number of inverted lists (at the expense of recall).