liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-10 14:46:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added more scaling advice to readme [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2026-04-26 12:56:07 -07:00
parent a7551a61ca
commit 609d01f4c6
1 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
README.md
View File

@@ -11,6 +11,8 @@ Store your vectors with the rest of your data. Supports:
Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recovery, JOINs, and all of the other [great features](https://www.postgresql.org/about/) of Postgres Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recovery, JOINs, and all of the other [great features](https://www.postgresql.org/about/) of Postgres
Have a lot of vectors? Use [half-precision vectors](#half-precision-vectors) and [binary quantization](#binary-quantization) to scale
[![Build Status](https://github.com/pgvector/pgvector/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector/actions) [![Build Status](https://github.com/pgvector/pgvector/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector/actions)
## Installation ## Installation
@@ -314,6 +316,8 @@ For a large number of workers, you may need to increase `max_parallel_workers` (
The [index options](#index-options) also have a significant impact on build time (use the defaults unless seeing low recall) The [index options](#index-options) also have a significant impact on build time (use the defaults unless seeing low recall)
Use [binary quantization](#binary-quantization) for faster build times at scale
### Indexing Progress ### Indexing Progress
Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
@@ -673,6 +677,10 @@ SHOW shared_buffers;
Be sure to restart Postgres for changes to take effect. Be sure to restart Postgres for changes to take effect.
### Storing
Use the `halfvec` type instead of `vector` for a smaller working set.
### Loading ### Loading
Use `COPY` for bulk loading data ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/loading/example.py)). Use `COPY` for bulk loading data ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/loading/example.py)).
@@ -687,6 +695,8 @@ Add any indexes *after* loading the initial data for best performance.
See index build time for [HNSW](#index-build-time) and [IVFFlat](#index-build-time-1). See index build time for [HNSW](#index-build-time) and [IVFFlat](#index-build-time-1).
Use [binary quantization](#binary-quantization) for smaller indexes and faster build times at scale.
In production environments, create indexes concurrently to avoid blocking writes. In production environments, create indexes concurrently to avoid blocking writes.
```sql ```sql
@@ -717,6 +727,8 @@ SELECT * FROM items ORDER BY embedding <#> '[3,1,2]' LIMIT 5;
#### Approximate Search #### Approximate Search
Use [binary quantization](#binary-quantization) with re-ranking to keep indexes in-memory at scale.
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).
```sql ```sql
@@ -759,10 +771,13 @@ COMMIT;
## Scaling ## Scaling
Scale pgvector the same way you scale Postgres.
Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to [tune parameters](#tuning) and [monitor performance](#monitoring). Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to [tune parameters](#tuning) and [monitor performance](#monitoring).
For a smaller working set:
1. Use the `halfvec` type instead of `vector` for tables
2. Use [binary quantization](#binary-quantization) for indexes (with re-ranking for search)
Scale horizontally with [replicas](https://www.postgresql.org/docs/current/hot-standby.html), or use [Citus](https://github.com/citusdata/citus) or another approach for sharding ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/citus/example.py)). Scale horizontally with [replicas](https://www.postgresql.org/docs/current/hot-standby.html), or use [Citus](https://github.com/citusdata/citus) or another approach for sharding ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/citus/example.py)).
## Languages ## Languages
@@ -878,6 +893,8 @@ No, but like other index types, you’ll likely see better performance if they d
SELECT pg_size_pretty(pg_relation_size('index_name')); SELECT pg_size_pretty(pg_relation_size('index_name'));
``` ```
Use [half-precision indexing](#half-precision-indexing) or [binary quantization](#binary-quantization) for smaller indexes.
## Troubleshooting ## Troubleshooting
#### Why isn’t a query using an index? #### Why isn’t a query using an index?