liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-13 08:06:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Moved section [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2023-03-05 18:16:43 -08:00
parent 4d8eae1c3e
commit 6c1536ee78
1 changed files with 32 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
README.md
View File

@@ -187,38 +187,6 @@ Use `EXPLAIN ANALYZE` to debug performance
EXPLAIN ANALYZE SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 1; EXPLAIN ANALYZE SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 1;
``` ```
## Reference
### Vector Type
Each vector takes `4 * dimensions + 8` bytes of storage. Each element is a single precision floating-point number (like the `real` type in Postgres), and all elements must be finite (no `NaN`, `Infinity` or `-Infinity`). Vectors can have up to 16,000 dimensions.
### Vector Operators
Operator | Description
--- | ---
\+ | element-wise addition
\- | element-wise subtraction
<-> | Euclidean distance
<#> | negative inner product
<=> | cosine distance
### Vector Functions
Function | Description
--- | ---
cosine_distance(vector, vector) → double precision | cosine distance
inner_product(vector, vector) → double precision | inner product
l2_distance(vector, vector) → double precision | Euclidean distance
vector_dims(vector) → integer | number of dimensions
vector_norm(vector) → double precision | Euclidean norm
### Aggregate Functions
Function | Description
--- | ---
avg(vector) → vector | arithmetic mean
## Languages ## Languages
Use pgvector from any language with a Postgres client. Use pgvector from any language with a Postgres client.
@@ -258,6 +226,38 @@ Two things you can try are:
1. use dimensionality reduction 1. use dimensionality reduction
2. compile Postgres with a larger block size (`./configure --with-blocksize=32`) and edit the limit in `src/ivfflat.h` 2. compile Postgres with a larger block size (`./configure --with-blocksize=32`) and edit the limit in `src/ivfflat.h`
## Reference
### Vector Type
Each vector takes `4 * dimensions + 8` bytes of storage. Each element is a single precision floating-point number (like the `real` type in Postgres), and all elements must be finite (no `NaN`, `Infinity` or `-Infinity`). Vectors can have up to 16,000 dimensions.
### Vector Operators
Operator | Description
--- | ---
\+ | element-wise addition
\- | element-wise subtraction
<-> | Euclidean distance
<#> | negative inner product
<=> | cosine distance
### Vector Functions
Function | Description
--- | ---
cosine_distance(vector, vector) → double precision | cosine distance
inner_product(vector, vector) → double precision | inner product
l2_distance(vector, vector) → double precision | Euclidean distance
vector_dims(vector) → integer | number of dimensions
vector_norm(vector) → double precision | Euclidean norm
### Aggregate Functions
Function | Description
--- | ---
avg(vector) → vector | arithmetic mean
## Additional Installation Methods ## Additional Installation Methods
### Docker ### Docker