mirror of
https://github.com/elastic/elasticsearch.git
synced 2025-04-25 15:47:23 -04:00
f00364aefd
Adds new `quantization_options` to `dense_vector`. This allows for
vectors to be automatically quantized to `byte` when indexed.
Example:
```
PUT vectors
{
"mappings": {
"properties": {
"my_vector": {
"type": "dense_vector",
"index": true,
"index_options": {
"type": "int8_hnsw"
}
}
}
}
}
```
When querying, the query vector is automatically quantized and used when
querying the HNSW graph. This reduces the memory required to only `25%`
of what was previously required for `float` vectors at a slight loss of
accuracy.
This is currently only available when `index: true` and when using
`hnsw`
|
||
|---|---|---|
| .. | ||
| recipes | ||
| disk-usage.asciidoc | ||
| fix-common-cluster-issues.asciidoc | ||
| general.asciidoc | ||
| indexing-speed.asciidoc | ||
| knn-search.asciidoc | ||
| recipes.asciidoc | ||
| search-speed.asciidoc | ||
| size-your-shards.asciidoc | ||
| use-elasticsearch-for-time-series-data.asciidoc | ||