Merge pull request #670 from jmazanec15/issue-669

Change nlists to nlist for k-NN IVF algorithm
This commit is contained in:
Naarcha-AWS 2022-06-14 13:10:30 -05:00 committed by GitHub
commit b8f10754d1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 3 deletions

View File

@ -331,7 +331,7 @@ POST /_plugins/_knn/models/{model_id}/_train?preference={node_id}
"engine":"faiss",
"space_type": "l2",
"parameters":{
"nlists":128,
"nlist":128,
"encoder":{
"name":"pq",
"parameters":{
@ -361,7 +361,7 @@ POST /_plugins/_knn/models/_train?preference={node_id}
"engine":"faiss",
"space_type": "l2",
"parameters":{
"nlists":128,
"nlist":128,
"encoder":{
"name":"pq",
"parameters":{

View File

@ -99,7 +99,7 @@ Paramater Name | Required | Default | Updatable | Description
Paramater Name | Required | Default | Updatable | Description
:--- | :--- | :--- | :--- | :---
`nlists` | false | 4 | false | Number of buckets to partition vectors into. Higher values may lead to more accurate searches, at the expense of memory and training latency. For more information about choosing the right value, refer to [*faiss*'s documentation](https://github.com/facebookresearch/faiss/wiki/Guidelines-to-choose-an-index).
`nlist` | false | 4 | false | Number of buckets to partition vectors into. Higher values may lead to more accurate searches, at the expense of memory and training latency. For more information about choosing the right value, refer to [Guidelines to choose an index](https://github.com/facebookresearch/faiss/wiki/Guidelines-to-choose-an-index).
`nprobes` | false | 1 | false | Number of buckets to search over during query. Higher values lead to more accurate but slower searches.
`encoder` | false | flat | false | Encoder definition for encoding vectors. Encoders can reduce the memory footprint of your index, at the expense of search accuracy.