Skip to content

Commit e1dda62

Browse files
kosabogibenironsidejohn-wagsterleemthompo
authored
Adds a small section and navigation link to BBQ documentation on the 'Dense vector' page (#2575)
⚠️ DO NOT MERGE BEFORE elastic/elasticsearch#133066 ### 📸 [Preview](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/2575/solutions/search/vector/dense-vector#bbq) [This PR](elastic/elasticsearch#133066) introduces a new section on Better Binary Quantization (BBQ) in the Reference documentation. In this PR, I've added a link to that newly added page. Related issue: elastic/developer-docs-team#333 --------- Co-authored-by: Benjamin Ironside Goldstein <[email protected]> Co-authored-by: John Wagster <[email protected]> Co-authored-by: Liam Thompson <[email protected]>
1 parent 2592ff3 commit e1dda62

File tree

1 file changed

+8
-2
lines changed

1 file changed

+8
-2
lines changed

solutions/search/vector/dense-vector.md

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ Dense neural embeddings capture semantic meaning by translating content into fix
1212
- Image similarity search
1313
- Content-based recommendations
1414

15-
## Working with dense vectors in Elasticsearch
15+
## Working with dense vectors in {{es}}
1616

1717
:::{tip}
1818
Using the `semantic_text` field type provides automatic model management and sensible defaults. [Learn more](../semantic-search/semantic-search-semantic-text.md).
@@ -25,4 +25,10 @@ Dense vector search requires both index configuration and a strategy for generat
2525
- Refer to [this overview](../semantic-search.md#using-nlp-models) of the main options
2626
- You can also [bring your own embeddings](bring-own-vectors.md)
2727
- Use the `dense_vector` field type
28-
2. Query the index using the [`knn` search](knn.md)
28+
2. Query the index using the [`knn` search](knn.md)
29+
30+
## Better Binary Quantization (BBQ) [bbq]
31+
32+
Better Binary Quantization (BBQ) is a vector quantization method for `dense_vector` fields that compresses vectors for faster and more memory-efficient similarity search. BBQ can improve relevance and cost efficiency, especially when used with HNSW.
33+
34+
For details on how BBQ works, supported algorithms, and configuration examples, refer to [Better Binary Quantization (BBQ)](https://www.elastic.co/docs/reference/elasticsearch/index-settings/bbq)

0 commit comments

Comments
 (0)