community[patch]: Add vector index support to SingleStoreDB VectorStore (#17308)

This pull request introduces support for various Approximate Nearest
Neighbor (ANN) vector index algorithms in the VectorStore class,
starting from version 8.5 of SingleStore DB. Leveraging this enhancement
enables users to harness the power of vector indexing, significantly
boosting search speed, particularly when handling large sets of vectors.

---------

Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
volodymyr-memsql
2024-02-14 21:43:12 +02:00
committed by GitHub
parent 0bc4a9b3fc
commit e36bc379f2
3 changed files with 166 additions and 11 deletions

View File

@@ -106,6 +106,14 @@
"print(docs[0].page_content)"
]
},
{
"cell_type": "markdown",
"id": "035cba66",
"metadata": {},
"source": [
"Enhance your search efficiency with SingleStore DB version 8.5 or above by leveraging [ANN vector indexes](https://docs.singlestore.com/cloud/reference/sql-reference/vector-functions/vector-indexing/). By setting `use_vector_index=True` during vector store object creation, you can activate this feature. Additionally, if your vectors differ in dimensionality from the default OpenAI embedding size of 1536, ensure to specify the `vector_size` parameter accordingly. "
]
},
{
"cell_type": "code",
"execution_count": null,