Skip to content

Conversation

maxjiang153
Copy link
Contributor

Add ElasticsearchVectorStore support for creating index configuration. such as dims, denseVectorIndexing and similarity.

Also, include support for adding documents to ES with a failed response; this change will result in an exception.

@tzolov tzolov self-assigned this Apr 26, 2024
@tzolov tzolov added enhancement New feature or request vector store labels Apr 26, 2024
@tzolov tzolov added this to the 1.0.0-M1 milestone Apr 30, 2024
@tzolov
Copy link
Contributor

tzolov commented Apr 30, 2024

Thanks @wmz7year ,
We're still considering adding the concept of runtime options to the VectorStores (similar to the model clients). Anyway this PR is a step in this direction if we get there eventually.

@

@tzolov
Copy link
Contributor

tzolov commented Apr 30, 2024

Rebased, squashed and merged at f90c51a

Additionally rename the dims property into dimension.
Add javadoc and antora ES properties documentation.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request vector store

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants