Skip to content

Introduce Oracle Database embedding store extension - #2494

Merged
geoand merged 1 commit into
quarkiverse:mainfrom
omatheusmesmo:feat/oracle-embedding-store
May 25, 2026
Merged

geoand merged 1 commit into
quarkiverse:mainfrom
omatheusmesmo:feat/oracle-embedding-store

Conversation

@omatheusmesmo

Copy link
Copy Markdown
Collaborator

Describe your changes

Adds a new quarkus-langchain4j-oracle extension that uses Oracle Database 23ai AI Vector Search as an embedding store, backed by the langchain4j-oracle library.

It follows the conventions established by the existing stores (closest to pgvector):

  • QuarkusOracleEmbeddingStore is a non-final wrapper that delegates to langchain4j's final OracleEmbeddingStore, so the bean can be proxied by ArC.
  • Configuration is split into build-time (default-store-enabled, per-store datasource) and runtime (table, columns, exact-search, IVF vector-index.*, and JSON metadata-indexes).
  • Named stores are supported via the @EmbeddingStoreName qualifier, each able to target a different Agroal datasource.
  • Dev Services starts an Oracle Free 23ai container (gvenzl/oracle-free:23-slim) automatically; the image is overridable.

Unlike pgvector, there is no dimension property: Oracle stores embeddings in a native VECTOR(*, FLOAT32) column and infers the dimension at insert time. The vector index and metadata indexes are created independently, so metadata filtering can be accelerated without an IVF index on small tables that rely on exact search.

Configuration

Default store:

quarkus.langchain4j.oracle.table=embeddings
quarkus.langchain4j.oracle.create-option=CREATE_IF_NOT_EXISTS

Named store backed by a separate datasource:

quarkus.langchain4j.oracle.products.datasource=products-ds
quarkus.langchain4j.oracle.products.table=product_embeddings

Injection

@Inject
EmbeddingStore<TextSegment> defaultStore;

@Inject
@EmbeddingStoreName("products")
EmbeddingStore<TextSegment> productsStore;

@omatheusmesmo
omatheusmesmo requested a review from a team as a code owner May 24, 2026 23:46
@quarkus-bot

This comment has been minimized.

Use Oracle Database 23ai AI Vector Search as an embedding store, backed
by langchain4j-oracle. Follows the pgvector conventions: a non-final
wrapper bean, build-time/runtime config split, named stores via
@EmbeddingStoreName, Agroal datasource, and Dev Services.

* Fix quarkiverse#2492

Signed-off-by: Matheus Oliveira <[email protected]>
@omatheusmesmo
omatheusmesmo force-pushed the feat/oracle-embedding-store branch from db6d678 to 0e6719b Compare May 25, 2026 00:16
@quarkus-bot

quarkus-bot Bot commented May 25, 2026

Copy link
Copy Markdown

Status for workflow Build (on pull request)

This is the status report for running Build (on pull request) on commit 0e6719b.

✅ The latest workflow run for the pull request has completed successfully.

It should be safe to merge provided you have a look at the other checks in the summary.

@geoand

geoand commented May 25, 2026 •

Copy link
Copy Markdown
Collaborator

Thanks!

Dev Services starts an Oracle Free 23ai container (gvenzl/oracle-free:23-slim) automatically; the image is overridable.

Is this an official image?

Also cc @jmartisk

@jmartisk

jmartisk commented May 25, 2026 •

Copy link
Copy Markdown
Collaborator

Thanks!

Dev Services starts an Oracle Free 23ai container (gvenzl/oracle-free:23-slim) automatically; the image is overridable.

Is this an official image?

Also cc @jmartisk

It is used by Quarkus core and also Spring Data and others (see https://hub.docker.com/r/gvenzl/oracle-free#users-of-these-images) so I guess it should be fine

@jmartisk jmartisk left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@geoand

geoand commented May 25, 2026

Copy link
Copy Markdown
Collaborator

Thanks for having a look!

@geoand
geoand merged commit 6aebcb4 into quarkiverse:main May 25, 2026
92 checks passed
@omatheusmesmo

Copy link
Copy Markdown
Collaborator Author

Thanks everyone!

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add Oracle Database embedding store support

3 participants