# Milvus (/docs/coreai/components/milvus)



Component Category [#component-category]

Vector database

Component Description [#component-description]

Milvus is the vector database used by CoreAI for storing embeddings and supporting semantic retrieval workflows. It is built for large-scale vector search and similarity matching across embedding-driven applications.

Why It Is Used [#why-it-is-used]

In BullSequana AI, Milvus provides the vector storage and similarity search capabilities needed for retrieval-augmented generation and other embedding-based experiences. It supports semantic search, knowledge retrieval, and other AI patterns that depend on fast nearest-neighbor queries over embedding data.

Learn More [#learn-more]

* [Milvus Documentation](https://milvus.io/docs)
* [Milvus on GitHub](https://github.com/milvus-io/milvus)

Interacts With [#interacts-with]

* `CoreAI API`, for vector queries and retrieval logic.
* `Kafka (Strimzi)`, which provides the message queue backend for Milvus (3 replicas).
* `OAuth2 Proxy`, which protects the Attu administration UI with Keycloak SSO.
* `Docling`, whose document processing outputs feed vector embedding workflows.
* `LiteLLM`, for embedding-producing model flows upstream of storage.
* `CoreAI Web Portal`, where vector store capabilities are configured and consumed.