Milvus

Component Category

Vector database

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

It provides the vector storage and similarity search capabilities needed for retrieval-augmented generation and other embedding-based experiences. This makes it a strong fit for semantic search, knowledge retrieval, and other AI patterns that depend on fast nearest-neighbor queries over embedding data.

Learn More

• Milvus Documentation
• Milvus on GitHub

Interacts With

• CoreAI API for vector queries and retrieval logic
• Docling and related processing flows whose outputs feed vector workflows
• LiteLLM or embedding-producing model flows upstream of storage
• MinIO as part of the surrounding storage setup used by the deployed service
• CoreAI Web Portal where vector store capabilities may be configured or consumed