Scale agent retrieval workloads with Milvus
Use Milvus to create vector collections, ingest embeddings, and serve filtered similarity search for RAG and agent retrieval workloads.
npx skills add agentskillexchange/skills --skill scale-agent-retrieval-workloads-with-milvus
Milvus is a cloud-native vector database for scalable approximate nearest-neighbor search. This skill is for operators who need a repeatable retrieval workflow: deploy Milvus, create vector collections, ingest embeddings, tune indexes, and expose filtered similarity search to a RAG or agent application. Invoke it when an agent needs production-grade retrieval infrastructure instead of a simple local vector store. The boundary is the retrieval operations workflow for agent systems, not a generic database listing.
What this skill actually does
Inputs and prerequisites: Milvus, embedding model, agent or RAG application.
Setup notes: Follow the Milvus deployment documentation, create collections and indexes for embeddings, ingest vectors, then connect the retrieval endpoint to the agent or RAG workflow.
Source and verification boundary: use https://github.com/milvus-io/milvus as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.