How to use Milvus: what you can do with it

3 use cases

• Start a vector database in a single local file

  Install pymilvus with Milvus Lite and create a collection in a local file, no server needed.

  • REPO milvus-io/milvus
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Beginner
  View prompt

  Using milvus-io/milvus with Milvus Lite, create milvus_demo.db, embed <documents> with <model>, create a collection with the right dimension, insert them, and search for <query>. Show me the top 3 results with their text.

  Share Email me this

• Build a RAG pipeline on Milvus

  Store document chunks in Milvus and retrieve them for an LLM, following the Build RAG tutorial.

  • REPO milvus-io/milvus
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Intermediate
  View prompt

  Build a RAG pipeline for <documents> on milvus-io/milvus following the Build RAG with Milvus tutorial: chunk, embed with <model>, insert, retrieve top 3 with client.search and answer with <LLM>. Test it on <questions>.

  Share Email me this

• Add full text and hybrid search to vector search

  Use BM25 full text search and sparse vectors alongside dense vectors for better recall.

  • REPO milvus-io/milvus
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Advanced
  View prompt

  On my milvus-io/milvus server, add BM25 full text search and hybrid search for collection <name> following the README's tutorials. Compare hybrid and dense-only results on <queries> and recommend which to ship.

  Share Email me this

Quick start with Milvus

1. Check you have what it needs: Python and the pymilvus SDK; Milvus Lite for a local file, or a deployed Milvus server or Zilliz Cloud with credentials; An embedding model to create vectors.
2. Open milvus-io/milvus on GitHub and read the README and license.
3. Install the SDK with pip install -U pymilvus, and pymilvus[milvus-lite] for Milvus Lite
4. Create a local database with MilvusClient("milvus_demo.db")
5. Create a collection with client.create_collection using your embedding dimension, for example 768
6. Insert your embedded data with client.insert

These steps come from our top use case, Start a vector database in a single local file, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for milvus-io/milvus

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Software and DevOps

About this repo

• Who it is forDevelopers building RAG, semantic search or recommendation systems who want a vector database that starts small and scales out.
• Why it is hot47k stars, talked about in 2 AI sources we track
• LanguageGo
• Sourcegithub.com/milvus-io/milvus · Back to Hot repos

Requirements

• Python and the pymilvus SDK
• Milvus Lite for a local file, or a deployed Milvus server or Zilliz Cloud with credentials
• An embedding model to create vectors

Related repos

• Trended earlier REPO qdrant/qdrant Qdrant Qdrant is a vector similarity search engine and vector database written in Rust. It stores points, which are vectors with a JSON payload, and offers dense, sparse and multivector search, rich payload filtering, hybrid search with fusion, quantization that cuts RAM use by up to 97%, distributed deployment, a Web UI, REST and gRPC APIs, official clients in several languages and Qdrant Edge for small devices.
• Trended earlier REPO masumedb/masume Masume A keyboard-first terminal database client written in Go, with AI chat, notebooks, headless commands, and an MCP server for external agents.
• Trended earlier REPO Yamz-Labs/kyojin Kyojin Kyojin is an open source inference engine, built on ExLlamaV3, that runs large GLM, Qwen and MiMo models on one AMD Strix Halo mini PC with 128 GB of memory.