milvus-lite

What it is and what it does

Milvus Lite is a pure-Python vector database designed for local development, prototyping, and small-scale AI applications. It stores data in a local `.db` file or runs as an embedded gRPC server, exposing the same pymilvus API as the full Milvus system. This means code written against Milvus Lite can move to Milvus Standalone, Milvus Distributed, or Zilliz Cloud with minimal changes.

The engine implements an LSM-style storage backend with write-ahead logging, in-memory memtables, and immutable Parquet segments. It supports dense vector search via FAISS indexes, sparse BM25 full-text search, hybrid search combining multiple retrieval routes, scalar and geometry filtering, dynamic and JSON fields, partitions, and aliases. All code is inspectable Python with native stack traces, making debugging and understanding behavior straightforward during development.

Use it for:

• Prototyping vector search applications locally before deploying to a production Milvus cluster
• Running integration tests and CI/CD pipelines that need a real vector database without external dependencies
• Embedding and searching documents or vectors in Jupyter notebooks and data science workflows
• Building hybrid search systems combining dense vector retrieval with BM25 full-text search on a single machine
• Developing and testing multi-client applications using the standalone gRPC server mode

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Milvus Lite is a pure-Python local vector database that provides dense and sparse vector search, BM25 full-text search, and scalar filtering through a Milvus-compatible API, storing data in a local `.db` file or embedded gRPC server.

Yes. Milvus Lite is worth installing for local development and testing workflows. It has low install friction, active maintenance, no known vulnerabilities, a permissive license, and solves a real problem—providing a Milvus-compatible vector database that runs without external infrastructure. The pure-Python implementation and recent release (8 days old) suggest solid current support. Reserve it for development and small-scale use; the documentation explicitly directs large-scale production workloads to Milvus Standalone, Milvus Distributed, or Zilliz Cloud.

Install

milvus-lite on PyPI

pip install milvus-lite

uv add milvus-lite

poetry add milvus-lite

Installing milvus-lite

Before you install

Low install friction; pure Python wheel with five runtime dependencies (faiss-cpu, grpcio, numpy, pyarrow, tomli). Active maintenance with release 8 days old. Requires Python 3.10 or newer; wheel availability for faiss-cpu and pyarrow on Windows may vary.

License in practice

Apache-2.0 permissive license allows commercial and private use with attribution; no copyleft obligations or restrictions on derivative works.

Quickstart

pip install -U milvus-lite

from milvus_lite import MilvusLite, CollectionSchema, FieldSchema, DataType

schema = CollectionSchema(fields=[
    FieldSchema(name="id", dtype=DataType.INT64, is_primary=True),
    FieldSchema(name="vec", dtype=DataType.FLOAT_VECTOR, dim=4),
])

with MilvusLite("./data") as db:
    col = db.create_collection("docs", schema)
    col.insert([{"id": 1, "vec": [0.1, 0.2, 0.3, 0.4]}])
    results = col.search([[0.1, 0.2, 0.3, 0.4]], top_k=2)

Requires Python 3.10 or newer. On Windows, installation depends on compatible wheels for faiss-cpu and pyarrow being available for your Python version.

Verify before relying

• Performance characteristics (latency, throughput) for typical workload sizes relative to Milvus Standalone or Zilliz Cloud
• Data volume limits or practical scaling boundaries for local `.db` files
• Migration path or tooling for moving from original C++/CGo milvus-lite to this pure-Python engine beyond re-importing data

Package facts

Evidence: milvus_lite-3.2.0-py3-none-any.whl

Keywords: bm25, database, embedding, milvus, search, vector

Tags

More Artificial Intelligence packages