milvus-lite
Lightweight version of Milvus for local development and testing
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or newer.
- On Windows, installation depends on compatible wheels for faiss-cpu and pyarrow being available for your Python version.
- Low install friction; pure Python wheel with five runtime dependencies (faiss-cpu, grpcio, numpy, pyarrow, tomli).
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with attribution; no copyleft obligations or restrictions on derivative works.
last release 2026-08-06 (8 days) · last repo commit 2026-08-11 · 457 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,753,632 downloads/mo, #3,589 on PyPI
Alternatives
Verify before relying
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)- 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
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 on it.
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
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.
Requires Python 3.10 or newer. On Windows, installation depends on compatible wheels for faiss-cpu and pyarrow being available for your Python version.
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)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
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagesfaiss-cpugrpcionumpypyarrowtomli |
| Maintenance | Actively maintained 8 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,753,632 / month, #3,589 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: DatabaseTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: milvus_lite-3.2.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “local vector database”
- milvus-liteMilvus Lite is a pure-Python local vector database that provides…
- qdrant-clientPython client library for Qdrant vector search engine, supporting…
- nano-vectordbA lightweight vector database that stores and queries embeddings with…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also langchain-milvus · pymilvus.model · llama-index-vector-stores-milvus · pyobvector · upstash-vector · opentelemetry-instrumentation-milvus · llama-index-vector-stores-postgres · bm25s · redisvl · chromadb