msoedov/vector_lake

S3 vector database for LLM Agents and RAG.

52
/ 100
Established

VectorLake is designed for machine learning engineers and data scientists who need to store and query high-dimensional data efficiently and cost-effectively. It helps manage the large sets of numerical 'embeddings' that come out of machine learning models. You can feed it these embeddings, and it allows you to quickly find similar data points, especially useful for applications like powering AI assistants or recommendation systems.

Available on PyPI.

Use this if you need a low-maintenance, scalable, and cost-effective way to store and query vast amounts of numerical embedding data for your machine learning applications, particularly when using S3 storage.

Not ideal if you're looking for a full-featured transactional database or if your primary need isn't handling large-scale vector similarity search.

machine-learning-engineering data-science vector-search retrieval-augmented-generation big-data-storage
Maintenance 10 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 9 / 25

How are scores calculated?

Stars

57

Forks

4

Language

Python

License

MIT

Last pushed

Jan 28, 2026

Commits (30d)

0

Dependencies

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/msoedov/vector_lake"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.