On: Vector databases: analyzing the trade-offs

[mark_l_watson]

For use with LLMs, I implemented my own vector DB code in Common Lisp and Swift.

When I work in Python, my favorite is absolutely Chroma embedded.

The article is wrong about Chroma embedded being in memory only. It also works fine with write through to a local disk, including maintaining index files.

[fzliu → mark_l_watson]

Shameless self-plug for our embedded vector database milvus-lite (https://github.com/milvus-io/milvus-lite):

    pip install milvus

[mark_l_watson → fzliu]

Thank you, I will try it. I noticed that you put the entire implementation inside the package’s __init__.py file. Interesting, and I had not seen that done before.

[horstmeyer → mark_l_watson]

I have seen that pattern before, and for me it's a bit of an antipattern. Usually you wouldn't look for substantial code there, and in most cases it is nicer to organize your code in modules. You can import from those in the __init.py__ file, this way achieving the same effect as having all code live in __init.py__. But it's a matter of preference.

[dmezzetti → mark_l_watson]

Another one mentioned below to try is txtai: https://github.com/neuml/txtai

It can run embedded in a single Python instance and has no issues running in production that way.