Re:Vector databases: analyzing the trade-offs
by fzliu on Sunday August 20, 2023 @06:43PM
(#37203636)
Shameless self-plug for our embedded vector database milvus-lite (https://github.com/milvus-io/milvus-lite):
pip install milvus
Re:Vector databases: analyzing the trade-offs
by mark_l_watson on Sunday August 20, 2023 @07:15PM
(#37203856)
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.
Re:Vector databases: analyzing the trade-offs
by horstmeyer on Sunday August 20, 2023 @11:20PM
(#37205103)
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.
Re:Vector databases: analyzing the trade-offs
by dmezzetti on Sunday August 20, 2023 @07:22PM
(#37203895)
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.
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.