Re:Measuring the popularity of different vector databases
by metadat on Tuesday September 20, 2022 @05:46PM
(#32918221)
Is there documentation for how to build / train the txtai models from scratch? I looked but didn't yet find it.
p.s. it might be self evident to some, but Python is missing from the list of supported languages:
API bindings for JavaScript,
Java, Rust and Go
Presumably Python has "native" support :)p.p.s this looks awesome, submitted: https://news.ycombinator.com/item?id=32918254
Re:Measuring the popularity of different vector databases
by txtai on Tuesday September 20, 2022 @05:53PM
(#32918312)
Thank you for the kinds words!
Best documentation on training models is the trainer pipeline - https://neuml.github.io/txtai/pipeline/train/trainer. There are a lot of great pretrained models available: https://huggingface.co/models?pipeline_tag=sentence-similari...
Funny on Python, never thought of how that section read, definitely a good clarification to make.
txtai can build vector indexes with Faiss/HNSW/Annoy and supports running SQL statements against them. External vector databases can also be plugged in.