News for hackers. Stuff that matters.
Re:Knowledge retrieval architectures for LLMs (2023) by foxgrover on Friday April 28, 2023 @08:10AM (#35740315)
Few other helpful options recently added to Langchain:

1. Extraction for query filters - https://twitter.com/hwchase17/status/1651617956881924096?s=4...

2. Contextual compression to eek more out of prompt stuffing - https://twitter.com/hwchase17/status/1649428295467905025?s=4...

And then it’s been there awhile but map-reduce, with Terran, etc are ways to apply LLM completions over large documents and/or large sets of documents: 3. https://m.youtube.com/watch?v=f9_BWhCI4Zo

There are no comments on this comment yet.