docs: document LLMLingua sidecar setup, ship sidecar/ in npm package#8
Open
jajanet wants to merge 1 commit intosliday:mainfrom
Open
docs: document LLMLingua sidecar setup, ship sidecar/ in npm package#8jajanet wants to merge 1 commit intosliday:mainfrom
jajanet wants to merge 1 commit intosliday:mainfrom
Conversation
The llmlingua stage is enabled by default but silently no-ops without the Python sidecar. This adds setup instructions and ships sidecar/ in the npm package so npm installs have the files needed. Also documents TAMP_LLMLINGUA_URL env var to work around the startup race condition when the sidecar is still loading the model.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The llmlingua stage is enabled by default, but silently no-ops without the Python sidecar.
I had to do some debug steps too figure why this is the case, and I'd imagine other people would be interested in having this setup and working out of the box. LLMLingua has 20x token compression with minimal performance loss is pretty big (Jiang et al). I use a Mac though, not sure if the issue is specific to me
This adds setup instructions and ships
sidecar/in the npm package, so npm installs have the files needed. Also documentsTAMP_LLMLINGUA_URLenv var to work around the startup race condition when the sidecar is still loading the model.