Chunksize - a simple approach to splitting #16
Conversation
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
This prints any output as chunks of the given size. It is useful for running something like this: ttok -m model -i infile --encode --chunksize | split 'outfile.' and then decoding the outfiles in order to accommodate embedding model token limits.
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Outdated suggestions cannot be applied.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.
This change implements a simple alternative to https://github.com/simonw/ttok/pull/2/files. It does not deal with output files, and instead simply prints each chunk sequentially by the existing output mechanism.
When producing text output this is uninteresting. With
--tokensit gives readable split output. Combined with--encodeit produces one encoded chunk per line, output that can be piped tosplit -l 1 prefix, which can be decoded later. This makes it straightforward to split long text into chunks for embedding or other purposes.