feat: add token counting for LLM context estimation#1307
Open
camjac251 wants to merge 1 commit intoXAMPPRocky:masterfrom
Open
feat: add token counting for LLM context estimation#1307camjac251 wants to merge 1 commit intoXAMPPRocky:masterfrom
camjac251 wants to merge 1 commit intoXAMPPRocky:masterfrom
Conversation
Add optional token counting using tiktoken o200k_base encoding. Build with `--features tokens` to enable, then use `--tokens` flag or `show_tokens = true` in config to display the Tokens column. - New `tokens` feature flag (included in `all` features) - `--tokens` / `-T` flag to enable at runtime - `show_tokens` config option in tokei.toml - Tokens column shows LLM token count per file/language - `--sort tokens` / `--rsort tokens` support - Token counts in JSON/YAML output via serde
Author
|
@XAMPPRocky thoughts? |
|
@XAMPPRocky I was looking for alternatives to count tokens like this, do you think we can merge it? |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add optional token counting using tiktoken's
o200k_baseencoding for LLM context estimation.Builds upon #1268 by @Arichy, with runtime configuration and updated encoding.
Features:
tokensfeature flag (included inall)--tokens/-Tflag for runtime opt-inshow_tokensconfig option intokei.toml--sort tokens/--rsort tokenssupportUsage
cargo install tokei --features tokens tokei . --tokensOr via config (
~/.config/tokei.toml):Example
Test plan
cargo test --features tokenspassesRelated: #1268