Please check the build logs for more information.
See Builds for ideas on how to fix a failed build, or Metadata for how to configure docs.rs builds.
If you believe this is docs.rs' fault, open an issue.
langsan is a sanitization library for language models
Out of a desire to be first to market, many companies from OpenAI to Anthropic are releasing language models without proper input or output sanitization. This can lead to a variety of safety and security issues, including but not limited to human-invisible adversarial attacks, data leakage, and generation of harmful content.
langsan provides immutable string wrappers guaranteeing their contents are within restricted unicode ranges, generally those only officially supported by a particular language model. All unicode code blocks are available as features. The library is designed to be fast and efficient, with minimal overhead.
Note:
The crates.io version of this crate does not have all of the features because crates.io is limited to 300, and there are more than 300 unicode blocks. If you need a specific block, you can use the git version of this crate by adding the following to your Cargo.toml:
[]
= { = "https://github.com/mdegans/langsan.git" }