LLMLingua is a web application that allows users to paste instructions, context, and questions, then compresses them into shorter prompts for large language models. Users can set a target token count or compression ratio, making it easier to fit within LLM input limits. Designed for AI researchers and developers optimizing prompt engineering.
LLMLingua is an Other AI project. It reduces the length of prompts for large language models to fit token limits and optimize input. LLMLingua is a B2B product aimed at AI researchers and developers. It is available for free. It ships for the web, and it can be self-hosted.
Behind LLMLingua is Microsoft, and it first shipped in 2023. Among its 5 catalogued features are prompt compression, token count setting, and compression ratio setting.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do