Show HN: Reducing LLM input tokens by 70%

Category: devtools

Tags: prompt-compression, llm, api

Score: 5.3/10 (Innovation: 5, Technical: 5, Documentation: 3, Utility: 6)

Adola provides a prompt compression API that reduces LLM input token counts while preserving essential context for query responses. It offers a simple client library for developers to integrate compression into their retrieval-augmented generation pipelines, potentially lowering costs and latency.

Target audience: backend devs, data engineers

Repository: https://adola.app/

View on Hacker News