headroom
RAG / Q&Aheadroomlabs-ai/headroom
77.2K6.0KPythonApache-2.0
Automatically compress text before sending it to large models, saving a lot on token fees without changing answer quality.
🔍 RAG / Q&A🤖 Agent Frameworks
headroomlabs-ai/headroom
Automatically compress text before sending it to large models, saving a lot on token fees without changing answer quality.