Quira
- 1 Devlogs
- 0 Total hours
Quira is a next-gen Python RAG framework featuring speculative vector search, Context Tetris for token compression, and differential caching to eliminate redundant API costs.
Quira is a next-gen Python RAG framework featuring speculative vector search, Context Tetris for token compression, and differential caching to eliminate redundant API costs.
I am working on Quira.
Quira is a next-gen Python RAG framework..
I implemented many features that cut costs of RAG retrieval and generation by a 25-30%…. It also gives the results very fast with much lower latency…..
I am still trying to improve it as much as I can based on feedbacks and personal testing…