Feature Request: Add R2R for RAG as alternative to nlm_ingestor

[FellowTraveler]

R2R is working great here in docker, supports embeddings, graph-rag, HyDE, hybrid search, etc. It has a great API and seems like would be a quick way to add RAG as well as chatbot memory to Jar3d.

https://r2r-docs.sciphi.ai/api-reference/introduction

https://github.com/SciPhi-AI/R2R

[john-adeojo]

Thanks for sharing

[john-adeojo]

The most recent commit uses Docker to get up and running with Jar3d. The approach should cause less errors, please give it a try and let me know how it goes.

[FellowTraveler]

Will do.