JamAI Base
JamAI Base is an open-source retrieval-augmented-generation backend that pairs an embedded SQLite database with an embedded LanceDB vector store behind a spreadsheet-like UI and a REST API, so LLM calls, embeddings and reranking can be wired together as table columns.
JamAI Base is an open-source RAG backend platform built around an embedded SQLite database and an embedded LanceDB vector database, with built-in orchestration for LLM calls, vector embeddings and reranking. It is used through a spreadsheet-like interface or a REST API.
Generative Tables populate columns automatically with LLM-generated data and expose the result through a REST endpoint; Action Tables connect a frontend to an LLM backend for real-time interaction and multi-step workflow orchestration; Knowledge Tables hold structured data and documents that give other tables contextual grounding; and Chat Tables handle the state needed to build a chatbot. LanceDB integration is used to store and query large-scale multimodal embeddings.