JamAI Base is an open-source backend platform designed to simplify the development of retrieval-augmented generation systems and AI-driven applications. The platform integrates both a relational database and a vector database into a single embedded architecture, allowing developers to store structured data alongside semantic embeddings. It includes built-in orchestration for large language models, vector search, and reranking pipelines so that AI applications can retrieve relevant information before generating responses. JamAI Base exposes its functionality through a simple REST API and a spreadsheet-style interface that allows users to manage AI workflows visually. One of the key ideas behind the platform is the concept of generative tables, which allow database columns to automatically populate with AI-generated content. The system also supports action tables and chat tables that simplify the creation of interactive AI features such as conversational interfaces and dynamic workflows.
Features
- Integrated relational and vector database architecture using SQLite and LanceDB
- Built-in orchestration for LLM inference, embeddings, and reranking
- Spreadsheet-style interface for managing AI workflows and data
- Generative tables that automatically populate columns with LLM outputs
- REST API for integrating AI capabilities into external applications
- Chat and action tables for building conversational and interactive systems