Repolode
Submit
EmbeddedLLM

EmbeddedLLM/JamAIBase

Open-source RAG backend platform with a spreadsheet-like UI, combining SQLite, LanceDB, and managed LLM orchestration behind a REST API.

Open-source alternative to:Airtable

View on GitHubWebsite
Stars
1,104
Forks
48
Open issues
2
Last commit
16 days ago

What is it?

JamAI Base is a backend platform for building retrieval-augmented generation (RAG) applications. It pairs an embedded SQLite database with an embedded LanceDB vector database, and manages LLM calls, vector embeddings, and rerankers as part of the data layer.

Data is organized into several table types: Generative Tables that fill columns with LLM output, Action Tables that handle real-time user inputs and outputs, Knowledge Tables that hold structured data and uploaded documents, and Chat Tables for chatbot conversations that can draw on Knowledge Tables. Users define columns and their relationships through natural language prompts in a spreadsheet-style interface, and the same tables are reachable through a REST API.

The project supports self-hosting as well as a cloud-hosted option. It states support for LLMs such as OpenAI GPT-4, Anthropic Claude 3, and Meta Llama 3, along with hybrid search, query rewriting, and adaptive chunking for RAG pipelines.

Key features

  • 01Generative tables that auto-populate columns with LLM-generated content
  • 02Knowledge tables for managing structured data and uploaded documents
  • 03Chat tables for building chatbots that use RAG over knowledge tables
  • 04Hybrid search and reranking across keyword, structured, and vector retrieval
  • 05Built-in REST API for integrating tables into applications

Use cases

  • Building a chatbot that answers questions from your own documents
  • Generating structured data columns with LLM-based enrichment
  • Creating an AI-backed frontend interaction layer without managing backend plumbing
  • Prototyping RAG pipelines through a spreadsheet interface

Quick start

  1. 1

    Sign up for a free account on the JamAI Base Cloud

  2. 2

    Follow the self-hosted launch guide in the documentation

Things to know

  • Self-hosting requires following an external guide rather than a single documented command.
  • Some features depend on LLM provider access, so you may need your own API keys.

In collections

Open-source AI agent frameworks & appsAI chatbots & chat clients

Topics

#rag#llm#vector-database#backend-as-a-service#spreadsheet#chatbot#ai-agents#workflow-orchestration#agents#ai

FAQ

What is JamAIBase?
Open-source RAG backend platform with a spreadsheet-like UI, combining SQLite, LanceDB, and managed LLM orchestration behind a REST API. JamAI Base is a backend platform for building retrieval-augmented generation (RAG) applications. It pairs an embedded SQLite database with an embedded LanceDB vector database, and manages LLM calls, vector embeddings, and rerankers as part of the data layer.
Is JamAIBase free to use? What license does it have?
JamAIBase is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is JamAIBase still maintained?
Actively maintained. The last commit to JamAIBase was on Oct 22, 2026.
What can I use JamAIBase for?
Building a chatbot that answers questions from your own documents Generating structured data columns with LLM-based enrichment Creating an AI-backed frontend interaction layer without managing backend plumbing Prototyping RAG pipelines through a spreadsheet interface
How do I install JamAIBase?
Sign up for a free account on the JamAI Base Cloud Follow the self-hosted launch guide in the documentation
Where can I get JamAIBase?
The source code and installation instructions are on GitHub: https://github.com/EmbeddedLLM/JamAIBase

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects