Larkup-RAG creates an open-source RAG server in minutes
Larkup-RAG is an toolkit for turning documents into a working RAG server. It is meant to reduce repeated setup work such as chunking documents, creating embeddings, connecting a , deploying the app, and running an .
Data can come from files, URLs, or , and the toolkit automatically chunks and indexes the content. Users can choose the and , including for privacy or services such as OpenAI, Pinecone, Qdrant, and LanceDB.
The finished server can be called through an SDK or connected directly to LangChain and AI SDK agents. It also includes a demo UI for testing retrieval before deployment, with deployment options such as Vercel, Azure, and Hetzner.
Key points
- Larkup-RAG is an toolkit for creating a RAG .
- It loads data from files, URLs, or .
- It automatically chunks and indexes the content.
- It supports as well as OpenAI, Pinecone, Qdrant, and LanceDB.
- It can connect to LangChain and AI SDK agents.