Skip to main content

LarkupRAG Logo

Larkup-RAG is an open-source toolkit that takes you from zero to a running Retrieval-Augmented Generation (RAG) server in minutes. It eliminates the complexities of manual infrastructure setup, allowing you to easily configure vector stores, chunking strategies, and embedding models through a simple interface, and immediately connect your AI agents.

​
Who is Larkup-RAG for?

For Developers & Technical Teams
  • Launch a Full RAG Server: Stop worrying about infrastructure. Go from documents to a deployed RAG API in minutes.
  • Connect with SDKs: Integrate powerful search into your applications using our native SDKs.
  • Agent Integrations: Seamlessly connect your RAG pipeline to autonomous agents using AI-SDK or LangChain.
  • Bring Your Own Vector Store: Use local models for privacy, or connect to OpenAI, LanceDB, Pinecone, Qdrant, and more.
For Non-Technical Users & Business Teams
  • Instant Chatbot: Build a chatbot trained on your own data with zero coding required.
  • Embed Anywhere: Just provide an API key, instantly chat with your data, and embed the widget on your site.
  • User-Friendly Interface: Manage your data sources, vector stores, and chunking strategies all through an intuitive web UI.

​
How it Works

Larkup-RAG simplifies the process into 6 core steps:
1

Configure

Choose your embedding models and vector store.
2

Load Data

Ingest data easily from files, URLs, or web scraping.
3

Index

Automatically chunk and embed your loaded data.
4

Launch

Spin up your RAG server instantly.
5

Demo

Test your retrieval quality using the built-in demo UI.
6

Deploy

Deploy to your favorite cloud platforms (e.g., Vercel, Azure).
No coding required , use the Web UI. Prefer the terminal? See the CLI guide.

​
Get Started

Quick Start

Get a server running locally in under 5 minutes.

Instant Chatbot

Launch a chatbot connected to your docs with just an API key.

SDK Integration

Connect your RAG server to your apps using our SDK.

Agent Frameworks

Use AI-SDK or LangChain to connect RAG to your agents.