Comfy-UI-inspired RAG Modules for implementing custom LLM applications

Try it in the demo site.

The demo includes some examples of graphs.

You need git, node and npm. Given those dependencies are installed, run the following commands to try it out:

$ git clone https://github.com/jagenjo/litegraph.js.git
$ cd litegraph.js
$ npm install
$ node utils/server.js
>>
Example app listening on https://127.0.0.1:8000

Open your browser and point it to https://127.0.0.1:8000. You can select a demo from the dropdown at the top of the page.

• Modular Rag and Rag Flow, Part I

• Modular Rag and Rag Flow, Part II

• AutoRAG, for finding the optimal RAG pipeline for your data

• Litegraph, a graph node engine and editor written in Javascript similar to PD or UDK Blueprints, comes with its own editor in HTML5 Canvas2D. The engine can run client side or server side using Node. It allows to export graphs as JSONs to be included in applications independently. Famously in ComfyUI.

• Ragas, an evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

• Best-README-Template, for READMEs like this one