anuran-roy/MemoRAG
a barebones implementation of an ExpressJS server with RAG pipeline without using LangChain or any other LLM Framework, with features for calling LLMs, data processing, etc built from scratch
This project provides a basic backend server for building Retrieval Augmented Generation (RAG) applications. It takes your data and a user's question, retrieves relevant information, and then uses a Large Language Model (LLM) to generate an informed answer. It's designed for developers who want to learn or implement RAG pipelines from the ground up without relying on external frameworks.
No commits in the last 6 months.
Use this if you are a backend developer looking to build or learn the fundamentals of RAG systems using Node.js and ExpressJS.
Not ideal if you need a plug-and-play RAG solution or prefer to use existing LLM frameworks like LangChain for rapid development.
Stars
7
Forks
—
Language
TypeScript
License
—
Category
Last pushed
Feb 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/anuran-roy/MemoRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
upstash/rag-chat
Prototype SDK for RAG development.
vercel-labs/ai-sdk-preview-rag
Retrieval-augmented generation (RAG) template powered by the AI SDK.
merefield/discourse-chatbot
An AI bot with RAG capability for Topics and Chat in Discourse, currently powered by OpenAI
ajac-zero/example-rag-app
Open-Source RAG app with LLM Observability (Langfuse), support for 100+ providers (LiteLLM),...
skaldlabs/skald
Context layer platform in your infrastructure