Rag Packages

Backend for your Personal Assistant, powered by Private AI (aka PAPA)

DataStax RAGStack TS

🚀 Accelerate LLM application development

Connect to the ITTIA APIs or self-hosted ones

A NodeJS RAG framework to easily work with LLMs and custom datasets

MCP server for Langflow RAG integration with Cursor

Quickest way to production grade RAG UI.

A NodeJS RAG framework to easily work with LLMs and custom datasets

The memory layer for Personalized AI in Typescript

An MCP Server for RAG Web Browser Actor

A Model Context Protocol server for fetching and storing documentation in a vector database, enabling semantic search and retrieval to augment LLM capabilities with relevant documentation context.

MCP server for integrating Tavily search API with LLMs, providing web search, RAG context generation, and QnA capabilities

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

The TypeScript Code Extractor and Analyzer can be handy for RAG (Retrieval-Augmented Generation) systems for codebases. It provides a detailed and structured representation of the codebase that can be converted into embeddings, enabling more effective adv

Client for the Vectorize API

A customizable React chat widget for RAG applications

A framework for connecting your data to large language models

CLI tool for syncing local files to Needle

CLI tool for syncing local files to Needle

An MCP server for semantic documentation search and retrieval using vector databases to augment LLM capabilities.