The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

Library to generate vector embeddings in NodeJS

A REST API and CLI tool for managing text embeddings and querying similarities, ideal for NLP and search applications.

markdown-it plugin for embedding github source links

A NodeJS RAG framework to easily work with LLMs and embeddings

A demo AI chatbot with Vercel AI SDK, Turso as vector DB and google gemini model.

This project is a photo gallery app 🎨 It leverages a CLIP model for powerful image search based on text keywords. You can easily filter through your images using AI-driven queries!

➖ Stripped down, stable version of firecrawl optimized for self-hosting and ease of contribution. Billing logic and AI features are completely removed. Crawl and convert any website into LLM-ready markdown.

Find the images in your dataset most similar to a query image from URL or drag-and-drop, with FiftyOne!

The Mixedbread AI Provider is a provider for the Vercel AI SDK. It provides a simple interface to the Mixedbread AI API.

A Next.js web application that allows users to search for anime and manga using description-based queries. It leverages models/embeddings generated by AniSearchModel.

An app for people with short-term-memory 🧠

Insert data into a Qdrant vector database to train a chatbot on your own data. Designed to work with `librai-ui`, enabling custom data querying and contextual responses from the AI chatbot.

Playground to experiment with how closely a language-based AI thinks two texts are to each other.

Intelligent data steward toolbox using Large Language Model embeddings for automated Data-Harmonization

A simple solution to combine Version Control with Embed Indexing. Creates, updates, and removes embeddings of the repository files based on GIT A (Added Files), M (Modified Files), R (Removed Files), using Voyage and Pinecone.

Use local LLMs in your browser and Node.js apps. Register at https://fxn.ai

This is a simple example of how to use the Ollama RAG (retrieval augmented generation) using Ollama embeddings with nodejs, typescript, docker and chromadb

Magick is a cutting-edge toolkit for a new kind of AI builder. Make Magick with us!

A Retrieval Augmented Generator (RAG) that operates entirely locally, combining document retrieval and language model generation to provide accurate and contextually relevant responses. Built with @langchain-ai