📄 Explore the FSM 8.9.2 Meta-Reflective Framework for structured guidance on non-commercial adaptation and crediting in your projects.

Convert any image into a Region Adjacency Graph (RAG)

A bit of JavaScript to fix your text rag for prepositions, small words, or emphasis, adapted to the French language

Retrieval-Augmented-Generation of over 1700+ pages of Unreal Engine documentation served through FAISS + OpenAI with LangChain

Implementation of semantic search using Sentence-BERT (SBERT) for a workshop. It demonstrates how to generate sentence embeddings and perform search based on cosine similarity, allowing for meaningful, context-aware search results. The repository includes instructions for setting up, text preprocessing, and running the search.

Ask questions about your books

An interactive tool to ask questions about your Markdown files using Streamlit UI, powered by OpenAI API

GenAI RAG based app tests

RAG chatbot built on top of trending M&A news.

A modern RAG framework for closed and open source LLMs built as a demo for the startup Brance.

A minimal & iterative implementation of a retriever-augmented generation (RAG) system

This repository contains question-answers model as an interface which retrieves answers from vector database for a question. Embeddings or tokenised vector being computed using OpenAI API call which gets inserted into ChromaDB as a RAG. OpenAI API key would be required to run this service.

Demo UI for the axgen library

A simple chat application that integrate LLM APIs such as OpenAI or Cohere and VectorDB to perform tarot readings

Exploring the use case of LLMs in healthcare, in particular assisting in document retrieval and summarization.

Tutorials for LangChain

LambdaRAG is a Retrieval Augmented Generation Chat AI Demo. Please read the full RAGs to Riches blog series.