AIxplora is a open-source tool which let's you query all kind of files not limited to any length or format.

This repository features three demos that can be effortlessly integrated into your AWS environment. They serve as a practical guide to leveraging AWS services for crafting a sophisticated Large Language Model (LLM) Generative AI, geared towards creating a responsive Question and Answer Bot and localizing content generation.

A Node-RED node that interacts with OpenAI machine learning models to generate text like ChatGPT

Simple, cross-platform port of GloVe embeddings, written in C

An LLM challenge to (i) fine-tune pre-trained HuggingFace transformer model to build a Code Generation language model, and (ii) build a retrieval-augmented generation (RAG) application using LangChain

A comprehensive Pre-RAG prototype dashboard for document parsing, multi-method chunking, vector embedding generation, and hybrid search exploration. Built with React and powered by in-browser ML models.

Lemone: the API for french tax law and embeddings computation 🇫🇷

OpenAI Text Embeddings for Semantic FAQ Search. Uses OpenAI embeddings to enable intelligent, semantic search across FAQs for more accurate and relevant results.

FastAPI backend featuring Jina AI embeddings, ChromaDB vector search, and multi-LLM support (Gemini Pro + Groq) for evidence-based medical assessments with emergency detection and session management.

Code and Analysis for our paper titled 'Low Anisotropy Sense Retrofitting (LASeR): Towards Isotropic and Sense Enriched Representations

A web-based dashboard allowing the epxloration of a small NLP dataset obtained by scraping a religious alt-right website.

AI SDK - Jina AI Provider

Lightweight Semantic Chunking Library. Plug any embedding provider/API. Batch embeddings for efficiency and handling API rate limits.

RAG supported Chat API using Ollama LLM

Application de suggestions de contenu basé sur l'historique utilisateur via un model d'embeddings entrainé - Projet 10 du parcours de formation AI Engineer d'Openclassrooms

Analyzes and improves text embeddings by comparing language models and applying fine-tuning to reshape embedding space geometry.

Comparison of dense, LI, sparse, and hybrid retrievers across different backends to determine the Pareto frontiers across quality, latency, and storage