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.
Python script demonstrating the process of recovering text from embeddings, highlighting the associated privacy risks and mitigation strategies in dense retrieval systems.
A Node-RED node that interacts with OpenAI machine learning models to generate text like ChatGPT
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.
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
Lemone: the API for french tax law and embeddings computation 🇫🇷
A production-style RAG-based AI Knowledge Assistnt developed during the AI & Automation Internship at NEXEAGENT. The system securely uploads company documents, generates semantic embeddings, stores contextual knowledge in a vector database, and delivers accurate AI-powered responses using Google Gemini, (RAG) & intelligent vector Search pipelines.
ChemicalDice is a deep learning featurizer trained with unsupervised learning on the CHEMBL database. It encodes six molecular representations: quantum descriptors, bioactivity profiles, language model embeddings, graph-based features, physicochemical properties, and 2D image-based features.
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.
ReelMind — A RAG-powered chatbot that lets you paste any YouTube URL and ask questions about the video's content. It extracts the transcript, indexes it with embeddings and FAISS, and answers your questions grounded in what was actually said.
OpenAI Text Embeddings for Semantic FAQ Search. Uses OpenAI embeddings to enable intelligent, semantic search across FAQs for more accurate and relevant results.
AI-powered fashion image similarity search system. Originally built as a technical hiring assignment for LabhTeX — this project's success led directly to a full-time AI/ML Engineer offer. Uses image embeddings for visual similarity search, containerized with Docker and deployment-ready.
A web-based dashboard allowing the epxloration of a small NLP dataset obtained by scraping a religious alt-right website.
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
Comparison of dense, LI, sparse, and hybrid retrievers across different backends to determine the Pareto frontiers across quality, latency, and storage
Analyzes and improves text embeddings by comparing language models and applying fine-tuning to reshape embedding space geometry.
Lightweight Semantic Chunking Library. Plug any embedding provider/API. Batch embeddings for efficiency and handling API rate limits.
To associate your repository with the embeddings-model topic, visit your repo's landing page and select "manage topics."