Zep | The Memory Foundation For Your AI Stack

self-improving user memory framework for conversational AI apps

The Fast Vector Similarity Library is designed to provide efficient computation of various similarity measures between vectors.

Question Answering Generative AI application with Large Language Models (LLMs) and Amazon OpenSearch Service

State-of-the-art CLIP/SigLIP embedding models finetuned for the fashion domain. +57% increase in evaluation metrics vs FashionCLIP 2.0.

Hybrid Search demo on Movies Dataset using Couchbase with Native Python SDK & LangChain Vector Store integration & Streamlit

High-level ElasticSearch client for Julia

🔎 A vector based image search engine using Visual Transformer model type.

⚡️ Build quick LLM pipelines for AI applications

Q&A Chatbot Demo using Couchbase, LangChain, OpenAI and Streamlit

This project demonstrates using `Elasticsearch` and vector search techniques to efficiently find answers to user questions in FAQ documents by leveraging embeddings and evaluating search performance with hit rate and mean reciprocal rank (MRR).

RAG Vector Search with MongoDB, Hugging Face and Node JS

This Python Flask application is designed to process and rank resumes based on job descriptions. It uses Azure's Document Analysis Client for document processing, and a MongoDB database for storing job descriptions and resumes. The application also generates embeddings for the processed documents using AzureOpenAI.

Simple and pure Julia-based implementation of ChatGPT retrieval plugin logic

MediCopilot uses AI to assist healthcare professionals

Memory Management Service, a Long Term Memory Solution for AI

Tư Tưởng Hồ Chí Minh Chatbot

Question-Answering App Over Your Own Data with LLamaindex and ElasticSearch !

How to use configure haystack to use weaviate