privateGPT logo

privateGPT

Interact with your data in an execution only environment without using the internet, substantially reducing data security/vulnerability issues created via connection to the web using a combination of LangChainAI + llama.cpp

Key Points: GitHub privateGPT GitHub link: https://github.com/imartinez/privateGPT

Introduce privateGPT

The "privateGPT" project allows users to interact privately with their documents using the power of GPT (Generative Pre-trained Transformer) language models. It ensures 100% privacy by not allowing any data to leave the user's execution environment. Users can ingest documents, ask questions without an internet connection, and receive answers based on the content of their documents. The project provides instructions on setting up the environment, ingesting datasets, and running queries locally. It utilizes LangChain, GPT4All, and LlamaCpp for document processing and embedding creation. The project is not production-ready but serves as a test for a fully private question-answering solution. Interact with your data in an execution only environment without using the internet, substantially reducing data security/vulnerability issues created via connection to the web using a combination of LangChainAI + llama.cpp

Alternatives & Similar Tools

LongLLaMA-handle very long text contexts, up to 256,000 tokens logo

LongLLaMA is a large language model designed to handle very long text contexts, up to 256,000 tokens. It's based on OpenLLaMA and uses a technique called Focused Transformer (FoT) for training. The repository provides a smaller 3B version of LongLLaMA for free use. It can also be used as a replacement for LLaMA models with shorter contexts.