What does HackerNews think of privateGPT?

Interact privately with your documents using the power of GPT, 100% privately, no data leaks

Language: Python

Run ChatGPT-like LLMs on your laptop in 3 lines of code | Sep 2023
I've been playing around with https://github.com/imartinez/privateGPT and wanted to create a simple Python package that made it easier to run ChatGPT-like LLMs on your own machine, use them with non-public data, and integrate them into practical GPU-accelerated applications.

This resulted in Python package I call OnPrem.LLM.

In the documentation, there are examples for how to use it for information extraction, text generation, retrieval-augmented generation (i.e., chatting with documents on your computer), and text-to-code generation: https://amaiya.github.io/onprem/

Enjoy!

GPU-Accelerated LLM on an Orange Pi | Aug 2023
Expand Context ↕
> a local wikipedia dump

There exists (at least) a project to train and query an LLM on local documents: privateGPT - https://github.com/imartinez/privateGPT

It should provide links to the the source with the relevant content, to check the exact text:

> You'll need to wait 20-30 seconds (depending on your machine) while the LLM model consumes the prompt and prepares the answer. Once done, it will print the answer and the 4 sources it used as context from your documents

You will have noticed, in that first sentence, that it may not be practical, especially on an Orange Pi.
Ask HN: What's the best self hosted/local alternative to GPT-4? | May 2023
For personal use, check out https://github.com/imartinez/privateGPT. It's lightweight and has lots of momentum from the OS community. There's even an open PR to support huggingface LLMs. For business use, here's some shameless self promotion: https://mirage-studio.io/private_chatgpt. We offer a version that can be hosted on your own GPU cluster.
Ask HN: What's the best self hosted/local alternative to GPT-4? | May 2023
This is a good candidate: https://github.com/imartinez/privateGPT
PrivateGPT: An app to interact privately with your documents using GPT | May 2023
Seriously? This is low effort even in area of low efforts.

First, the name is similar to a better known repo: https://github.com/imartinez/privateGPT

just the P is capitalized.

Even while giving credits - instead of linking to the original repo trying to link to the creator to try and hide the origin.

Show HN: DB-GPT, an LLM tool for database | May 2023
How does this compare with PrivateGPT (https://github.com/imartinez/privateGPT)

How long do y'all think it'll take for production-ready projects like this to effectively be run on something like an M2 chip?

ChatGPT vs. open source on harder tasks | May 2023
Expand Context ↕
And their "what's next?" links to a project that relies on langchain[0].

[0] https://github.com/imartinez/privateGPT