In a previous tutorial, we demonstrated how you can train a custom AI chatbot using the ChatGPT API. Although it works pretty well, we know that once your free OpenAI credit is used up, you have to pay for the API, which is not affordable for everyone. Additionally, several users are not comfortable sharing confidential data with OpenAI. So if you want to create a private AI chatbot without connecting to the internet or paying any money for API access, this guide is for you. PrivateGPT is a new open source project that lets you interact with your documents privately in an AI chatbot interface. To find out more, let's learn how to train a custom AI chatbot using PrivateGPT locally.

1. To run PrivateGPT locally on your machine, you need a moderate to advanced machine. You can't run it on older laptops/desktops. To give you a brief idea, I tested PrivateGPT on an entry-level desktop with an Intel 10th generation i3 processor, and it took almost 2 minutes to answer questions. Remember that PrivateGPT does not use the GPU. Currently, it only relies on the CPU, which makes the performance even worse. But if you want to test the project, you can certainly go ahead and check it out.

2. PrivateGPT can be used offline without connecting to any online servers or adding any API keys from OpenAI or Pinecone. To facilitate this, it runs an LLM model locally on your computer. So you need to download a GPT4All-J compatible LLM model on your computer. I have added detailed steps below for you to follow.

1. First, you need to install Python 3.10 or later on your Windows, macOS or Linux computer. You can click this link to download Python directly.