PrivateGPT: Local LLMs to Chat with your Docs

Why PrivateGPT?

PrivateGPT provides an API (a tool for computer programs) that has everything you need to create AI applications that understand context and keep things private.

It’s like a set of building blocks for AI. This API is designed to work just like the OpenAI API, but it has some extra features.

So, if you’re already using the OpenAI API in your software, you can switch to the PrivateGPT API without changing your code, and it won’t cost you any extra money.

You can use PrivateGPT with CPU only if you want

Forget about expensive GPU’s if you dont have one already 💯

The PrivateGPT Project

PrivateGPT allow us to chat with our documents locally and without an internet connection.

• PrivateGPT project
• PrivateGPT Source Code at Github
  • License: Apache 2.0 ✅

How to use PrivateGPT?

• Setting Up PrivateGPT: Choose Your Path 🛠️

  • Manual Setup 🔍:

    1. Detailed Documentation: Follow the official documentation to install all dependencies manually.
       If you go with Manual Setup 👇

       • The documentation of PrivateGPT is great and they guide you to setup all dependencies.

       • You just need Python installed in your computer and then install the required packages.

       • This kind of projects normally have very specific set of packages dependencies (specific versions and so on), that is why it is recommended to use Python Package Management.

  • Docker-based Setup 🐳:
    2. Streamlined Process: Opt for a Docker-based solution to use PrivateGPT for a more straightforward setup process.

SelfHosting PrivateGPT

I have tried those with some other project and they worked for me 90% of the time, probably the other 10% was me doing something wrong.

To make sure that the steps are perfectly replicable for anyone, I bring you a guide with PrivateGPT & Docker to contain all the Dependencies (and make it work 100% of the times).

• To ensure that the steps are perfectly replicable for anyone, I’ve created a guide on using PrivateGPT with Docker to contain all dependencies and make it work flawlessly 100% of the time.
  • 🐳 Follow the Docker image setup guide for quick setup here.
  • 💡 Alternatively, learn how to build your own Docker image to run PrivateGPT locally, which is the recommended approach. You can find the guide here.

With this approach, you will need just one thing to setup PrivateGPT locally: get Docker Installed

PrivateGPT with Docker

1. Get Docker: Ensure that Docker is installed on your machine.

   Really, Just Get Docker 🐋

   You can install Docker for any PC, Mac, or Linux at home or in any cloud provider that you wish. It will just take a few moments. If you are on Linux, just:

   apt-get update && sudo apt-get upgrade && curl -fsSL https://get.docker.com -o get-docker.sh
   sh get-docker.sh
   #sudo apt install docker-compose -y

   And install also Docker-compose with:

   apt install docker-compose -y

   When the process finishes, you can use it to self-host other services as well. You should see the versions with:

   docker --version
   docker-compose --version
   #sudo systemctl status docker #and the status

2. Choose Your Docker Image:

   • Use a Pre-built Image: Download and run a pre-built Docker image suitable for your project.
   • Build Your Own Image: Alternatively, you can build your own Docker image from a Dockerfile tailored to your specific requirements.

3. Configure NGINX for HTTPS: (Optional)

   • If you require secure connections, set up NGINX as a reverse proxy to provide HTTPS by obtaining SSL/TLS certificates.
   • This step ensures encrypted and secure data transmission.

Then, use the following Stack / Docker configuration file to deploy it:

version: '3'

services:
  ai-privategpt:
    image: fossengineer/privategpt  # Replace with your image name and tag
    container_name: privategpt
    ports:
      - "8001:8001"
    volumes:
      - ai-privategpt:/app
    command: /bin/bash -c "poetry run python scripts/setup && tail -f /dev/null" #make run
    
volumes:
  ai-privategpt:

That’s it, now get your favourite LLM model ready and start using it with the PrivateGPT UI at: localhost:8001

Remember that you can use CPU mode only if you dont have a GPU (It happens to me as well).

Just remember to use models compatible with llama.cpp, as the project suggests.

PrivateGPT API

PrivateGPT API is OpenAI API (ChatGPT) compatible, this means that you can use it with other projects that require such API to work.

How to Build your PrivateGPT Docker Image

The best way (and secure) to SelfHost PrivateGPT. Build your own Image.

You will need a Dockerfile.

But dont worry, here you have a sample Dockerfile to build your own PrivateGPT Docker Image.

# Use the specified Python base image
FROM python:3.11-slim

# Set the working directory in the container
WORKDIR /app

# Install necessary packages
RUN apt-get update && apt-get install -y \
    git \
    build-essential

# Clone the private repository
RUN git clone https://github.com/imartinez/privateGPT

WORKDIR /app/privateGPT

# Install poetry
RUN pip install poetry

# Copy the project files into the container
COPY . /app

#Adding openai pre v1 to avoid error
RUN sed -i '/\[tool\.poetry\.dependencies\]/a openai="1.1.0"' pyproject.toml

# Lock and install dependencies using poetry
RUN poetry lock
RUN poetry install --with ui,local

# Run setup script
#RUN poetry run python scripts/setup # this scripts download the models (the embedding and LLM models)

# Keep the container running
#CMD ["tail", "-f", "/dev/null"]

It’s not magic, just some automation to make PrivateGPT work without much effort.

The setup script will download these 2 models by default:

• LLM: conversational model
  • LLama 7B.
• Embedding: the model that converts our documents to a vector DB
  • Mistral 7B Instruct.

Use GGUF format for the models and it will be fine (llama.cpp related)

And then build your Docker image to run PrivateGPT with:

docker build -t privategpt .
#podman build -t privategpt .

#docker tag privategpt docker.io/fossengineer/privategpt:v1 #example I used
#docker push docker.io/fossengineer/privategpt:v1

docker-compose up -d #to spin the container up with CLI

Using your PrivateGPT Docker Image

You will need Docker installed and use the Docker-Compose Stack below.

If you are not very familiar with Docker, don’t be scared and install Portainer to deploy the container with GUI.

version: '3'

services:
  ai-privategpt:
    image: privategpt  # Replace with your image name and tag
    container_name: privategpt2
    ports:
      - "8002:8001"
    volumes:
      - ai-privategpt:/app
    # environment:
    #   - SOME_ENV_VAR=value  # Set any environment variables if needed
    #command: tail -f /dev/null
    # environment:
    #   - PGPT_PROFILES=local
    command: /bin/bash -c "poetry run python scripts/setup && tail -f /dev/null" #make run
    
volumes:
  ai-privategpt:

When the server is started it will print a log Application startup complete.

Execute the comand make run in the container:

docker exec -it privategpt make run

Navigate to http://localhost:8002 to use the Gradio UI or to http://localhost:8002/docs (API section) to try the API using Swagger UI.

FAQ

Other F/OSS Alternatives to have Local LLMs

• The Text Generation Web UI Project, that you can also SelfHost with Docker.

What is happening inside PrivateGPT?

These are the guts of our PrivateGPT beast.

The Embedding Model will create the vectorDB records of our documents and then, the LLM will provide the replies for us.

• Embedding Model - BAAI/bge-small-en-v1.5
• Conversational Model (LLM) - TheBloke/Mistral 7B
• VectorDBs - PrivateGPT uses QDrant (F/OSS ✅)
• RAG Framework - PrivateGPT uses LLamaIndex (yeap, also F/OSS ✅)

You can check and tweak this default options with the settings.yaml file.

Python for PrivateGPT

What are Gradio Apps?

Gradio is an open-source Python library that simplifies the development of interactive machine learning (ML) and natural language processing (NLP) applications.

You can also run Gradio-Lite (JS) - Serverless Gradio running in the browser. Similarly we can do with Transformers.JS

Python Dependencies 101

When we are sharing software, we need to make sure that our PCs have the same libraries/packages installed.

Same applies when we try some Python coding