How to Set Up and Use Quivr with Docker on Ubuntu 22.04

Quivr, your second brain, utilizes the power of GenerativeAI to be your personal assistant! It is an Open-source RAG Framework for building GenAI Second Brains that is free to use locally. Quivr allows users to store and retrieve unstructured information, chats with your docs (PDF, CSV, ...), interact with connected applications, and build AI applications powered by Foundation Models.

Fast and Efficient: Designed with speed and efficiency at its core. Quivr ensures rapid access to your data.

Secure: Your data, your control. Always.

File Compatibility: Text, Markdown, PDF, Powerpoint, Excel, CSV, Word, Audio, Video

Public/Private: Share your brains with your users via a public link, or keep them private.

Offline Mode: Quivr works offline, so you can access your data anytime, anywhere.

Operating System: Ubuntu 20 or newer

Git, Python 3.9 or later.

Docker and Docker Compose

Supabase CLI - Follow the instructions here to install the Supabase CLI that is required.

Running Quivr with Docker provides a containerized environment that simplifies setup and avoids dependency issues. Here’s a step-by-step guide to installing and using Quivr with Docker on Ubuntu 22.04.

Open Git Bash (or any terminal like PowerShell). Run the following command to clone the Quivr repository:

git clone https://github.com/QuivrHQ/quivr.git
cd quivr

Quivr requires some environment variables to be set up for database connections and other services. Docker simplifies this process, but you’ll still need to configure a .env file.

In the Quivr directory, you’ll find a file called .env.example. Copy it to create your own .env file:

cp .env.example .env
vim .env # or emacs or vscode or nano

You just need to update the OPENAI_API_KEY variable in the .env file. If you want to use Ollama instead, please uncomment the following lines in the .env file: OLLAMA_API_BASE_URL. Remeber to install Ollama first and run the following command to start Ollama: ollama run llama3.2. You can find more information about Ollama here.

cd backend && supabase start
supabase status

Quivr uses Docker Compose to set up the application along with its dependencies (Postgres, Redis, etc.). Open a terminal (Git Bash or PowerShell) and navigate to the Quivr directory, Run the following command to start Quivr using Docker Compose:

cd ../
docker compose pull
docker compose up

The first time you run this command, Docker will download the images, which may take a few minutes depending on your internet speed. After the build completes, Quivr and its services will be running.

Open your web browser and navigate to http://localhost:3000. You will see the Quivr interface. You can now sign in to the app with admin@quivr.app & admin. You can access the app at http://localhost:3000/login.

Note: You can access Quivr backend API at http://localhost:5050/docs.

In the Quivr interface, click on the "Create brain" button to upload text files, PDFs, or other supported document types. Quivr will process and index the content, making it searchable through the platform.

After creating your brain app, you can now query your uploaded documents by asking questions or typing keywords. Quivr uses advanced language models to interpret your queries and retrieve the most relevant information.

By following these steps, you can easily set up and run Quivr on Windows 10 using Docker. The containerized setup simplifies installation and configuration while providing a scalable solution for knowledge management. With Quivr, you can efficiently store, manage, and query your knowledge base using AI-powered tools. For more advanced configurations, explore the Quivr GitHub repository for additional documentation and community support.