diff --git a/docs/docs/get-started/install.mdx b/docs/docs/get-started/install.mdx index cbaa5095..c52b6ec3 100644 --- a/docs/docs/get-started/install.mdx +++ b/docs/docs/get-started/install.mdx @@ -28,66 +28,131 @@ If you prefer running Podman or Docker containers and manually editing `.env` fi - Create an [OpenAI API key](https://platform.openai.com/api-keys). This key is **required** to start OpenRAG, but you can choose a different model provider during [Application Onboarding](#application-onboarding). - Optional: Install GPU support with an NVIDIA GPU, [CUDA](https://docs.nvidia.com/cuda/) support, and compatible NVIDIA drivers on the OpenRAG host machine. If you don't have GPU capabilities, OpenRAG provides an alternate CPU-only deployment. -## Install OpenRAG {#install} +## Installation Methods {#install} :::note Windows users To use OpenRAG on Windows, use [WSL (Windows Subsystem for Linux)](https://learn.microsoft.com/en-us/windows/wsl/install). ::: -To set up a project and install OpenRAG as a dependency, do the following: +Choose an installation method based on your needs: -1. Create a new project with a virtual environment using `uv init`. +* The automatic installer script detects and installs prerequisites and then runs OpenRAG. Recommended for first-time users. +* For a quick test, use `uvx` to run OpenRAG without creating a project or modifying files. +* Use `uv add` to install OpenRAG as a managed dependency in a new or existing Python project. +* Use `uv pip install` to install OpenRAG into an existing virtual environment. - ```bash - uv init YOUR_PROJECT_NAME - cd YOUR_PROJECT_NAME - ``` + + - The `(venv)` prompt doesn't change, but `uv` commands will automatically use the project's virtual environment. - For more information on virtual environments, see the [uv documentation](https://docs.astral.sh/uv/pip/environments). - -2. Add OpenRAG to your project. - ```bash - uv add openrag - ``` - - To add a specific version of OpenRAG: - ```bash - uv add openrag==0.1.25 - ``` - -3. Start the OpenRAG TUI. - ```bash - uv run openrag - ``` - -
- Install a local wheel - - If you downloaded the OpenRAG wheel to your local machine, follow these steps: - - 1. Add the wheel to your project's virtual environment. + The script detects and installs uv, Docker/Podman, and Docker Compose prerequisites, then runs OpenRAG with `uvx`. + 1. Create a directory to store the OpenRAG configuration files: ```bash - uv add PATH/TO/openrag-VERSION-py3-none-any.whl + mkdir openrag-workspace + cd openrag-workspace ``` - Replace `PATH/TO/` and `VERSION` with the path and version of your downloaded OpenRAG `.whl` file. - - For example, if your `.whl` file is in the `~/Downloads` directory: - + 2. Run the installer: ```bash - uv add ~/Downloads/openrag-0.1.8-py3-none-any.whl + curl -fsSL https://docs.openr.ag/files/run_openrag_with_prereqs.sh | bash ``` - 2. Run OpenRAG. + The TUI creates a `.env` file and docker-compose files in the current working directory. + + + + Use `uvx` to quickly run OpenRAG without creating a project or modifying any files. + + 1. Create a directory to store the OpenRAG configuration files: + ```bash + mkdir openrag-workspace + cd openrag-workspace + ``` + + 2. Run OpenRAG: + ```bash + uvx openrag + ``` + + To run a specific version: + ```bash + uvx --from openrag==0.1.30 openrag + ``` + + The TUI creates a `.env` file and docker-compose files in the current working directory. + + + + + Use `uv add` to install OpenRAG as a dependency in your Python project. This adds OpenRAG to your `pyproject.toml` and lockfile, making your installation reproducible and version-controlled. + + 1. Create a new project with a virtual environment: + ```bash + uv init YOUR_PROJECT_NAME + cd YOUR_PROJECT_NAME + ``` + + The `(venv)` prompt doesn't change, but `uv` commands will automatically use the project's virtual environment. + + 2. Add OpenRAG to your project: + ```bash + uv add openrag + ``` + + To add a specific version: + ```bash + uv add openrag==0.1.30 + ``` + + 3. Start the OpenRAG TUI: ```bash uv run openrag ``` - + +
+ Install a local wheel + + If you downloaded the OpenRAG wheel to your local machine, install it by specifying its path: + + 1. Add the wheel to your project: + ```bash + uv add PATH/TO/openrag-VERSION-py3-none-any.whl + ``` + + Replace `PATH/TO/` and `VERSION` with the path and version of your downloaded OpenRAG `.whl` file. + + 2. Run OpenRAG: + ```bash + uv run openrag + ```
-4. Continue with [Set up OpenRAG with the TUI](#setup). + + + + + Use `uv pip install` to install OpenRAG into an existing virtual environment that isn't managed by `uv`. + + :::tip + For new projects, `uv add` is recommended as it manages dependencies in your project's lockfile. + ::: + + 1. Activate your virtual environment. + + 2. Install OpenRAG: + ```bash + uv pip install openrag + ``` + + 3. Run OpenRAG: + ```bash + openrag + ``` + + + + +Continue with [Set up OpenRAG with the TUI](#setup). ## Set up OpenRAG with the TUI {#setup} diff --git a/scripts/run_openrag_with_prereqs.sh b/docs/static/files/run_openrag_with_prereqs.sh similarity index 100% rename from scripts/run_openrag_with_prereqs.sh rename to docs/static/files/run_openrag_with_prereqs.sh