gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

propagate prerequisites and format install cmds

Browse source
This commit is contained in:
April M 2025-12-04 19:16:05 -08:00
parent d578e7832e
commit 951fd4b176
8 changed files with 195 additions and 173 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/docs/_partial-onboarding.mdx
View file

@ -30,7 +30,6 @@ You only need to complete onboarding for your preferred providers.
4. In the second onboarding panel, select a provider for embeddings and select your **Embedding Model**.
5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**.
6. Continue with the [Quickstart](/quickstart).
</TabItem>
<TabItem value="OpenAI" label="OpenAI">
@ -42,7 +41,6 @@ You only need to complete onboarding for your preferred providers.
4. In the second onboarding panel, select a provider for embeddings and select your **Embedding Model**.
5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**.
6. Continue with the [Quickstart](/quickstart).
</TabItem>
<TabItem value="IBM watsonx.ai" label="IBM watsonx.ai">
@ -54,7 +52,6 @@ You only need to complete onboarding for your preferred providers.
4. In the second onboarding panel, select a provider for embeddings and select your **Embedding Model**.
5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**.
6. Continue with the [Quickstart](/quickstart).
</TabItem>
<TabItem value="Ollama" label="Ollama">
@ -73,7 +70,6 @@ You only need to complete onboarding for your preferred providers.
</details>
3. Click **Complete**.
4. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
5. Continue with the [Quickstart](/quickstart).
</TabItem>
</Tabs>

25
docs/docs/_partial-wsl-install.mdx
View file

@ -1,25 +0,0 @@
1. [Install WSL](https://learn.microsoft.com/en-us/windows/wsl/install) with the Ubuntu distribution using WSL 2:
```powershell
wsl --install -d Ubuntu
```
For new installations, the `wsl --install` command uses WSL 2 and Ubuntu by default.
For existing WSL installations, you can [change the distribution](https://learn.microsoft.com/en-us/windows/wsl/install#change-the-default-linux-distribution-installed) and [check the WSL version](https://learn.microsoft.com/en-us/windows/wsl/install#upgrade-version-from-wsl-1-to-wsl-2).
:::warning Known limitation
OpenRAG isn't compatible with nested virtualization, which can cause networking issues.
Don't install OpenRAG on a WSL distribution that is installed inside a Windows VM.
Instead, install OpenRAG on your base OS or a non-nested Linux VM.
:::
2. [Start your WSL Ubuntu distribution](https://learn.microsoft.com/en-us/windows/wsl/install#ways-to-run-multiple-linux-distributions-with-wsl) if it doesn't start automatically.
3. [Set up a username and password for your WSL distribution](https://learn.microsoft.com/en-us/windows/wsl/setup/environment#set-up-your-linux-username-and-password).
4. [Install Docker Desktop for Windows with WSL 2](https://learn.microsoft.com/en-us/windows/wsl/tutorials/wsl-containers). When you reach the Docker Desktop **WSL integration** settings, make sure your Ubuntu distribution is enabled, and then click **Apply & Restart** to enable Docker support in WSL.
5. Install and run OpenRAG from within your WSL Ubuntu distribution.
<br/>
If you encounter issues with port forwarding or the Windows Firewall, you might need to adjust the [Hyper-V firewall settings](https://learn.microsoft.com/en-us/windows/security/operating-system-security/network-security/windows-firewall/hyper-v-firewall) to allow communication between your WSL distribution and the Windows host. For more troubleshooting advice for networking issues, see [Troubleshooting WSL common issues](https://learn.microsoft.com/en-us/windows/wsl/troubleshooting#common-issues).

33
docs/docs/get-started/docker.mdx
View file

@ -6,7 +6,6 @@ slug: /docker
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import PartialOnboarding from '@site/docs/_partial-onboarding.mdx';
import PartialWsl from '@site/docs/_partial-wsl-install.mdx';
To manage your own OpenRAG services, deploy OpenRAG with Docker or Podman.
@ -20,36 +19,30 @@ OpenRAG has two Docker Compose files. Both files deploy the same services, but t
## Prerequisites
- Install the following:
- For Microsoft Windows, you must use the Windows Subsystem for Linux (WSL).
See [Install OpenRAG on Windows](/install-windows) before proceeding.
- [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- [uv](https://docs.astral.sh/uv/getting-started/installation/).
- [Podman](https://podman.io/docs/installation) (recommended) or [Docker](https://docs.docker.com/get-docker/).
- [`podman-compose`](https://docs.podman.io/en/latest/markdown/podman-compose.1.html) or [Docker Compose](https://docs.docker.com/compose/install/). To use Docker Compose with Podman, you must alias Docker Compose commands to Podman commands.
- Install [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- Microsoft Windows only: To run OpenRAG on Windows, you must use the Windows Subsystem for Linux (WSL).
- Install [uv](https://docs.astral.sh/uv/getting-started/installation/).
<details>
<summary>Install WSL for OpenRAG</summary>
- Install [Podman](https://podman.io/docs/installation) (recommended) or [Docker](https://docs.docker.com/get-docker/).
<PartialWsl />
- Install [Podman Compose](https://docs.podman.io/en/latest/markdown/podman-compose.1.html) or [Docker Compose](https://docs.docker.com/compose/install/).
To use Docker Compose with Podman, you must alias Docker Compose commands to Podman commands.
</details>
- Prepare model providers and credentials.
During [application onboarding](#application-onboarding), you must select language model and embedding model providers.
If your chosen provider offers both types, you can use the same provider for both selections.
If your provider offers only one type, such as Anthropic, you must select two providers.
Gather the credentials and connection details for your chosen model providers before starting onboarding:
- Gather the credentials and connection details for your preferred model providers.
- OpenAI: Create an [OpenAI API key](https://platform.openai.com/api-keys).
- Anthropic language models: Create an [Anthropic API key](https://www.anthropic.com/docs/api/reference).
- IBM watsonx.ai: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.
- Ollama: Use the [Ollama documentation](https://docs.ollama.com/) to set up your Ollama instance locally, in the cloud, or on a remote server, and then get your Ollama server's base URL.
- Optional: Install GPU support with an NVIDIA GPU, [CUDA](https://docs.nvidia.com/cuda/) support, and compatible NVIDIA drivers on the OpenRAG host machine. This is required to use the GPU-accelerated Docker Compose file. If you choose not to use GPU support, you must use the CPU-only Docker Compose file instead.
You must have access to at least one language model and one embedding model.
If your chosen provider offers both types, you can use the same provider for both models.
If your provider offers only one type, such as Anthropic, you must select two providers.
- 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 with Docker Compose

127
docs/docs/get-started/install-uv.mdx
View file

@ -9,76 +9,113 @@ You can use [`uv`](https://docs.astral.sh/uv/getting-started/installation/) to i
For other installation methods, see [Choose an installation method](/install-options).
## Prerequisites
- For Microsoft Windows, you must use the Windows Subsystem for Linux (WSL).
See [Install OpenRAG on Windows](/install-windows) before proceeding.
* **`uv pip install`**: Install OpenRAG as an unmanaged dependency in a virtual environment.
* **`uv add`** (Recommended): Install OpenRAG as a managed dependency in a new or existing Python project.
- Install [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- Install [uv](https://docs.astral.sh/uv/getting-started/installation/).
## uv add (Recommended)
- Install [Podman](https://podman.io/docs/installation) (recommended) or [Docker](https://docs.docker.com/get-docker/).
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.
- Install [Podman Compose](https://docs.podman.io/en/latest/markdown/podman-compose.1.html) or [Docker Compose](https://docs.docker.com/compose/install/).
To use Docker Compose with Podman, you must alias Docker Compose commands to Podman commands.
1. Create a new project with a virtual environment:
```bash
uv init YOUR_PROJECT_NAME
cd YOUR_PROJECT_NAME
```
- Gather the credentials and connection details for your preferred model providers.
The `(venv)` prompt doesn't change, but `uv` commands will automatically use the project's virtual environment.
- OpenAI: Create an [OpenAI API key](https://platform.openai.com/api-keys).
- Anthropic language models: Create an [Anthropic API key](https://www.anthropic.com/docs/api/reference).
- IBM watsonx.ai: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.
- Ollama: Use the [Ollama documentation](https://docs.ollama.com/) to set up your Ollama instance locally, in the cloud, or on a remote server, and then get your Ollama server's base URL.
2. Add the OpenRAG package to your project:
```bash
uv add openrag
```
You must have access to at least one language model and one embedding model.
If your chosen provider offers both types, you can use the same provider for both models.
If your provider offers only one type, such as Anthropic, you must select two providers.
To add a specific version:
```bash
uv add openrag==0.1.30
```
- 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.
If you downloaded the OpenRAG wheel to your local machine, install OpenRAG by specifying the path and name of the OpenRAG `.whl` file:
## Install and start OpenRAG with uv
```bash
uv add PATH/TO/openrag-VERSION-py3-none-any.whl
```
There are two ways to install OpenRAG with `uv`:
* [**`uv add`** (Recommended)](#uv-add): Install OpenRAG as a managed dependency in a new or existing `uv` Python project.
This is recommended because it adds OpenRAG to your `pyproject.toml` and lockfile for better management of dependencies and the virtual environment.
* [**`uv pip install`**](#uv-pip-install): Use the [`uv pip` interface](https://docs.astral.sh/uv/pip/) to install OpenRAG into an existing Python project that uses `pip`, `pip-tools`, and `virtualenv` commands.
3. Start the OpenRAG TUI:
```bash
uv run openrag
```
If you encounter errors during installation, see [Troubleshoot OpenRAG](/support/troubleshoot).
### uv add {#uv-add}
## uv pip install
1. Create a new `uv`-managed Python project:
Use `uv pip install` to install OpenRAG into an existing virtual environment that isn't managed by `uv`.
```bash
uv init PROJECT_NAME
```
:::tip
For new projects, `uv add` is recommended as it manages dependencies in your project's lockfile.
:::
2. Change into your new project directory:
1. Activate your virtual environment.
```bash
cd PROJECT_NAME
```
2. Install OpenRAG:
```bash
uv pip install openrag
```
Because `uv` manages the virtual environment for you, you won't see a `(venv)` prompt.
`uv` commands automatically use the project's virtual environment.
3. Run OpenRAG:
```bash
uv run openrag
```
If you encounter errors during installation, see [Troubleshoot OpenRAG](/support/troubleshoot).
2. Add OpenRAG to your project:
* Add the latest version:
```bash
uv add openrag
```
* Add a specific version:
```bash
uv add openrag==0.1.30
```
* Add a local wheel:
```bash
uv add path/to/openrag-VERSION-py3-none-any.whl
```
For more options, see [Managing dependencies with `uv`](https://docs.astral.sh/uv/concepts/projects/dependencies/).
3. Start the OpenRAG TUI:
```bash
uv run openrag
```
### uv pip install {#uv-pip-install}
1. Activate your virtual environment.
2. Install the OpenRAG Python package:
```bash
uv pip install openrag
```
3. Start the OpenRAG TUI:
```bash
uv run openrag
```
## Set up OpenRAG with the TUI
<!-- use partial? -->
When the Terminal User Interface (TUI) starts, you must complete the initial setup to configure OpenRAG.
![OpenRAG TUI Interface](@site/static/img/OpenRAG_TUI_2025-09-10T13_04_11_757637.svg)
## Next steps
* [Manage OpenRAG services](/manage-services)
* [Chat](/chat)
* [Upload documents](/ingestion)
* Try some of OpenRAG's core features in the [quickstart](/quickstart#chat-with-documents).
* Learn how to [manage OpenRAG services](/manage-services).
* [Upload documents](/ingestion), and then use the [**Chat**](/chat) to explore your data.

74
docs/docs/get-started/install-uvx.mdx
View file

@ -11,37 +11,63 @@ You can use [`uvx`](https://docs.astral.sh/uv/guides/tools/#running-tools) to in
The [automatic installer script](/install) also uses `uvx` to install OpenRAG.
:::
Depending on your project structure, `uvx` might not be suitable for production deployments.
This installation method is best for testing OpenRAG by running it outside of a Python project.
For other installation methods, see [Choose an installation method](/install-options).
## Prerequisites
- For Microsoft Windows, you must use the Windows Subsystem for Linux (WSL).
See [Install OpenRAG on Windows](/install-windows) before proceeding.
- Install [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- Install [uv](https://docs.astral.sh/uv/getting-started/installation/).
- Install [Podman](https://podman.io/docs/installation) (recommended) or [Docker](https://docs.docker.com/get-docker/).
- Install [Podman Compose](https://docs.podman.io/en/latest/markdown/podman-compose.1.html) or [Docker Compose](https://docs.docker.com/compose/install/).
To use Docker Compose with Podman, you must alias Docker Compose commands to Podman commands.
- Gather the credentials and connection details for your preferred model providers.
- OpenAI: Create an [OpenAI API key](https://platform.openai.com/api-keys).
- Anthropic language models: Create an [Anthropic API key](https://www.anthropic.com/docs/api/reference).
- IBM watsonx.ai: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.
- Ollama: Use the [Ollama documentation](https://docs.ollama.com/) to set up your Ollama instance locally, in the cloud, or on a remote server, and then get your Ollama server's base URL.
You must have access to at least one language model and one embedding model.
If your chosen provider offers both types, you can use the same provider for both models.
If your provider offers only one type, such as Anthropic, you must select two providers.
- 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 and run OpenRAG with uvx
1. Create a directory to store your OpenRAG configuration files and data, and then change to that directory:
1. Create a directory to store your OpenRAG configuration files and data, and then change to that directory:
```bash
mkdir openrag-workspace
cd openrag-workspace
```
```bash
mkdir openrag-workspace
cd openrag-workspace
```
:::tip
If you want to use a pre-populated [`.env`](/reference/configuration) file for OpenRAG, copy it to this directory before invoking OpenRAG.
:::
2. Optional: If you want to use a pre-populated [`.env`](/reference/configuration) file for OpenRAG, copy it to this directory before invoking OpenRAG.
2. Invoke OpenRAG:
```bash
uvx openrag
```
3. Invoke OpenRAG:
You can invoke a specific version using any of the [`uvx` version specifiers](https://docs.astral.sh/uv/guides/tools/#requesting-specific-versions), such as `--from`:
```bash
uvx openrag
```
```bash
uvx --from openrag==0.1.30 openrag
```
You can invoke a specific version using any of the [`uvx` version specifiers](https://docs.astral.sh/uv/guides/tools/#requesting-specific-versions), such as `--from`:
Invoking OpenRAG with `uvx openrag` creates a cached, ephemeral environment for the TUI in your local `uv` cache.
By invoking OpenRAG in a specific directory, your OpenRAG configuration files and data are stored separately from the `uv` cache.
Clearing the `uv` cache doesn't remove your entire OpenRAG installation.
After clearing the cache, you can re-invoke OpenRAG (`uvx openrag`) to restart the TUI with your preserved configuration and data.
```bash
uvx --from openrag==0.1.30 openrag
```
Invoking OpenRAG with `uvx openrag` creates a cached, ephemeral environment for the TUI in your local `uv` cache.
By invoking OpenRAG in a specific directory, your OpenRAG configuration files and data are stored separately from the `uv` cache.
Clearing the `uv` cache doesn't remove your entire OpenRAG installation.
After clearing the cache, you can re-invoke OpenRAG (`uvx openrag`) to restart the TUI with your preserved configuration and data.
If you encounter errors during installation, see [Troubleshoot OpenRAG](/support/troubleshoot).
@ -56,6 +82,6 @@ If it detects a `.env` file in the OpenRAG installation directory, it sources an
## Next steps
* [Manage OpenRAG services](/manage-services)
* [Chat](/chat)
* [Upload documents](/ingestion)
* Try some of OpenRAG's core features in the [quickstart](/quickstart#chat-with-documents).
* Learn how to [manage OpenRAG services](/manage-services).
* [Upload documents](/ingestion), and then use the [**Chat**](/chat) to explore your data.

39
docs/docs/get-started/install-windows.mdx
View file

@ -3,25 +3,38 @@ title: Install OpenRAG on Microsoft Windows
slug: /install-windows
---
import PartialWsl from '@site/docs/_partial-wsl-install.mdx';
If you're using Windows, you must install OpenRAG within the Windows Subsystem for Linux (WSL).
For guided configuration and simplified service management, install OpenRAG with services managed by the [Terminal User Interface (TUI)](/tui).
For self-managed services, deploy OpenRAG with Docker or Podman inside your WSL distribution.
## Nested virtualization isn't supported
## Prepare your WSL environment
OpenRAG isn't compatible with nested virtualization, which can cause networking issues.
Don't install OpenRAG on a WSL distribution that is installed inside a Windows VM.
Instead, install OpenRAG on your base OS or a non-nested Linux VM.
<PartialWsl />
## Install OpenRAG in the WSL
## Install OpenRAG within the WSL
1. [Install WSL](https://learn.microsoft.com/en-us/windows/wsl/install) with an Ubuntu distribution using WSL 2:
<!-- Use any install method to install OpenRAG within your WSL distribution. -->
```powershell
wsl --install -d Ubuntu
```
## Next steps
For new installations, the `wsl --install` command uses WSL 2 and Ubuntu by default.
* [Manage OpenRAG services](/manage-services)
* [Chat](/chat)
* [Upload documents](/ingestion)
For existing WSL installations, you can [change the distribution](https://learn.microsoft.com/en-us/windows/wsl/install#change-the-default-linux-distribution-installed) and [check the WSL version](https://learn.microsoft.com/en-us/windows/wsl/install#upgrade-version-from-wsl-1-to-wsl-2).
2. [Start your WSL Ubuntu distribution](https://learn.microsoft.com/en-us/windows/wsl/install#ways-to-run-multiple-linux-distributions-with-wsl) if it doesn't start automatically.
3. [Set up a username and password for your WSL distribution](https://learn.microsoft.com/en-us/windows/wsl/setup/environment#set-up-your-linux-username-and-password).
4. [Install Docker Desktop for Windows with WSL 2](https://learn.microsoft.com/en-us/windows/wsl/tutorials/wsl-containers). When you reach the Docker Desktop **WSL integration** settings, make sure your Ubuntu distribution is enabled, and then click **Apply & Restart** to enable Docker support in WSL.
The Docker Desktop WSL integration makes Docker available within your WSL distribution.
You don't need to install Docker or Podman separately in your WSL distribution before you install OpenRAG.
5. Install and run OpenRAG from within your WSL Ubuntu distribution.
You can install OpenRAG in your WSL distribution using any of the [OpenRAG installation methods](/install-options).
## Troubleshoot OpenRAG in WSL
If you encounter issues with port forwarding or the Windows Firewall, you might need to adjust the [Hyper-V firewall settings](https://learn.microsoft.com/en-us/windows/security/operating-system-security/network-security/windows-firewall/hyper-v-firewall) to allow communication between your WSL distribution and the Windows host. For more troubleshooting advice for networking issues, see [Troubleshooting WSL common issues](https://learn.microsoft.com/en-us/windows/wsl/troubleshooting#common-issues).

47
docs/docs/get-started/install.mdx
View file

@ -13,44 +13,34 @@ For a fully guided installation and preview of OpenRAG's core features, try the
For guided configuration and simplified service management, install OpenRAG with services managed by the [Terminal User Interface (TUI)](/tui).
The installer script detects and installs any missing dependencies, and then installs OpenRAG with [`uvx`](https://docs.astral.sh/uv/guides/tools/#running-tools) in the directory where you run the script.
The installer script installs `uv`, Docker or Podman, Docker Compose, and OpenRAG.
This installation method is best for running OpenRAG outside of a Python project.
This installation method is best for testing OpenRAG by running it outside of a Python project.
For other installation methods, see [Choose an installation method](/install-options).
## Prerequisites
- All OpenRAG installations require [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- For Microsoft Windows, you must use the Windows Subsystem for Linux (WSL).
See [Install OpenRAG on Windows](/install-windows) before proceeding.
- If you aren't using the automatic installer script, install the following:
- Install [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- [uv](https://docs.astral.sh/uv/getting-started/installation/).
- [Podman](https://podman.io/docs/installation) (recommended) or [Docker](https://docs.docker.com/get-docker/).
- [`podman-compose`](https://docs.podman.io/en/latest/markdown/podman-compose.1.html) or [Docker Compose](https://docs.docker.com/compose/install/). To use Docker Compose with Podman, you must alias Docker Compose commands to Podman commands.
- To run OpenRAG on Microsoft Windows, you must use the Windows Subsystem for Linux (WSL).
See [Install OpenRAG on Windows](/install-windows).
- Prepare model providers and credentials.
During [application onboarding](#application-onboarding), you must select language model and embedding model providers.
If your chosen provider offers both types, you can use the same provider for both selections.
If your provider offers only one type, such as Anthropic, you must select two providers.
Gather the credentials and connection details for your chosen model providers before starting onboarding:
- Gather the credentials and connection details for your preferred model providers.
- OpenAI: Create an [OpenAI API key](https://platform.openai.com/api-keys).
- Anthropic language models: Create an [Anthropic API key](https://www.anthropic.com/docs/api/reference).
- IBM watsonx.ai: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.
- Ollama: Use the [Ollama documentation](https://docs.ollama.com/) to set up your Ollama instance locally, in the cloud, or on a remote server, and then get your Ollama server's base URL.
You must have access to at least one language model and one embedding model.
If your chosen provider offers both types, you can use the same provider for both models.
If your provider offers only one type, such as Anthropic, you must select two providers.
- 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}
## Run the installer script {#install}
The script detects and installs uv, Docker/Podman, and Docker Compose prerequisites, then it installs and runs OpenRAG with `uvx`.
1. Create a directory to store your OpenRAG configuration file, and then change to that directory:
1. Create a directory to store your OpenRAG configuration files and data, and then change to that directory:
```bash
mkdir openrag-workspace
@ -71,6 +61,8 @@ The script detects and installs uv, Docker/Podman, and Docker Compose prerequisi
```
:::
The installer script installs OpenRAG with [`uvx`](https://docs.astral.sh/uv/guides/tools/#running-tools) in the directory where you run the script.
3. Wait while the installer script prepares your environment and installs OpenRAG.
You might be prompted to install certain dependencies if they aren't already present in your environment.
@ -79,9 +71,8 @@ Once the environment is ready, the OpenRAG Terminal User Interface (TUI) starts.
![OpenRAG TUI Interface](@site/static/img/OpenRAG_TUI_2025-09-10T13_04_11_757637.svg)
The installer script uses `uvx`, which creates a cached, ephemeral environment in your local `uv` cache.
Running the script in a specific directory, your OpenRAG configuration files and data are stored separately from the `uv` cache.
Clearing the cache doesn't delete your entire OpenRAG installation, only the TUI environment.
Because the installer script uses `uvx`, it creates a cached, ephemeral environment in your local `uv` cache, and your OpenRAG configuration files and data are stored separately from the `uv` cache.
Clearing the cache doesn't delete your entire OpenRAG installation, only the temporary TUI environment.
After clearing the cache, run `uvx openrag` to [access the TUI](/tui) and continue with your preserved configuration and data.
If you encounter errors during installation, see [Troubleshoot OpenRAG](/support/troubleshoot).
@ -218,6 +209,6 @@ The first time you start the OpenRAG application, you must complete application
## Next steps
* [Manage OpenRAG services](/manage-services)
* [Chat](/chat)
* [Upload documents](/ingestion)
* Try some of OpenRAG's core features in the [quickstart](/quickstart#chat-with-documents).
* Learn how to [manage OpenRAG services](/manage-services).
* [Upload documents](/ingestion), and then use the [**Chat**](/chat) to explore your data.

19
docs/docs/get-started/quickstart.mdx
View file

@ -6,29 +6,20 @@ slug: /quickstart
import Icon from "@site/src/components/icon/icon";
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import PartialWsl from '@site/docs/_partial-wsl-install.mdx';
import PartialIntegrateChat from '@site/docs/_partial-integrate-chat.mdx';
Use this quickstart to install OpenRAG, and then try some of OpenRAG's core features.
## Prerequisites
This quickstart requires the following:
- An [OpenAI API key](https://platform.openai.com/api-keys).
- Get an [OpenAI API key](https://platform.openai.com/api-keys).
This quickstart uses OpenAI for simplicity.
For other providers, see the complete [installation guide](/install).
For other providers, see the other [installation methods](/install-options).
- [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- Install [Python](https://www.python.org/downloads/release/python-3100/) version 3.13 or later.
- Microsoft Windows only: To run OpenRAG on Windows, you must use the Windows Subsystem for Linux (WSL).
<details>
<summary>Install WSL for OpenRAG</summary>
<PartialWsl />
</details>
- For Microsoft Windows, you must use the Windows Subsystem for Linux (WSL).
See [Install OpenRAG on Windows](/install-windows) before proceeding.
## Install OpenRAG