> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pyspur.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Install PySpur in under 2 minutes

## Setup Options

Choose the installation method that best suits your needs:

### Option A: Using `pyspur` Python Package

This is the quickest way to get started. Python 3.12 or higher is required.

<AccordionGroup>
  <Accordion icon="python" title="1. Install PySpur">
    ```sh theme={null}
    pip install pyspur
    ```
  </Accordion>

  <Accordion icon="folder" title="2. Initialize a new project">
    ```sh theme={null}
    pyspur init my-project
    cd my-project
    ```

    This will create a new directory with a `.env` file.
  </Accordion>

  <Accordion icon="play" title="3. Start the server">
    ```sh theme={null}
    pyspur serve --sqlite
    ```

    By default, this will start PySpur app at `http://localhost:6080` using a sqlite database.
    We recommend you configure a postgres instance URL in the `.env` file to get a more stable experience.
  </Accordion>

  <Accordion icon="gear" title="4. Customize Your Deployment">
    You can customize your PySpur deployment in two ways:

    a. **Through the app** (Recommended):

    * Navigate to the API Keys tab in the app
    * Add your API keys for various providers (OpenAI, Anthropic, etc.)
    * Changes take effect immediately

    b. **Manual Configuration**:

    * Edit the `.env` file in your project directory
    * It is recommended to configure a postgres database in .env for more reliability
    * Restart the app with `pyspur serve`. Add `--sqlite` if you are not using postgres
  </Accordion>
</AccordionGroup>

### Option B: Using Docker (Recommended for Scalable, In-Production Systems)

This is the recommended way for production deployments:

<AccordionGroup>
  <Accordion icon="docker" title="1. Install Docker">
    First, install Docker by following the official installation guide for your operating system:

    * [Docker for Linux](https://docs.docker.com/engine/install/)
    * [Docker Desktop for Mac](https://docs.docker.com/desktop/install/mac-install/)
  </Accordion>

  <Accordion icon="terminal" title="2. Create a PySpur Project">
    Once Docker is installed, create a new PySpur project with:

    ```sh theme={null}
    curl -fsSL https://raw.githubusercontent.com/PySpur-com/pyspur/main/start_pyspur_docker.sh | bash -s pyspur-project
    ```

    This will:

    * Start a new PySpur project in a new directory called `pyspur-project`
    * Set up the necessary configuration files
    * Start PySpur app automatically backed by a local postgres docker instance
  </Accordion>

  <Accordion icon="browser" title="3. Access PySpur">
    Go to `http://localhost:6080` in your browser.
  </Accordion>

  <Accordion icon="gear" title="4. Customize Your Deployment">
    You can customize your PySpur deployment in two ways:

    a. **Through the app** (Recommended):

    * Navigate to the API Keys tab in the app
    * Add your API keys for various providers (OpenAI, Anthropic, etc.)
    * Changes take effect immediately

    b. **Manual Configuration**:

    * Edit the `.env` file in your project directory
    * Restart the services with:
      ```sh theme={null}
      docker compose up -d
      ```
  </Accordion>
</AccordionGroup>

### Using Local Models with Ollama

<AccordionGroup>
  <Accordion icon="server" title="Configure Ollama">
    1. Start Ollama service with:

    ```sh theme={null}
    OLLAMA_HOST="0.0.0.0" ollama serve
    ```

    2. Update your `.env` file with:

    ```sh theme={null}
    OLLAMA_BASE_URL=http://host.docker.internal:11434
    ```

    3. Download models using: `ollama pull <model-name>`
    4. Select Ollama models from the sidebar for LLM nodes

    Note: PySpur only works with models that support structured-output and json mode. Most newer models should be good, but please confirm this from Ollama documentation for the model you wish to use.
  </Accordion>
</AccordionGroup>

## Next Steps

After installation, you can:

* 🪄 **Create New Workflow**
  Click "New Spur" to create a workflow from scratch
* 📋 **Use Templates**
  Start with one of our pre-built templates
* 💾 **Import Spur JSONs**
  Import spurs shared by other users
* 🌐 **Deploy as API**
  Single click using the "Deploy" button in the top bar

## Need Help?

<CardGroup>
  <Card title="Join Our Discord" icon="discord" href="https://discord.gg/7Spn7C8A5F">
    Connect with the community and get help
  </Card>

  <Card title="Talk to Creators" icon="calendar" href="https://calendly.com/d/cnf9-57m-bv3/pyspur-founders">
    Schedule a call with the PySpur team
  </Card>
</CardGroup>