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

# Anaconda AI SDK Overview

export const GCell = ({children, className}) => <div className={`grid-table-cell ${className || ""}`} role="cell">
    {children}
  </div>;

export const GTH = ({children, className}) => <div className={`grid-table-th ${className || ""}`} role="columnheader">
    {children}
  </div>;

export const GRow = ({children}) => <div className="grid-table-row" role="row">{children}</div>;

export const GBody = ({children}) => <div className="grid-table-body" role="rowgroup">{children}</div>;

export const GHead = ({children}) => <div className="grid-table-head" role="rowgroup">{children}</div>;

export const GTable = ({children, className, cols}) => <div className={`grid-table not-prose overflow-hidden rounded-2xl ${className || ""}`} style={{
  "--grid-table-cols": cols
}} role="table">
    {children}
  </div>;

The Anaconda AI SDK provides a Python interface for managing models and inference servers. Use it to list and download quantized models, configure and launch API servers, and integrate directly into your application's workflows.

For installation and configuration, see [Getting started](/cli-reference/anaconda-ai/getting-started).

## Client initialization

```py theme={null}
from anaconda_ai import AnacondaAIClient
client = AnacondaAIClient()
```

### Common initialization parameters

The `AnacondaAIClient` constructor accepts several optional parameters. The most commonly used ones are:

```py theme={null}
client = AnacondaAIClient(
    backend='ai-catalyst',           # Backend to use
    site='my-site',                  # Site configuration for multi-site backends  
    stop_server_on_exit=False,       # Auto-stop servers on Python exit
    server_operations_timeout=120    # Timeout for server operations
)
```

**Key parameters:**

<GTable cols="30% 40% 30%">
  <GHead>
    <GRow>
      <GTH>Parameter</GTH>
      <GTH>Description</GTH>
      <GTH>Default</GTH>
    </GRow>
  </GHead>

  <GBody>
    <GRow>
      <GCell>`backend`</GCell>
      <GCell>Backend to use (`'ai-navigator'`, `'ai-catalyst'`, `'anaconda-desktop'`)</GCell>
      <GCell>Configured default</GCell>
    </GRow>

    <GRow>
      <GCell>`site`</GCell>
      <GCell>Site name for multi-site configurations (ai-catalyst only). See [site configuration](/cli-reference/anaconda-auth/getting-started#site-configuration)</GCell>
      <GCell>Configured default</GCell>
    </GRow>

    <GRow>
      <GCell>`stop_server_on_exit`</GCell>
      <GCell>Automatically stop servers started in this session when Python exits</GCell>
      <GCell>`True`</GCell>
    </GRow>

    <GRow>
      <GCell>`server_operations_timeout`</GCell>
      <GCell>Timeout in seconds for server start/stop operations</GCell>
      <GCell>`60`</GCell>
    </GRow>
  </GBody>
</GTable>

<Note>
  Additional parameters for authentication, SSL, and proxy configuration are available. See the [anaconda-auth documentation](/cli-reference/anaconda-auth/getting-started#global-options) for details.
</Note>

Initializing the client exposes:

<GTable cols="30% 70%">
  <GHead>
    <GRow>
      <GTH>Accessor</GTH>
      <GTH>Description</GTH>
    </GRow>
  </GHead>

  <GBody>
    <GRow>
      <GCell>[`.models`](/cli-reference/anaconda-ai/sdk/models)</GCell>
      <GCell>Model listing, metadata retrieval, and download</GCell>
    </GRow>

    <GRow>
      <GCell>[`.servers`](/cli-reference/anaconda-ai/sdk/servers)</GCell>
      <GCell>Server creation and control</GCell>
    </GRow>

    <GRow>
      <GCell>[`.vector_db`](/cli-reference/anaconda-ai/sdk/sdk-vectordb)</GCell>
      <GCell>Vector database management (ai-navigator and anaconda-desktop only)</GCell>
    </GRow>
  </GBody>
</GTable>