> For the complete documentation index, see [llms.txt](https://ai.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai.ortusbooks.com/getting-started/configuration.md).

# Configuration

The bx-ai settings you will actually use, on one page.

Settings live in `boxlang.json` under `modules.bxai.settings`. Every setting has a default, so set only what you need. Your values are merged over the defaults.

```json
{
  "modules": {
    "bxai": {
      "settings": {
        "provider": "openai",
        "defaultParams": { "model": "gpt-4.1", "temperature": 0.7 }
      }
    }
  }
}
```

## The basics

| Setting         | Default    | What it does                                                     |
| --------------- | ---------- | ---------------------------------------------------------------- |
| `provider`      | `"openai"` | Provider used when a call does not name one                      |
| `apiKey`        | `""`       | Key for `provider`. Prefer the `<PROVIDER>_API_KEY` env var      |
| `defaultParams` | `{}`       | Request params for every call, such as `model` and `temperature` |
| `timeout`       | `90`       | Request timeout in seconds                                       |
| `returnFormat`  | `"single"` | What `aiChat()` returns: `single`, `all`, `raw`, `json` or `xml` |

## Providers

Give a provider its own `params` and `options`. They apply whenever that provider is used:

```json
"providers": {
  "openai": { "params": { "model": "gpt-4.1" } },
  "ollama": { "params": { "model": "qwen3:0.6b" }, "options": { "baseURL": "http://my-server:11434" } }
}
```

## Profiles

A profile is a named combination of provider, model, params, options and key. Use it when you switch between setups, such as a `fast` model and a `planner` model:

```json
"profiles": {
  "fast":    { "description": "Cheap and quick", "provider": "openai", "model": "gpt-4.1-mini", "params": { "temperature": 0 }, "apiKeyEnv": "OPENAI_API_KEY" },
  "planner": { "provider": "claude", "model": "claude-opus-5-5", "params": { "max_tokens": 8192 }, "apiKeyEnv": "CLAUDE_API_KEY" }
}
```

```javascript
aiChat( "Summarize this", {}, { profile: "fast" } )
```

See [Profiles](/main-components/profiles.md) for agents, switching and listing.

## Embeddings

`aiEmbed()` uses your chat provider unless you say otherwise:

```json
"embeddings": { "defaultProvider": "openai", "defaultModel": "text-embedding-3-small" }
```

## Logging

| Setting                                        | Default | What it does                                            |
| ---------------------------------------------- | ------- | ------------------------------------------------------- |
| `logRequest` / `logResponse`                   | `false` | Write requests or responses to `ai.log`                 |
| `logRequestToConsole` / `logResponseToConsole` | `false` | Print them to the console. Best way to debug a provider |

## Everything else

You can leave these alone until you need them.

| Setting                             | Learn more                                                                                                                                                                            |
| ----------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `memory`                            | [Memory](/main-components/memory.md)                                                                                                                                                  |
| `audio`                             | [Audio](/main-components/audio.md)                                                                                                                                                    |
| `image`                             | [Image generation](/main-components/image-generation.md)                                                                                                                              |
| `security`                          | [Security](/advanced/security.md)                                                                                                                                                     |
| `webSearch`                         | [Web search](/main-components/web-search.md)                                                                                                                                          |
| `mcp`                               | [MCP stdio clients](/model-context-protocol-mcp/client/stdio.md), [MCP server rate limiting](/model-context-protocol-mcp/server/rate-limiting.md#module-settings) and trusted proxies |
| `skillsDirectory`, `autoLoadSkills` | [Skills](/main-components/skills.md)                                                                                                                                                  |
| `gateways`                          | [Gateways](/main-components/gateways.md)                                                                                                                                              |
| `hitl`                              | [Human-in-the-Loop](/main-components/human-in-the-loop.md)                                                                                                                            |

## API keys

1. Set `<PROVIDER>_API_KEY` in the environment, for example `OPENAI_API_KEY`. This is the default way and needs no setting.
2. For a profile, set `apiKeyEnv` to the **name** of the variable. The profile never stores the key.
3. Pass `apiKey` in the call options to override everything else.

## Override per call

A call always wins over settings:

```javascript
aiChat( "Hello", { temperature: 0 }, { provider: "claude", timeout: 120 } )
```

The order, lowest to highest: `defaultParams`, the provider's `params`, the profile, the params of the call.

Full provider walkthroughs are in [Provider Setup](/getting-started/installation/provider-setup.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://ai.ortusbooks.com/getting-started/configuration.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.