> For the complete documentation index, see [llms.txt](https://docs.interactive.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.interactive.ai/sdk/variables.md).

# Variables

## Overview

Variables are structured prompts that define persistent variables for agent sessions. Each variable specifies a name, data type, persistence scope, and default value.

Variables are stored as text prompts on the platform. The SDK parses the YAML or JSON content into typed Python objects.

***

## Convenience methods

These methods automatically apply the folder prefix and `type="variable"`, so you don't have to.

## `get_variable` [(source)](https://github.com/interactive-ai/interactiveai-python-sdk/blob/main/interactiveai/_client/client.py#L3632)

Get a variable prompt by name.

Automatically prefixes the name with `variables/` and sets `type="variable"`.

```python
get_variable(
    name: str,
    *,
    version: int | None = None,
    label: str | None = None,
    cache_ttl_seconds: int | None = None,
    fallback: str | None = None,
    max_retries: int | None = None,
    fetch_timeout_seconds: int | None = None,
) -> VariablePromptClient
```

**Parameters**

* `name` — Variable name (without the `variables/` prefix).
* `version` — Optional version number.
* `label` — Optional label filter.
* `cache_ttl_seconds` — Cache TTL override.
* `fallback` — Fallback YAML/JSON content string.
* `max_retries` — Maximum number of retries.
* `fetch_timeout_seconds` — Fetch timeout override.

**Returns**

VariablePromptClient

***

## `create_variable` [(source)](https://github.com/interactive-ai/interactiveai-python-sdk/blob/main/interactiveai/_client/client.py#L3670)

Create a variable prompt.

Automatically prefixes the name with `variables/` and sets `type="variable"`.

```python
create_variable(
    *,
    name: str,
    prompt: str,
    labels: List[str] | None = None,
    tags: List[str] | None = None,
    config: Any | None = None,
    commit_message: str | None = None,
) -> VariablePromptClient
```

**Parameters**

* `name` — Variable name (without the `variables/` prefix).
* `prompt` — JSON content string.
* `labels` — Labels to assign.
* `tags` — Tags to assign.
* `config` — Additional config dict.
* `commit_message` — Optional commit message.

**Returns**

VariablePromptClient

***

## `update_variable` [(source)](https://github.com/interactive-ai/interactiveai-python-sdk/blob/main/interactiveai/_client/client.py#L3705)

Update a variable prompt version.

Automatically sets `type="variable"` and routes through the type-specific endpoint.

```python
update_variable(
    *,
    name: str,
    version: int,
    new_labels: List[str] | None = None,
) -> Any
```

**Parameters**

* `name` — Variable name (without the `variables/` prefix).
* `version` — The version number of the prompt to update.
* `new_labels` — New labels to assign to the prompt version.

**Returns**

The updated prompt from the InteractiveAI API.

***

## `list_variables` [(source)](https://github.com/interactive-ai/interactiveai-python-sdk/blob/main/interactiveai/_client/client.py#L3729)

List variable prompts.

```python
list_variables(
    *,
    label: str | None = None,
    tag: str | None = None,
    page: int | None = None,
    limit: int | None = None,
) -> PromptMetaListResponse
```

**Parameters**

* `label` — Optional label filter.
* `tag` — Optional tag filter.
* `page` — Page number.
* `limit` — Items per page.

**Returns**

PromptMetaListResponse

***

## `delete_variable` [(source)](https://github.com/interactive-ai/interactiveai-python-sdk/blob/main/interactiveai/_client/client.py#L3752)

Delete a variable prompt.

Automatically prefixes the name with `variables/`.

```python
delete_variable(
    name: str,
    *,
    label: str | None = None,
    version: int | None = None,
) -> None
```

**Parameters**

* `name` — Variable name (without the `variables/` prefix).
* `label` — If set, deletes versions carrying this label.
* `version` — If set, deletes only this specific version.

***

## Fetching variables

```python
variables = client.get_variable("session-state")

for v in variables.entries:
    print(v.name, v.type, v.default_value)
```

***

## Creating variables

```python
content = """
{
  "variables": [
    {
      "name": "is_authenticated",
      "type": "boolean",
      "persistence": "customer",
      "default_value": false
    },
    {
      "name": "subscription_plan",
      "type": "string",
      "persistence": "customer",
      "default_value": "guest"
    }
  ]
}
"""

variables = client.create_variable(
    name="session-state",
    prompt=content,
    labels=["production"],
)
```

The SDK validates the YAML structure on create and raises `ValueError` if the content is malformed.

***

## `VariablePromptClient`

Returned by `get_variable()` and `create_variable()`.

**Attributes**

* `name` — Prompt name.
* `version` — Prompt version number.
* `labels` — List of labels (e.g. `["production"]`).
* `tags` — List of tags.
* `config` — Arbitrary config dict stored with the prompt.
* `is_fallback` — `True` if this was returned from a fallback value.
* `raw_content` — The original unparsed text content.
* `entries` — `List[VariableEntry]` (property).

**Methods**

* `compile()` — Returns the parsed `VariablesContent` dataclass. Template variable substitution does not apply to structured prompts.
* `variables` — Always returns an empty list.

***

## `VariableEntry`

Dataclass representing a single variable definition.

| Field           | Type            | Description                                            |
| --------------- | --------------- | ------------------------------------------------------ |
| `name`          | `str`           | Variable name (e.g. `"is_authenticated"`).             |
| `type`          | `str`           | Data type (`"boolean"`, `"string"`, `"number"`, etc.). |
| `persistence`   | `Optional[str]` | Persistence scope (`"customer"`, `"session"`, etc.).   |
| `default_value` | `Any`           | Default value for the variable.                        |

***

## Content format

Variables can be authored in YAML or JSON. JSON is recommended for readability.

```json
{
  "variables": [
    {
      "name": "is_authenticated",
      "type": "boolean",
      "persistence": "customer",
      "default_value": false
    },
    {
      "name": "language",
      "type": "string",
      "persistence": "session",
      "default_value": "en"
    }
  ]
}
```


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.interactive.ai/sdk/variables.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.