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

# Themes

<Warning>
  We are sunsetting our SDKs and will no longer add new features, security patches, bug fixes, or technical support for them. To access the latest capabilities and ongoing improvements, we encourage you to migrate to our [RESTful API](/api-rest/introduction).

  SDK support will officially end on **December 31, 2026**. On this date, the underlying endpoints used by the SDKs and related documentation will be decommissioned.

  To avoid any disruption to your services, please ensure your migration is complete by that date.

  For migration assistance, please contact us at [support@bigdata.com](mailto:support@bigdata.com).
</Warning>

## ThemeTree

A hierarchical tree structure rooted in a main theme, branching into distinct sub-themes that guide the analyst's research process.

**Parameters**

* `label` (str): The name of the theme or sub-theme.
* `node` (int): A unique identifier for the node.
* `summary` (str, optional): A brief explanation of the node’s relevance.
* `children` (Optional\[List\[ThemeTree]]): A list of child nodes representing sub-themes.
* `keywords` (Optional\[List\[str]]): A list of keywords summarizing the main theme.

**Key Methods**

* `from_dict(tree_dict)`: Create a ThemeTree object from a dictionary.
* `as_string(prefix="")`: Convert the tree into a string.
* `get_label_summaries()`: Extract all label summaries from the tree.
* `get_summaries()`: Extract all node summaries from the tree.
* `get_terminal_label_summaries()`: Extract label/summary pairs from terminal nodes.
* `get_terminal_labels()`: Extract terminal node labels.
* `get_terminal_summaries()`: Extract summaries from terminal nodes.
* `print(prefix="")`: Print the tree.
* `visualize(engine="graphviz")`: Visualize the tree as a mind map (requires `graphviz` or `plotly`).
* `get_label_to_parent_mapping()`: Map each leaf node label to its parent.
* `save_json(filepath)`: Save the ThemeTree as a JSON file.

**Example**

```python theme={null}
from bigdata_research_tools.themes import ThemeTree

tree = ThemeTree(
    label="AI",
    node=0,
    summary="Artificial Intelligence and its applications.",
    children=[],
    keywords=["machine learning", "automation"]
)
print(tree.as_string())
```

***

## generate\_theme\_tree

Generate a `ThemeTree` from a main theme and (optionally) a focus.

**Parameters**

* `main_theme` (str): The primary theme to analyze.
* `focus` (str, optional): Specific aspect(s) to guide sub-theme generation.
* `llm_model_config` (dict, optional): Configuration for the LLM used to generate themes.

**Returns**

* `ThemeTree`: The generated theme tree.

**Example**

```python theme={null}
from bigdata_research_tools.themes import generate_theme_tree

tree = generate_theme_tree(main_theme="AI", focus="healthcare")
tree.print()
```

***

## stringify\_label\_summaries

Convert the label summaries of a ThemeTree into a list of strings.

**Parameters**

* `label_summaries` (dict): Dictionary of label summaries from a ThemeTree.

**Returns**

* `List[str]`: List of strings, each containing a label and its summary.

**Example**

```python theme={null}
from bigdata_research_tools.themes import stringify_label_summaries

summaries = tree.get_label_summaries()
summary_strings = stringify_label_summaries(summaries)
for s in summary_strings:
    print(s)
```