> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/guardrails/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# nemoguardrails.embeddings.index

## Module Contents

### Classes

| Name                                                                  | Description                                                                          |
| --------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
| [`EmbeddingsIndex`](#nemoguardrails-embeddings-index-EmbeddingsIndex) | The embeddings index is responsible for computing and searching a set of embeddings. |
| [`IndexItem`](#nemoguardrails-embeddings-index-IndexItem)             | -                                                                                    |

### API

```python
class nemoguardrails.embeddings.index.EmbeddingsIndex()
```

The embeddings index is responsible for computing and searching a set of embeddings.

```python
nemoguardrails.embeddings.index.EmbeddingsIndex._get_embeddings(
    texts: typing.List[str]
)
```

async

```python
nemoguardrails.embeddings.index.EmbeddingsIndex.add_item(
    item: nemoguardrails.embeddings.index.IndexItem
)
```

async

Adds a new item to the index.

```python
nemoguardrails.embeddings.index.EmbeddingsIndex.add_items(
    items: typing.List[nemoguardrails.embeddings.index.IndexItem]
)
```

async

Adds multiple items to the index.

```python
nemoguardrails.embeddings.index.EmbeddingsIndex.build()
```

async

Build the index, after the items are added.

This is optional, might not be needed for all implementations.

```python
nemoguardrails.embeddings.index.EmbeddingsIndex.search(
    text: str,
    max_results: int,
    threshold: typing.Optional[float]
) -> typing.List[nemoguardrails.embeddings.index.IndexItem]
```

async

Searches the index for the closest matches to the provided text.

```python
class nemoguardrails.embeddings.index.IndexItem(
    text: str,
    meta: typing.Dict = dict()
)
```

Dataclass