nemoguardrails.embeddings.index

Module Contents

Classes

Name	Description
`EmbeddingsIndex`	The embeddings index is responsible for computing and searching a set of embeddings.
`IndexItem`	-

API

class nemoguardrails.embeddings.index.EmbeddingsIndex()

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

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

async

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

async

Adds a new item to the index.

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

async

Adds multiple items to the index.

nemoguardrails.embeddings.index.EmbeddingsIndex.build()

async

Build the index, after the items are added.

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

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.

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

Dataclass