PALModelEmbeddings

class hana_ai.vectorstore.embedding_service.PALModelEmbeddings(connection_context, model_version=None, batch_size=None, thread_number=None, is_query=None)

PAL embedding model.

Parameters:

connection_contextConnectionContext

Connection context.

model_versionstr, optional

Model version. Default to None.

batch_sizeint, optional

Batch size. Default to None.

thread_numberint, optional

Thread number. Default to None.

is_querybool, optional

Use different embedding model for query purpose. Default to None.

Methods

__call__(input)	Call self as a function.
aembed_documents(texts)	Asynchronous Embed search docs.
aembed_query(text)	Asynchronous Embed query text.
embed_documents(texts)	Embed multiple documents.
embed_query(text)	Embed a single query.
get_text_embedding_batch(texts[, show_progress])	Get text embedding batch.

embed_documents(texts: List[str]) → List[List[float]]

Embed multiple documents.

Parameters:

textsList[str]

List of texts.

Returns:

List[List[float]]

List of embeddings.

embed_query(text: str) → List[float]

Embed a single query.

Parameters:

textstr

Text.

Returns:

List[float]

Embedding.

get_text_embedding_batch(texts: List[str], show_progress=False, **kwargs)

Get text embedding batch.

Parameters:

textsList[str]

List of texts.

Returns:

List[List[float]]

List of embeddings.

async aembed_documents(texts: list[str]) → list[list[float]]

Asynchronous Embed search docs.

Args:

texts: List of text to embed.

Returns:

List of embeddings.

async aembed_query(text: str) → list[float]

Asynchronous Embed query text.

Args:

text: Text to embed.

Returns:

Embedding.