IBM watsonx.ai

pip install beekeeper-embeddings-watsonx
class WatsonxEmbedding

IBM watsonx embedding models.

Note

One of these parameters is required: project_id or space_id. Not both.

See https://cloud.ibm.com/apidocs/watsonx-ai#endpoint-url for the watsonx.ai API endpoints.

Parameters:

  • model_name (str) – IBM watsonx.ai model to be used. Defaults to ibm/slate-30m-english-rtrvr.

  • api_key (str) – watsonx API key.

  • url (str) – watsonx instance url.

  • truncate_input_tokens (str) – Maximum number of input tokens accepted. Defaults to 512

  • project_id (str, optional) – watsonx project_id.

  • space_id (str, optional) – watsonx space_id.

Example

from beekeeper.embeddings.watsonx import WatsonxEmbedding

watsonx_embedding = WatsonxEmbedding(
    api_key="your_api_key",
    url="your_instance_url",
    project_id="your_project_id",
)
get_documents_embedding(documents)

Compute embeddings for a list of documents.

Parameters:

documents (List[Document]) – List of documents to compute embeddings.

get_text_embedding(query)

Compute embedding for a single input text.

Parameters:

query (str) – Input query string to compute the embedding for.

Returns:

The embedding vector corresponding to the input query.

Return type:

List[float]

Example

embedded_query = watsonx_embedding.get_text_embedding(
    "Beekeeper is a data framework to load any data in one line of code and connect with AI applications."
)
get_texts_embedding(texts)

Compute embeddings for a list of texts.

Parameters:

texts (List[str]) – A list of input strings for which to compute embeddings.