watsonx.ai

WatsonxEmbedding #

Bases: BaseEmbedding

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.

Attributes:

Name	Type	Description
`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`	watsonx project_id.
`space_id`	`str`	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",
)

embed_documents #

embed_documents(documents: list[Document]) -> list[Document]

Embed a list of documents and assign the computed embeddings to the 'embedding' attribute.

Parameters:

Name	Type	Description	Default
`documents`	`list[Document]`	List of documents to compute embeddings.	required

embed_text #

embed_text(input: str | list[str]) -> list[Embedding]

Embed one or more text strings.

Parameters:

Name	Type	Description	Default
`input`	`str \| list[str]`	Input for which to compute embeddings.	required