embed_databricks: Embed text using a Databricks model

In ragnar: Retrieval-Augmented Generation (RAG) Workflows

Embed text using a Databricks model

Description

embed_databricks() gets embeddings for text using a model hosted in a Databricks workspace. It relies on the ellmer package for managing Databricks credentials. See ellmer::chat_databricks for more on supported modes of authentication.

Usage

embed_databricks(
  x,
  workspace = databricks_workspace(),
  model = "databricks-bge-large-en",
  batch_size = 512L
)

Arguments

x	x can be: A character vector, in which case a matrix of embeddings is returned. A data frame with a column named text, in which case the dataframe is returned with an additional column named embedding. Missing or NULL, in which case a function is returned that can be called to get embeddings. This is a convenient way to partial in additional arguments like model, and is the most convenient way to produce a function that can be passed to the embed argument of ragnar_store_create().
workspace	The URL of a Databricks workspace, e.g. "https://example.cloud.databricks.com". Will use the value of the environment variable DATABRICKS_HOST, if set.
model	The name of a text embedding model.
batch_size	split x into batches when embedding. Integer, limit of strings to include in a single request.

ragnar documentation built on Aug. 8, 2025, 7:07 p.m.