Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
This article describes what Databricks recommends for batch inference.
Batch inference using a Spark DataFrame
See Perform batch inference using a Spark DataFrame for a step-by-step guide through the model inference workflow using Spark.
For deep learning model inference examples see the following articles:
Structured data extraction and batch inference using Spark UDF
The following example notebook demonstrates the development, logging, and evaluation of a simple agent for structured data extraction to transform raw, unstructured data into organized, useable information through automated extraction techniques. This approach demonstrates how to implement custom agents for batch inference using MLflow's PythonModel
class and employ the logged agent model as a Spark User-Defined Function (UDF). This notebook also shows how to leverage Mosaic AI Agent Evaluation to evaluate the accuracy using ground truth data.
Structured data extraction and batch inference using Spark UDF
:::