Databricks Volumes

Batch process all your records using unstructured-ingest to store structured outputs locally on your filesystem and upload those local files to a Databricks Volume.

First you’ll need to install the Databricks Volume dependencies as shown here.

pip install "unstructured[databricks-volumes]"

Run Locally

The upstream connector can be any of the ones supported, but for convenience here, showing a sample command using the upstream local connector.

Shell

#!/usr/bin/env bash

unstructured-ingest \
  local \
  --input-path example-docs/book-war-and-peace-1p.txt \
  --output-dir local-to-databricks-volume \
  --strategy fast \
  --chunk-elements \
  --embedding-provider "<unstructured embedding provider, ie. langchain-huggingface>" \
  --num-processes 2 \
  --verbose \
  --work-dir "<directory for intermediate outputs to be saved>" \
  databricks-volumes \
  --host "$DATABRICKS_HOST" \
  --username "$DATABRICKS_USERNAME" \
  --password "$DATABRICKS_PASSWORD" \
  --volume "$DATABRICKS_VOLUME" \
  --catalog "$DATABRICKS_CATALOG"

For a full list of the options the CLI accepts check unstructured-ingest <upstream connector> databricks-volumes --help.

NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you’re running this locally. You can find more information about this in the installation guide.