Local

Connect local files to your preprocessing pipeline, and batch process all your documents using unstructured-ingest to store structured outputs locally on your filesystem.

Run Locally

Shell

#!/usr/bin/env bash

unstructured-ingest \
  local \
  --input-path example-docs \
  --output-dir local-ingest-output \
  --num-processes 2 \
  --recursive \
  --verbose

from unstructured.ingest.connector.local import SimpleLocalConfig
from unstructured.ingest.interfaces import PartitionConfig, ProcessorConfig, ReadConfig
from unstructured.ingest.runner import LocalRunner

if __name__ == "__main__":
    runner = LocalRunner(
        processor_config=ProcessorConfig(
            verbose=True,
            output_dir="local-ingest-output",
            num_processes=2,
        ),
        read_config=ReadConfig(),
        partition_config=PartitionConfig(),
        connector_config=SimpleLocalConfig(
            input_path="example-docs",
            recursive=True,
        ),
    )
    runner.run()

Run via the API

You can also use upstream connectors with the unstructured API. For this you’ll need to use the --partition-by-api flag and pass in your API key with --api-key.

Shell

#!/usr/bin/env bash

unstructured-ingest \
  local \
  --input-path example-docs \
  --output-dir local-ingest-output \
  --num-processes 2 \
  --recursive \
  --verbose \
  --partition-by-api \
  --api-key "$UNSTRUCTURED_API_KEY"

import os

from unstructured.ingest.connector.local import SimpleLocalConfig
from unstructured.ingest.interfaces import PartitionConfig, ProcessorConfig, ReadConfig
from unstructured.ingest.runner import LocalRunner

if __name__ == "__main__":
    runner = LocalRunner(
        processor_config=ProcessorConfig(
            verbose=True,
            output_dir="local-ingest-output",
            num_processes=2,
        ),
        read_config=ReadConfig(),
        partition_config=PartitionConfig(
            partition_by_api=True,
            api_key=os.getenv("UNSTRUCTURED_API_KEY"),
        ),
        connector_config=SimpleLocalConfig(
            input_path="example-docs",
            recursive=True,
        ),
    )
    runner.run()

Additionally, you will need to pass the --partition-endpoint if you’re running the API locally. You can find more information about the unstructured API here.

For a full list of the options the CLI accepts check unstructured-ingest local --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.