Azure

This page was recently updated. What do you think about it? Let us know!.

Connect Azure Storage to your preprocessing pipeline, and use the Unstructured Ingest CLI or the Unstructured Ingest Python library to batch process all your documents and store structured outputs locally on your filesystem.

The requirements are as follows.

The following video shows how to fulfill the minimum set of Azure Storage account requirements:

If you are generating an SAS token as shown in the preceding video, be sure to set the following permissions:

• Read and List for reading from the container only.
• Write and List for writing to the container only.
• Read, Write, and List for both reading from and writing to the container.

Here are some more details about these requirements:

• An Azure account. To create one, learn how.

• An Azure Storage account, and a container within that account. Create a storage account. Create a container.

• The Azure Storage remote URL, using the format az://<container-name>/<path/to/file/or/folder/in/container/as/needed>

  For example, if your container is named my-container, and there is a folder in the container named my-folder, the Azure Storage remote URL would be az://my-container/my-folder/.

• An SAS token (recommended), access key, or connection string for the Azure Storage account. Create an SAS token (recommended). Get an access key. Get a connection string.

  Create an SAS token (recommended):

  Get an access key or connection string:

The Azure Storage account connector dependencies:

CLI, Python

pip install "unstructured-ingest[azure]"

You might also need to install additional dependencies, depending on your needs. Learn more.

These environment variables:

• AZURE_STORAGE_REMOTE_URL - The Azure Storage remote URL, represented by --remote-url (CLI) or remote_url (Python).

  The remote URL takes the format az://<container-name>/<path/to/file/or/folder/in/container/as/needed>

  For example, if your container is named my-container, and there is a folder in the container named my-folder, the Azure Storage remote URL would be az://my-container/my-folder/.

• AZURE_STORAGE_ACCOUNT_NAME - The name of the Azure Storage account, represented by --account-name (CLI) or account_name (Python).

• AZURE_STORAGE_ACCOUNT_KEY, AZURE_STORAGE_CONNECTION_STRING, or AZURE_STORAGE_SAS_TOKEN - The name of the key, connection string, or SAS token for the Azure Storage account, depending on your security configuration, represented by --account-key (CLI) or account_key (Python), --connection-string (CLI) or connection_string (Python), and --sas_token (CLI) or sas_token (Python), respectively.

Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector.

This example sends data to Unstructured for processing by default. To process data locally instead, see the instructions at the end of this page.

CLI

#!/usr/bin/env bash

# Chunking and embedding are optional.

unstructured-ingest \
  azure \
    --remote-url $AZURE_STORAGE_REMOTE_URL \
    --account-name $AZURE_STORAGE_ACCOUNT_NAME \
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --strategy hi_res \
    --chunking-strategy by_title \
    --embedding-provider huggingface \
    --additional-partition-args="{\"split_pdf_page\":\"true\", \"split_pdf_allow_failed\":\"true\", \"split_pdf_concurrency_level\": 15}" \
  local \
    --output-dir $LOCAL_FILE_OUTPUT_DIR

For the Unstructured Ingest CLI and the Unstructured Ingest Python library, you can use the --partition-by-api option (CLI) or partition_by_api (Python) parameter to specify where files are processed:

• To do local file processing, omit --partition-by-api (CLI) or partition_by_api (Python), or explicitly specify partition_by_api=False (Python).

  Local file processing does not use an Unstructured API key or API URL, so you can also omit the following, if they appear:

  • --api-key $UNSTRUCTURED_API_KEY (CLI) or api_key=os.getenv("UNSTRUCTURED_API_KEY") (Python)
  • --partition-endpoint $UNSTRUCTURED_API_URL (CLI) or partition_endpoint=os.getenv("UNSTRUCTURED_API_URL") (Python)
  • The environment variables UNSTRUCTURED_API_KEY and UNSTRUCTURED_API_URL

• To send files to the Unstructured Partition Endpoint for processing, specify --partition-by-api (CLI) or partition_by_api=True (Python).

  Unstructured also requires an Unstructured API key and API URL, by adding the following:

  • --api-key $UNSTRUCTURED_API_KEY (CLI) or api_key=os.getenv("UNSTRUCTURED_API_KEY") (Python)
  • --partition-endpoint $UNSTRUCTURED_API_URL (CLI) or partition_endpoint=os.getenv("UNSTRUCTURED_API_URL") (Python)
  • The environment variables UNSTRUCTURED_API_KEY and UNSTRUCTURED_API_URL, representing your API key and API URL, respectively.
  You must specify the API URL only if you are not using the default API URL for Unstructured Ingest, for example, if you are using a self-hosted instance of the Unstructured API.

  The default API URL for Unstructured Ingest is https://api.unstructuredapp.io/general/v0/general, which is the API URL for the Unstructured Partition Endpoint.

  If you do not have an API key, get one now.

  If the Unstructured API is self-hosted, the process for generating Unstructured API keys, and the Unstructured API URL that you use, are different. For details, contact Unstructured Sales at [e-mail].