mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-08-17 21:29:05 +00:00
901704b6c0
### Description Create a new structure for ingest content in the docs, update with all configs
106 lines
3.3 KiB
ReStructuredText
106 lines
3.3 KiB
ReStructuredText
Azure
|
|
==========
|
|
Connect Azure to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem.
|
|
|
|
First you'll need to install the Azure dependencies as shown here.
|
|
|
|
.. code:: shell
|
|
|
|
pip install "unstructured[azure]"
|
|
|
|
Run Locally
|
|
-----------
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. code:: shell
|
|
|
|
unstructured-ingest \
|
|
azure \
|
|
--remote-url abfs://container1/ \
|
|
--account-name azureunstructured1 \
|
|
--output-dir azure-ingest-output \
|
|
--num-processes 2
|
|
|
|
.. tab:: Python
|
|
|
|
.. code:: python
|
|
|
|
import os
|
|
|
|
from unstructured.ingest.interfaces import (
|
|
FsspecConfig,
|
|
PartitionConfig,
|
|
ProcessorConfig,
|
|
ReadConfig,
|
|
)
|
|
from unstructured.ingest.runner import AzureRunner
|
|
|
|
if __name__ == "__main__":
|
|
runner = AzureRunner(
|
|
processor_config=ProcessorConfig(
|
|
verbose=True,
|
|
output_dir="azure-ingest-output",
|
|
num_processes=2,
|
|
),
|
|
read_config=ReadConfig(),
|
|
partition_config=PartitionConfig(),
|
|
fsspec_config=FsspecConfig(
|
|
remote_url="abfs://container1/",
|
|
),
|
|
)
|
|
runner.run(
|
|
account_name="azureunstructured1",
|
|
)
|
|
|
|
|
|
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``.
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. code:: shell
|
|
|
|
import os
|
|
|
|
from unstructured.ingest.interfaces import (
|
|
FsspecConfig,
|
|
PartitionConfig,
|
|
ProcessorConfig,
|
|
ReadConfig,
|
|
)
|
|
from unstructured.ingest.runner import AzureRunner
|
|
|
|
if __name__ == "__main__":
|
|
runner = AzureRunner(
|
|
processor_config=ProcessorConfig(
|
|
verbose=True,
|
|
output_dir="azure-ingest-output",
|
|
num_processes=2,
|
|
),
|
|
read_config=ReadConfig(),
|
|
partition_config=PartitionConfig(
|
|
partition_by_api=True,
|
|
api_key=os.getenv("UNSTRUCTURED_API_KEY"),
|
|
),
|
|
fsspec_config=FsspecConfig(
|
|
remote_url="abfs://container1/",
|
|
),
|
|
)
|
|
runner.run(
|
|
account_name="azureunstructured1",
|
|
)
|
|
|
|
|
|
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 <https://github.com/Unstructured-IO/unstructured-api>`_.
|
|
|
|
For a full list of the options the CLI accepts check ``unstructured-ingest azure --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 <https://unstructured-io.github.io/unstructured/installing.html>`_.
|