mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-08-11 02:08:13 +00:00
901704b6c0
### Description Create a new structure for ingest content in the docs, update with all configs
102 lines
3.3 KiB
ReStructuredText
102 lines
3.3 KiB
ReStructuredText
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
|
|
-----------
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. code:: shell
|
|
|
|
unstructured-ingest \
|
|
local \
|
|
--input-path example-docs \
|
|
--output-dir local-ingest-output \
|
|
--num-processes 2 \
|
|
--recursive \
|
|
--verbose \
|
|
|
|
.. tab:: Python
|
|
|
|
.. code:: python
|
|
|
|
import os
|
|
|
|
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"),
|
|
),
|
|
)
|
|
runner.run(
|
|
input_path="example-docs",
|
|
recursive=True,
|
|
)
|
|
|
|
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
|
|
|
|
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>"
|
|
|
|
.. tab:: Python
|
|
|
|
.. code:: python
|
|
|
|
import os
|
|
|
|
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"),
|
|
),
|
|
)
|
|
runner.run(
|
|
input_path="example-docs",
|
|
recursive=True,
|
|
)
|
|
|
|
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 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 <https://unstructured-io.github.io/unstructured/installing.html>`_.
|