mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-12 11:35:53 +00:00
901704b6c0
### Description Create a new structure for ingest content in the docs, update with all configs
105 lines
3.3 KiB
ReStructuredText
105 lines
3.3 KiB
ReStructuredText
Github
|
|
==========
|
|
Connect Github 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 Github dependencies as shown here.
|
|
|
|
.. code:: shell
|
|
|
|
pip install "unstructured[github]"
|
|
|
|
Run Locally
|
|
-----------
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. code:: shell
|
|
|
|
unstructured-ingest \
|
|
github \
|
|
--url Unstructured-IO/unstructured \
|
|
--git-branch main \
|
|
--output-dir github-ingest-output \
|
|
--num-processes 2 \
|
|
--verbose
|
|
|
|
.. tab:: Python
|
|
|
|
.. code:: python
|
|
|
|
import os
|
|
|
|
from unstructured.ingest.interfaces import PartitionConfig, ProcessorConfig, ReadConfig
|
|
from unstructured.ingest.runner import GithubRunner
|
|
|
|
if __name__ == "__main__":
|
|
runner = GithubRunner(
|
|
processor_config=ProcessorConfig(
|
|
verbose=True,
|
|
output_dir="github-ingest-output",
|
|
num_processes=2,
|
|
),
|
|
read_config=ReadConfig(),
|
|
partition_config=PartitionConfig(),
|
|
)
|
|
runner.run(
|
|
url="Unstructured-IO/unstructured",
|
|
git_branch="main",
|
|
)
|
|
|
|
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 \
|
|
github \
|
|
--url Unstructured-IO/unstructured \
|
|
--git-branch main \
|
|
--output-dir github-ingest-output \
|
|
--num-processes 2 \
|
|
--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 GithubRunner
|
|
|
|
if __name__ == "__main__":
|
|
runner = GithubRunner(
|
|
processor_config=ProcessorConfig(
|
|
verbose=True,
|
|
output_dir="github-ingest-output",
|
|
num_processes=2,
|
|
),
|
|
read_config=ReadConfig(),
|
|
partition_config=PartitionConfig(
|
|
partition_by_api=True,
|
|
api_key=os.getenv("UNSTRUCTURED_API_KEY"),
|
|
),
|
|
)
|
|
runner.run(
|
|
url="Unstructured-IO/unstructured",
|
|
git_branch="main",
|
|
)
|
|
|
|
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 github --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>`_.
|