em3ndez/unstructured-python-client: A Python client for the Unstructured hosted API · GitHub

This is a Python client for the Unstructured API.

pip install unstructured-client

Only the files parameter is required.

from unstructured_client import UnstructuredClient
from unstructured_client.models import shared
from unstructured_client.models.errors import SDKError

s = UnstructuredClient(api_key_auth="YOUR_API_KEY")

filename = "_sample_docs/layout-parser-paper-fast.pdf"

with open(filename, "rb") as f:
    # Note that this currently only supports a single file
    files=shared.Files(
        content=f.read(),
        file_name=filename,
	)

req = shared.PartitionParameters(
    files=files,
    # Other partition params
    strategy='ocr_only',
    languages=["eng"],
)

try:
    resp = s.general.partition(req)
    print(resp.elements[0])
except SDKError as e:
    print(e)

Result:

{
'type': 'UncategorizedText',
'element_id': 'fc550084fda1e008e07a0356894f5816',
'metadata': {
  'filename': 'layout-parser-paper-fast.pdf',
  'filetype': 'application/pdf',
  'languages': ['eng'],
  'page_number': 1
  }
}

If you are self hosting the API, or developing locally, you can change the server URL when setting up the client.

# Using a local server
s = unstructured_client.UnstructuredClient(
    server_url="http://localhost:8000",
    api_key_auth=api_key,
)

# Using your own server
s = unstructured_client.UnstructuredClient(
    server_url="https://your-server",
    api_key_auth=api_key,
)

See the general partition page for all available parameters. 

In order to speed up processing of long PDF files, split_pdf_page can be set to True (defaults to False). It will cause the PDF to be split at client side, before sending to API, and combining individual responses as single result. This parameter will affect only PDF files, no need to disable it for other filetypes.

Warning: this feature causes the parent_id metadata generation in elements to be disabled, as that requires having context of multiple pages.

The amount of workers utilized for splitting PDFs is dictated by the split_pdf_concurrency_level parameter, with a default of 5 and a maximum of 15 to keep resource usage and costs in check. The splitting process leverages asyncio to manage concurrency effectively. The size of each batch of pages (ranging from 2 to 20) is internally determined based on the concurrency level and the total number of pages in the document. Because the splitting process uses asyncio the client can encouter event loop issues if it is nested in another async runner, like running in a gevent spawned task. Instead, this is safe to run in multiprocessing workers (e.g., using multiprocessing.Pool with fork context).

Example:

req = shared.PartitionParameters(
    files=files,
    strategy="fast",
    languages=["eng"],
    split_pdf_page=True,
    split_pdf_concurrency_level=8
)

The Python SDK makes API calls using the requests HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with a custom requests.Session object.

For example, you could specify a header for every request that this sdk makes as follows:

import unstructured_client
import requests

http_client = requests.Session()
http_client.headers.update({'x-custom-header': 'someValue'})
s = unstructured_client.UnstructuredClient(client=http_client)

import unstructured_client
from unstructured_client.models import operations, shared

s = unstructured_client.UnstructuredClient(
    api_key_auth="YOUR_API_KEY",
)


res = s.general.partition(request=operations.PartitionRequest(
    partition_parameters=shared.PartitionParameters(
        files=shared.Files(
            content='0x2cC94b2FEF'.encode(),
            file_name='your_file_here',
        ),
        strategy=shared.Strategy.AUTO,
    ),
))

if res.elements is not None:
    # handle response
    pass

This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.

The following instructions are intended to help you get up and running with unstructured-python-client locally if you are planning to contribute to the project.

• Using pyenv to manage virtualenv's is recommended but not necessary

  • Mac install instructions. See here for more detailed instructions.
    • brew install pyenv-virtualenv
    • pyenv install 3.10
  • Linux instructions are available here.

• Create a virtualenv to work in and activate it, e.g. for one named unstructured-python-client:

  pyenv virtualenv 3.10 unstructured-python-client pyenv activate unstructured-python-client

• Run make install and make test

While we value open-source contributions to this SDK, this library is generated programmatically by Speakeasy. In order to start working with this repo, you need to:

1. Install Speakeasy client locally https://github.com/speakeasy-api/speakeasy#installation
2. Run speakeasy auth login
3. Run make client-generate. This allows to iterate development with python client.

There are two important files used by make client-generate:

1. openapi.json which is actually not stored here, but fetched from unstructured-api, represents the API that is supported on backend.
2. overlay_client.yaml is a handcrafted diff that when applied over above, produces openapi_client.json which is used to generate SDK.

Once PR with changes is merged, Github CI will autogenerate the Speakeasy client in a new PR, using the openapi.json and overlay_client.yaml You will have to manually bring back the human created lines in it.

Feel free to open a PR or a Github issue as a proof of concept and we'll do our best to include it in a future release!