Repository files navigation

This is a HTTP client for theUnstructured Platform API. You can sign uphere and process 1000 free pages per day for 14 days.

Please refer to the our documentation for a full guide on integrating theWorkflow Endpoint andPartition Endpoint into your Python code.

• SDK Installation
• Retries
• Error Handling
• Custom HTTP Client
• IDE Support
• SDK Example Usage
• Configuration
• File uploads
• Resource Management
• Debugging

The SDK can be installed with eitherpip orpoetry package managers.

PIP is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.

pip install unstructured-client

Poetry is a modern tool that simplifies dependency management and package publishing by using a singlepyproject.toml file to handle project metadata and dependencies.

poetry add unstructured-client

You can use this SDK in a Python shell withuv and theuvx command that comes with it like so:

uvx --from unstructured-client python

It's also possible to write a standalone Python script without needing to set up a whole project like so:

#!/usr/bin/env -S uv run --script# /// script# requires-python = ">=3.9"# dependencies = [#     "unstructured-client",# ]# ///fromunstructured_clientimportUnstructuredClientsdk=UnstructuredClient(# SDK arguments)# Rest of script here...

Once that is saved to a file, you can run it withuv run script.py wherescript.py can be replaced with the actual file name.

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide aRetryConfig object to the call:

fromunstructured_clientimportUnstructuredClientfromunstructured_client.utilsimportBackoffStrategy,RetryConfigwithUnstructuredClient()asuc_client:res=uc_client.destinations.create_connection_check_destinations(request={"destination_id":"cb9e35c1-0b04-4d98-83fa-fa6241323f96",    },RetryConfig("backoff",BackoffStrategy(1,50,1.1,100),False))assertres.dag_node_connection_checkisnotNone# Handle responseprint(res.dag_node_connection_check)

If you'd like to override the default retry strategy for all operations that support retries, you can use theretry_config optional parameter when initializing the SDK:

fromunstructured_clientimportUnstructuredClientfromunstructured_client.utilsimportBackoffStrategy,RetryConfigwithUnstructuredClient(retry_config=RetryConfig("backoff",BackoffStrategy(1,50,1.1,100),False),)asuc_client:res=uc_client.destinations.create_connection_check_destinations(request={"destination_id":"cb9e35c1-0b04-4d98-83fa-fa6241323f96",    })assertres.dag_node_connection_checkisnotNone# Handle responseprint(res.dag_node_connection_check)

Handling errors in this SDK should largely match your expectations. All operations return a response object or raise an exception.

By default, an API error will raise a errors.SDKError exception, which has the following properties:

When custom error responses are specified for an operation, the SDK may also raise their associated exceptions. You can refer to respectiveErrors tables in SDK docs for more details on possible exception types for each operation. For example, thecreate_connection_check_destinations_async method may raise the following exceptions:

fromunstructured_clientimportUnstructuredClientfromunstructured_client.modelsimporterrorswithUnstructuredClient()asuc_client:res=Nonetry:res=uc_client.destinations.create_connection_check_destinations(request={"destination_id":"cb9e35c1-0b04-4d98-83fa-fa6241323f96",        })assertres.dag_node_connection_checkisnotNone# Handle responseprint(res.dag_node_connection_check)excepterrors.HTTPValidationErrorase:# handle e.data: errors.HTTPValidationErrorDataraise(e)excepterrors.SDKErrorase:# handle exceptionraise(e)

The Python SDK makes API calls using thehttpx 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 your own HTTP client instance.Depending on whether you are using the sync or async version of the SDK, you can pass an instance ofHttpClient orAsyncHttpClient respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls.This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance ofhttpx.Client orhttpx.AsyncClient directly.

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

fromunstructured_clientimportUnstructuredClientimporthttpxhttp_client=httpx.Client(headers={"x-custom-header":"someValue"})s=UnstructuredClient(client=http_client)

or you could wrap the client with your own custom logic:

fromunstructured_clientimportUnstructuredClientfromunstructured_client.httpclientimportAsyncHttpClientimporthttpxclassCustomClient(AsyncHttpClient):client:AsyncHttpClientdef__init__(self,client:AsyncHttpClient):self.client=clientasyncdefsend(self,request:httpx.Request,*,stream:bool=False,auth:Union[httpx._types.AuthTypes,httpx._client.UseClientDefault,None        ]=httpx.USE_CLIENT_DEFAULT,follow_redirects:Union[bool,httpx._client.UseClientDefault        ]=httpx.USE_CLIENT_DEFAULT,    )->httpx.Response:request.headers["Client-Level-Header"]="added by client"returnawaitself.client.send(request,stream=stream,auth=auth,follow_redirects=follow_redirects        )defbuild_request(self,method:str,url:httpx._types.URLTypes,*,content:Optional[httpx._types.RequestContent]=None,data:Optional[httpx._types.RequestData]=None,files:Optional[httpx._types.RequestFiles]=None,json:Optional[Any]=None,params:Optional[httpx._types.QueryParamTypes]=None,headers:Optional[httpx._types.HeaderTypes]=None,cookies:Optional[httpx._types.CookieTypes]=None,timeout:Union[httpx._types.TimeoutTypes,httpx._client.UseClientDefault        ]=httpx.USE_CLIENT_DEFAULT,extensions:Optional[httpx._types.RequestExtensions]=None,    )->httpx.Request:returnself.client.build_request(method,url,content=content,data=data,files=files,json=json,params=params,headers=headers,cookies=cookies,timeout=timeout,extensions=extensions,        )s=UnstructuredClient(async_client=CustomClient(httpx.AsyncClient()))

Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.

• PyCharm Pydantic Plugin

# Synchronous Examplefromunstructured_clientimportUnstructuredClientwithUnstructuredClient()asuc_client:res=uc_client.destinations.create_connection_check_destinations(request={"destination_id":"cb9e35c1-0b04-4d98-83fa-fa6241323f96",    })assertres.dag_node_connection_checkisnotNone# Handle responseprint(res.dag_node_connection_check)

The same SDK client can also be used to make asychronous requests by importing asyncio.

# Asynchronous Exampleimportasynciofromunstructured_clientimportUnstructuredClientasyncdefmain():asyncwithUnstructuredClient()asuc_client:res=awaituc_client.destinations.create_connection_check_destinations_async(request={"destination_id":"cb9e35c1-0b04-4d98-83fa-fa6241323f96",        })assertres.dag_node_connection_checkisnotNone# Handle responseprint(res.dag_node_connection_check)asyncio.run(main())

Refer to theAPI parameters page for all available parameters.

Seepage splitting for more details.

In order to speed up processing of large PDF files, the client splits up PDFs into smaller files, sends these to the API concurrently, and recombines the results.split_pdf_page can be set toFalse to disable this.

The amount of workers utilized for splitting PDFs is dictated by thesplit_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 leveragesasyncio 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 usesasyncio the client can encouter event loop issues if it is nested in another async runner, like running in agevent spawned task. Instead, this is safe to run in multiprocessing workers (e.g., usingmultiprocessing.Pool withfork context).

Example:

req=operations.PartitionRequest(partition_parameters=shared.PartitionParameters(files=files,strategy="fast",languages=["eng"],split_pdf_concurrency_level=8    ))

Whensplit_pdf_page=True (the default), you can optionally specify a page range to send only a portion of your PDF to be extracted. The parameter takes a list of two integers to specify the range, inclusive. A ValueError is thrown if the page range is invalid.

Example:

req=operations.PartitionRequest(partition_parameters=shared.PartitionParameters(files=files,strategy="fast",languages=["eng"],split_pdf_page_range=[10,15],    ))

Whensplit_pdf_allow_failed=False (the default), any errors encountered during sending parallel request will break the process and raise an exception.Whensplit_pdf_allow_failed=True, the process will continue even if some requests fail, and the results will be combined at the end (the output from the errored pages will not be included).

Example:

req=operations.PartitionRequest(partition_parameters=shared.PartitionParameters(files=files,strategy="fast",languages=["eng"],split_pdf_allow_failed=True,    ))

Certain SDK methods accept file objects as part of a request body or multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.

fromunstructured_clientimportUnstructuredClientfromunstructured_client.modelsimportsharedwithUnstructuredClient()asuc_client:res=uc_client.general.partition(request={"partition_parameters": {"files": {"content":open("example.file","rb"),"file_name":"example.file",            },"split_pdf_page_range": [1,10,            ],"vlm_model":shared.VLMModel.GPT_4O,"vlm_model_provider":shared.VLMModelProvider.OPENAI,        },    })assertres.elementsisnotNone# Handle responseprint(res.elements)

TheUnstructuredClient class implements the context manager protocol and registers a finalizer function to close the underlying sync and async HTTPX clients it uses under the hood. This will close HTTP connections, release memory and free up other resources held by the SDK. In short-lived Python programs and notebooks that make a few SDK method calls, resource management may not be a concern. However, in longer-lived programs, it is beneficial to create a single SDK instance via acontext manager and reuse it across the application.

fromunstructured_clientimportUnstructuredClientdefmain():withUnstructuredClient()asuc_client:# Rest of application here...# Or when using async:asyncdefamain():asyncwithUnstructuredClient()asuc_client:# Rest of application here...

You can setup your SDK to emit debug logs for SDK requests and responses.

You can pass your own logger class directly into your SDK.

fromunstructured_clientimportUnstructuredClientimportlogginglogging.basicConfig(level=logging.DEBUG)s=UnstructuredClient(debug_logger=logging.getLogger("unstructured_client"))

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

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

• Usingpyenv to manage virtualenv's is recommended but not necessary

  • Mac install instructions. Seehere for more detailed instructions.
    • brew install pyenv-virtualenv
    • pyenv install 3.10
  • Linux instructions are availablehere.

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

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

• Runmake install andmake 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 locallyhttps://github.com/speakeasy-api/speakeasy#installation
2. Runspeakeasy auth login
3. Runmake client-generate. This allows to iterate development with python client.

There are two important files used bymake 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, producesopenapi_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, usingtheopenapi.json andoverlay_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!