UNSTRUCTURED_API_KEY
,
representing your Unstructured API key. To get your API key, do the following:
-
If you do not already have an Unstructured account, sign up for free.
After you sign up, you are automatically signed in to your new Unstructured Starter account, at https://platform.unstructured.io.
To sign up for a Team or Enterprise account instead, contact Unstructured Sales, or learn more.
-
If you have an Unstructured Starter or Team account and are not already signed in, sign in to your account at https://platform.unstructured.io.
For an Enterprise account, see your Unstructured account administrator for instructions, or email Unstructured Support at support@unstructured.io.
-
Get your Unstructured API key:
a. After you sign in to your Unstructured Starter account, click API Keys on the sidebar.
b. Click Generate API Key.For a Team or Enterprise account, before you click API Keys, make sure you have selected the organizational workspace you want to create an API key for. Each API key works with one and only one organizational workspace. Learn more.
c. Follow the on-screen instructions to finish generating the key.
d. Click the Copy icon next to your new key to add the key to your system’s clipboard. If you lose this key, simply return and click the Copy icon again.
Installation
Before using the SDK to interact with Unstructured, install the library:The SDK uses semantic versioning and major bumps could bring breaking changes. It is advised to
pin your installed version.
Basics
Let’s start with a simple example in which you send a PDF document to the Unstructured Partition Endpoint to be partitioned by Unstructured.The JavaScript/TypeScript SDK has the following breaking changes in v0.11.0:
- Imports under the
dist
path have moved up a level - Enums are now used for parameters with a set of options
- This includes
chunkingStrategy
,outputFormat
, andstrategy
- This includes
- All parameters to
partition
have moved to apartitionParameters
object
Page splitting
In order to speed up processing of large PDF files, thesplitPdfPage
* parameter is true
by default. This
causes the PDF to be split into small batches of pages before sending requests to the API. The client
awaits all parallel requests and combines the responses into a single response object. This is specific to PDF files and other
filetypes are ignored.
The number of parallel requests is controlled by splitPdfConcurrencyLevel
*.
The default is 8 and the max is set to 15 to avoid high resource usage and costs.
If at least one request is successful, the responses are combined into a single response object. An
error is returned only if all requests failed or there was an error during splitting.
This feature may lead to unexpected results when chunking because the server does not see the entire
document context at once. If you’d like to chunk across the whole document and still get the speedup from
parallel processing, you can:
- Partition the PDF with
splitPdfPage
set totrue
, without any chunking parameters. - Store the returned elements in
results.json
. - Partition this JSON file with the desired chunking parameters.
TypeScript
Customizing the client
Retries
You can also change the defaults for retries through theretryConfig
*
when initializing the client. If a request to the API fails, the client will retry the
request with an exponential backoff strategy up to a maximum interval of one minute. The
function keeps retrying until the total elapsed time exceeds maxElapsedTime
*,
which defaults to one hour:
TypeScript
Processing multiple files
The code example in the Basics section processes a single PDF file. But what if you want to process multiple files inside a directory with a mixture of subdirectories and files with different file types? The following example takes an input directory path to read files from and an output directory path to write the processed data to, processing one file at a time.TypeScript
Parameters & examples
The parameter names used in this document are for the JavaScript/TypeScript SDK, which follows thecamelCase
convention. The Python SDK follows the snake_case
convention. Other than this difference in naming convention,
the names used in the SDKs are the same across all methods.
- Refer to the API parameters page for the full list of available parameters.
- Refer to the Examples page for some inspiration on using the parameters.