Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.unstructured.io/llms.txt

Use this file to discover all available pages before exploring further.

The following information applies only to dedicated instance and in-VPC deployments of Unstructured Business.
Dedicated instance and in-VPC deployments require you to supply your own AI provider credentials. Unstructured does not provision shared API keys — you bring access credentials from the AI provider of your choice. This lets you use your preferred provider and apply any volume discounts you have negotiated with that provider to your Unstructured workloads. Credentials are required to use any of the following features: You must have an account with each AI provider you configure. Your provider bills usage directly to your account — these charges are not included in your Unstructured bill. If you do not pay these provider bills, the features that depend on that provider may stop working without prior notice.
The following steps do not apply to Let’s Go, Pay-As-You-Go, or Business SaaS accounts. This is because the costs for using the models that Unstructured provides are already factored into the pricing structures for these account types.For Unstructured Business dedicated instance and in-VPC deployments, completing the following steps enables you to better manage and reduce your overall costs by negotiating lower overall billing rates with Unstructured for its core features, while also leveraging any separately negotiated volume discounts with the AI providers that you want to use.

​
Keeping model provider traffic private

If your network policy requires AI provider traffic to stay off the public internet, use a model provider accessible through your cloud provider’s private networking. AWS — Use Amazon Bedrock to access foundation models through VPC endpoints. Unstructured configures the Bedrock VPC endpoint on its side; you grant access via IAM policy. Traffic never leaves the AWS network. For dedicated instance setup, see Connecting to services with AWS PrivateLink. Azure — Use Azure OpenAI Service to access models through a private endpoint on the Microsoft backbone. Unstructured creates a private endpoint in its VNet toward your Azure OpenAI resource. For dedicated instance setup, see Connecting to services with Azure Private Link.

​
Configure an AI provider

To have Unstructured use an AI model, you must first configure the model’s AI provider for each target Unstructured workspace within each corresponding Unstructured organizational account in your dedicated instance or in-VPC deployment, as follows. This procedure assumes that you have already created an account with the model’s AI provider, generated access credentials for your account with that AI provider, and obtained any other miscellaneous settings that the AI provider might also require. For more information, see the AI provider’s documentation. To configure an AI provider for a workspace, do the following:
  1. If you are not already signed in, sign in to your Unstructured account.
  2. In the top navigation bar, in the organizational account selector, select the name of the organizational account to which the target workspace belongs.
  3. Next to the organizational account selector, click the workspace selector, and then select the name of the target workspace.
  4. In the workspace navigation bar, click the AI Providers tab.
  5. In the list of available AI providers, next to the target AI provider’s name, click Configure.
  6. In the Configure AI Provider dialog, enter your access credentials for the AI provider, along with any other miscellaneous settings that the AI provider might also require. To get these settings, see your AI provider’s documentation.
  7. Click Save Configuration.
The configured AI provider is now ready to be used by all workflows in this workspace.

​
Update an AI provider’s configuration

After you configure an AI provider, you can no longer open that AI provider’s settings screen to make any changes to it. This is by design to prevent users from accessing sensitive access credentials strings or other sensitive settings that they might not otherwise be allowed to access across your organization. To update the settings for an AI provider, do the following:
  1. Delete the target AI provider’s current configuration.
  2. Configure the target AI provider again.

​
Delete an AI provider’s configuration

After you delete an AI provider’s configuration, any workflows in the selected workspace that rely on this AI provider might produce unexpected results or stop working altogether.
To delete an AI provider’s configuration, do the following:
  1. If you are not already signed in, sign in to your Unstructured account.
  2. In the top navigation bar, in the organizational account selector, select the name of the organizational account to which
    the workspace with the target AI provider’s configuration belongs.
  3. Next to the organizational account selector, click the workspace selector, and then select the name of the target workspace.
  4. In the workspace navigation bar, click the AI Providers tab.
  5. In the list of AI providers, next to the target AI provider’s name, click the ellipsis (three dots) icon.
  6. Click Delete Configuration.
  7. To confirm the deletion, click Delete Configuration.
You can configure the target AI provider again at any time.

​
No API support for AI provider management

You cannot use the Unstructured API to manage AI providers. You can manage AI providers only through the Unstructured UI.