> ## Documentation Index
> Fetch the complete documentation index at: https://docs.validio.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Amazon Bedrock

> Configure an Amazon Bedrock credential in Validio to leverage AI foundation models for generating SQL queries in custom validators and filters.

This guide covers how to configure an Amazon Bedrock credential in Validio to access AI foundation models for generating SQL queries in custom validators and filters.

![The Amazon Bedrock credential configuration form, showing name, model, AWS region, and API key fields](https://mintcdn.com/validio/h4NQPs1kJwlpB1Yj/images/docs/integrations/810-bedrock-credential-config.png?fit=max\&auto=format\&n=h4NQPs1kJwlpB1Yj\&q=85\&s=b80567dd386a3d26b7debd16b3bfdc86)

Configuration for Amazon Bedrock credential

Amazon Bedrock provides access to AI language models from AI companies (like Anthropic, Meta, Mistral, and Amazon). By adding an LLM credential for Amazon Bedrock to Validio, you can leverage the capabilities of selected models to generate SQL queries for custom validation and filtering.

## Prerequisites

Before setting up your Amazon Bedrock credential, ensure you have:

* Enabled the **Allow LLM credentials** setting in your Validio Workspace (requires Global `settings:WRITE`)
* Appropriate permissions to create credentials in your Validio namespace (requires `credentials:WRITE`)
* An active AWS account with an IAM identity that has permissions to use the Amazon Bedrock console.
* An Amazon Bedrock API key (you can generate one from the [Amazon Bedrock console](https://console.aws.amazon.com/bedrock)). Refer to [Generate an Amazon Bedrock API key](https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys-generate.html) in AWS documentation.

## Add an Amazon Bedrock credential

> [!NOTE]
>
> Because each Amazon Bedrock credential is tied to one language model, you should add one credential for each model you want to use in Validio.

To add an AWS Bedrock credential,

1. Navigate to **Credentials** and click **+ New credential**.
2. **Namespace**: Select the namespace where the resources will be created.
3. **Credential Type**: Select **AWS Bedrock** from the dropdown.
4. **Configuration**: Complete the required parameters.

   | Parameter | Description |
   | :- | :- |
   | Name | A unique identifier for this credential. |
   | Model | Select language model from the list, or enter a custom model ID or inference profile ARN. Models prefixed with **Global** route requests across all AWS Bedrock supported regions, while **US** models route only to North American regions (ca-central-1, us-east-1, us-east-2, us-west-1, us-west-2). |
   | AWS region | Select your valid AWS region. |
   | Authentication type | Select how to authenticate your identity when making requests to the Amazon Bedrock API. |
   | API key | Enter a valid Amazon Bedrock API key. |
   | Custom base URL | (Optional) Custom base URL for the Amazon Bedrock API. Only needed if using a proxy or custom endpoint. |
5. (Optional) Click **Test credential** to validate that Validio can successfully connect to Amazon Bedrock using your configuration. If the test fails, verify your API key is correct.
6. Click **Create credential** to save your configuration.

## Next steps

With your Amazon Bedrock credential configured, you can leverage AI models across various Validio features:

* **[Custom SQL validators](https://docs.validio.io/docs/validators/validator-types/custom-sql.md)**: Generate complex validation queries or fix errors in your SQL queries.
* **[SQL filters](https://docs.validio.io/docs/filters/filter-types.md#sql-filter)**: Create sophisticated filtering conditions and data selection criteria.
* **[Validator recommendations](https://docs.validio.io/docs/ai-features/validator-recommendations.md)**: Profile your data and generate recommendations to quickly set up monitoring