Amazon Bedrock
Available since 25.3
To use Amazon Bedrock as an AI provider in Team Edition, set it up like this:
- In Team Edition, go to Window -> Preferences -> AI -> Model configurations
- Click + and choose Amazon Bedrock as the engine to create a profile
- Select AWS Credentials as the authorization type
- Choose a credentials method:
- Access/secret keys: In the AWS console, create or use an IAM user with permission to use Bedrock. Generate an Access Key ID and Secret Access Key, and enter them in Team Edition. You can also enter an optional session token.
- Default credentials: Use your default AWS credentials.
- AWS profile: Choose a profile configured in your shared AWS credentials files.
- User name/password: Enter your user name and password.
- Select your Region
- Choose a model from the Model/Inference list
- Click Test connection to verify that the credentials and model work correctly
- Apply the changes
Settings¶
| Setting | Description | default |
|---|---|---|
| Authorization Type | Select AWS Credentials to configure AWS credentials in Team Edition, or Integrated AWS Cloud to use credentials from a configured AWS Cloud. | |
| Credentials | When AWS Credentials is selected: - Access/secret keys, with an optional session token - Default credentials - AWS profile - User name/password - Session credentials, available only in Team Edition multi-user or distributed mode When Integrated AWS Cloud is selected, use credentials from a configured AWS Cloud. |
|
| Model/Inference | Choose the AI model. Use Load model list to refresh the available models. You can also type a model name manually. | |
| Show available inferences | Fetches and displays the models available to your AWS account in the selected region. | false |
| Context size | A larger number allows the AI to use more data for better answers but may slow down response time. | 20000 |
| Temperature | Control AI's creativity from 0.0 (more precise) to 0.9 (more diverse). Note that higher temperature can lead to less predictable results. |
0.0 |
| Request timeout (sec) | Maximum time Team Edition waits for a response from the AI engine before the request fails; available under Advanced settings | 30 |
| Use environment variables | Read supported environment variables to override saved settings; available under Advanced settings | Off |
| Write AWS Bedrock queries to debug log | Logs your AI requests. For more details on logging, see Log Viewer; available under Advanced settings | false |
Use environment variables¶
| Variable | Description |
|---|---|
AWS_ACCESS_KEY_ID |
Access key ID; supply together with AWS_SECRET_ACCESS_KEY |
AWS_SECRET_ACCESS_KEY |
Secret access key; supply together with AWS_ACCESS_KEY_ID |
AWS_SESSION_TOKEN |
Optional session token for the access/secret key pair |
AWS_PROFILE |
Credential profile used if either AWS_ACCESS_KEY_ID or AWS_SECRET_ACCESS_KEY is not set; saved credentials are used if this variable is also not set |
AWS_REGION |
Region override |
DBEAVER_AI_BEDROCK_MODEL |
Model name |
AWS_ENDPOINT_URL_BEDROCK |
Metadata client endpoint |
AWS_ENDPOINT_URL_BEDROCK_RUNTIME |
Runtime endpoint |
AWS_ENDPOINT_URL |
Endpoint used for either client if its service-specific endpoint variable is not set |