Skip to main content

Quick start with AWS Bedrock

plan support
  • Self-hosted: Business, Enterprise Plus

Prerequisites​

  • An AWS account with Bedrock enabled in your region
  • Access to the models you plan to use (e.g., Anthropic Claude) granted in the Bedrock console
  • An AWS Bedrock API key AWS Bedrock API key You could copy the API key from the console. We recommend using the long-term API key with longer expiration date, so you don't have to rotate the key too often.
Notes

If you plan to use Amazon Bedrock Inference Profile to help track usage and cost when invoking a model. Please add model_id(inference profile ARN) in the configuration while setting up the embedding model or LLM model in Wren AI. For model name in the configuration, you could simply use the inference profile ID, as long as it belongs to the same inference profile.

Example of complete configuration for embedding model:

{
  "kwargs":{
    "timeout": 600,
    "model_id": "arn:aws:bedrock:xxxxxx"
  },
  "dimension": 4096
}

Example of complete configuration for LLM model:

{
  "kwargs": {
    "n": 1,
    "seed": 0,
    "timeout": 600,
    "max_tokens": 4096,
    "temperature": 0,
    "model_id": "arn:aws:bedrock:xxxxxx"
  },
  "context_window_size": 240000
}

Bedrock inference profile

Steps (Quick setup)​

1. During onboarding, select "Quick setup" and then "AWS Bedrock".​

AWS Bedrock onboarding

2. Enter your region and AWS Bedrock API key.​

AWS Bedrock region and API key

3. Select an embedding model.​

Best Model Recommendation

The following steps and screenshots use Titan Text Embedding V2 as an example and may not reflect the current best model configuration. For the latest recommended model combination and configuration, please contact your account manager or sales representative.

Now, let's go to the AWS Bedrock console to select an embedding model.

Visit the AWS Bedrock console -> "Model Catalog".​

AWS Bedrock console AWS Bedrock model catalog

AWS Bedrock search bar AWS Bedrock search for Titan

Click into the "Titan Text Embedding V2" model. Copy the model ID.​

AWS Bedrock Titan Text Embedding V2 model ID

Back to Wren AI, enter the model ID.​

At the "Embedding model" section, in the input, click "Add embedding model".

Add embedding model

Then, at the form, fill in the model ID you copied from the AWS Bedrock console.

Add embedding model form

The configuration is already filled in for you. Click "Add embedding model".

After that, click "Test connection" to verify the embedding model is working.

Test connection

4. Select a LLM model.​

Best Model Recommendation

The following steps and screenshots use Claude 4.5 Sonnet as an example and may not reflect the current best model configuration. For the latest recommended model combination and configuration, please contact your account manager or sales representative.

Let's go to the AWS Bedrock console to copy the "Inference Profile ID" for the model you plan to use.

Visit the AWS Bedrock console -> "Cross-region inference".​

AWS Bedrock cross-region inference

Search for "sonnet 4.5" in the search bar and find the "Claude 4.5 Sonnet" model. Copy the "Inference Profile ID".​

AWS Bedrock search for Sonnet 4.5

Back to Wren AI, click "Add model" and paste the "Inference Profile ID".​

Add LLM model form

5. Assign the models to pipelines.​

Assign models to each pipeline based on their intended usage, then click "Complete setup" to complete the setup.