Supported regions and models for Amazon Bedrock knowledge bases
Amazon Bedrock knowledge bases are supported in regions across the Americas, Asia, and Europe. Certain models provided by Amazon, Cohere, and Anthropic are supported for knowledge bases. You use a model for converting your data into vector embeddings and a model for information retrieval and response generation.
You must enable model access to use a model that's supported for knowledge bases.
If you use the Amazon Bedrock API, take note of your model Amazon Resource Name (ARN) that's required for converting your data into vector embeddings and for knowledge base retrieval and generation. Copy the model ID for your chosen model for knowledge bases and construct the model ARN using the model (resource) ID, following the provided ARN examples for your model resource type.
If you use the Amazon Bedrock console, you are not required to construct a model ARN, as you can select an available model as part of the steps for creating a knowledge base.
Amazon Bedrock knowledge bases are supported in the following regions:
Note
Amazon Titan Text Premier is currently only available in the us-east-1 Region.
| Region |
|---|
| US East (N. Virginia) |
| US West (Oregon) |
| Canada (Central) |
| Asia Pacific (Mumbai) |
| Asia Pacific (Singapore) (gated access) |
| Asia Pacific (Sydney) |
| Asia Pacific (Tokyo) |
| Europe (Frankfurt) |
| Europe (London) |
| Europe (Paris) |
| Europe (Ireland) (gated access) |
| South America (São Paulo) |
| AWS GovCloud (US-West) |
You can use the following models to convert your data into vector embeddings representation of the data:
Note
You can no longer create a new vector store with Amazon Titan Embeddings G1 - Text. Previously created vector stores using Amazon Titan Embeddings G1 - Text are still supported.
| Model name | Model ID |
|---|---|
| Amazon Titan Embeddings G1 - Text | amazon.titan-embed-text-v1 |
| Amazon Titan Text Embeddings V2 | amazon.titan-embed-text-v2:0 |
| Cohere Embed (English) | cohere.embed-english-v3 |
| Cohere Embed (Multilingual) | cohere.embed-multilingual-v3 |
You can use the following models with the RetrieveAndGenerate API operation to generate responses after retrieving information from knowledge bases:
Note
The RetrieveAndGenerate API queries the knowledge base and uses supported Amazon Bedrock
knowledge base models to generate responses from the information it retrieves. The
Retrieve API
only queries the knowledge base; it doesn't generate responses. Therefore, after retrieving
results with the Retrieve API, you could use the results in an
InvokeModel request with any Amazon Bedrock or SageMaker model to generate responses.
| Model | Model ID |
|---|---|
| Amazon Titan Text Premier | amazon.titan-text-premier-v1:0 |
| Anthropic Claude v2.0 | anthropic.claude-v2 |
| Anthropic Claude v2.1 | anthropic.claude-v2:1 |
| Anthropic Claude 3 Sonnet v1 | anthropic.claude-3-sonnet-20240229-v1:0 |
| Anthropic Claude 3 Sonnet 3.5 | anthropic.claude-3-5-sonnet-20240620-v1:0 |
| Anthropic Claude 3 Haiku v1 | anthropic.claude-3-haiku-20240307-v1:0 |
| Anthropic Claude Instant v1 | anthropic.claude-instant-v1 |
| Meta Llama 3.1 8B Instruct | meta.llama3-1-8b-instruct-v1:0 |
| Meta Llama 3.1 70B Instruct | meta.llama3-1-70b-instruct-v1:0 |
| Meta Llama 3.1 405B Instruct | meta.llama3-1-405b-instruct-v1:0 |
The RetrieveAndGenerate API operation supports the following types of throughput:
-
On-demand – Sends model inference requests to your current region. The rate or volume of your requests might be limited during peak utilization bursts. Choose on-demand throughput in the console or specify the model ID in an RetrieveAndGenerate request.
-
Cross-region inference – Distributes model inference requests across a set of regions to allow higher throughput and facilitate greater resilience. Specify an inference profile, which defines regional endpoints to send model invocation requests to, in a RetrieveAndGenerate or CreateDataSource request. For more information, see Improve resilience with cross-region inference.
Important
If you use cross-region inference, your data can be shared across regions.
