View Source ExAws.Bedrock (ex_aws_bedrock v1.5.4)
Interface to AWS Bedrock.
Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies.
Summary
Functions
Get the properties associated with a Amazon Bedrock custom model that you have created.
Get details about a Amazon Bedrock foundation model.
Invokes the specified Amazon Bedrock model to run inference using the input provided in the request body.
List of Amazon Bedrock foundation models that you can use.
Functions
Get the properties associated with a Amazon Bedrock custom model that you have created.
Get details about a Amazon Bedrock foundation model.
@spec invoke_model(String.t(), Jason.Encoder.t()) :: ExAws.Operation.t()
Invokes the specified Amazon Bedrock model to run inference using the input provided in the request body.
You use InvokeModel to run inference for text models, image models, and embedding models.
input = ExAws.Bedrock.Titan.TextModel.build("Hello, LLM.");
request = ExAws.Bedrock.invoke_model("amazon.titan-tg1-large", input);
{:ok, %{"results" => [%{"outputText" => output}|_]}} = ExAws.request(request, service_override: :bedrock);
output
Note the extra service override parameter required for correctly signing the request.
Use ExAws.Bedrock.request/2
to automatically provide the correct parameter.
Model parameters are normally JSON documents defined in the link below, therefore pass a
struct or map that can be serialized with Jason.encode/1
.
List of Amazon Bedrock foundation models that you can use.
Parameters
:by_customization_type
-:FINE_TUNING | :CONTINUED_PRE_TRAINING
:by_inference_type
-:ON_DEMAND | :PROVISIONED
:by_output_modality
-:TEXT | :IMAGE | :EMBEDDING
:by_provider
- An Amazon Bedrock model provider