Skip to main content

Amazon Bedrock

DeepEval supports using any Amazon Bedrock model for all evaluation metrics. To get started, you'll need to set up your AWS credentials.

Setting Up Your API Key​

To use Amazon Bedrock for deepeval's LLM-based evaluations (metrics evaluated using an LLM), provide your AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY in the CLI:

export AWS_ACCESS_KEY_ID=<your-aws-access-key-id>
export AWS_SECRET_ACCESS_KEY=<your-aws-secret-access-key>

Alternatively, if you're working in a notebook environment (e.g., Jupyter or Colab), set your keys in a cell:

%env AWS_ACCESS_KEY_ID=<your-aws-access-key-id>
%env AWS_SECRET_ACCESS_KEY=<your-aws-secret-access-key>

Python​

To use Amazon bedrock models for DeepEval metrics, define an AmazonBedrockModel and specify the model you want to use.

from deepeval.models import AmazonBedrockModel
from deepeval.metrics import AnswerRelevancyMetric

model = AmazonBedrockModel(
    model_id="anthropic.claude-3-opus-20240229-v1:0",
    temperature=0
)
answer_relevancy = AnswerRelevancyMetric(model=model)

There are TWO mandatory and FIVE optional parameters when creating an AmazonBedrockModel:

  • model_id: A string specifying the bedrock model identifier to call (e.g. anthropic.claude-3-opus-20240229-v1:0).
  • region_name: A string specifying the AWS region hosting your Bedrock endpoint (e.g. us-east-1).
  • [Optional] aws_access_key_id: A string specifiying your AWS Access Key ID. If omitted, falls back to the default AWS credentials chain.
  • [Optional] aws_secret_access_key: A string specifiying your AWS Secret Access Key. If omitted, falls back to the default AWS credentials chain.
  • [Optional] temperature: A float specifying the model temperature. Defaulted to 0.
  • [Optional] input_token_cost: A float specifying the per-input-token cost in USD. Defaulted to 0.
  • [Optional] output_token_cost: A float specifying the per-output-token cost in USD. Defaulted to 0.

Available Amazon Bedrock Models​

note

This list only displays some of the available models. For a comprehensive list, refer to the Amazon Bedrock's official documentation.

Below is a list of commonly used Amazon Bedrock foundation models:

  • anthropic.claude-3-opus-20240229-v1:0
  • anthropic.claude-3-sonnet-20240229-v1:0
  • amazon.titan-text-express-v1
  • amazon.titan-text-premier-v1:0
  • amazon.nova-micro-v1:0
  • amazon.nova-lite-v1:0
  • amazon.nova-pro-v1:0
  • amazon.nova-premier-v1:0