DSPy: The framework for programming—not prompting—language models
Python
docs(aws.md): changed lm calls to dspy.Bedrock etc.
Dhar Rawald2707eb7d019
diff --git a/docs/api/language_model_clients/aws.md b/docs/api/language_model_clients/aws.mdindex afac264f3..da06e8e8e 100644--- a/docs/api/language_model_clients/aws.md+++ b/docs/api/language_model_clients/aws.md@@ -12,19 +12,19 @@ sidebar_position: 9# 2. Configure your AWS credentials with the AWS CLI before using these models# initialize the bedrock aws provider-bedrock = Bedrock(region_name="us-west-2")+bedrock = dspy.Bedrock(region_name="us-west-2")# For mixtral on Bedrock-lm = AWSMistral(bedrock, "mistral.mixtral-8x7b-instruct-v0:1", **kwargs)+lm = dspy.AWSMistral(bedrock, "mistral.mixtral-8x7b-instruct-v0:1", **kwargs)# For haiku on Bedrock-lm = AWSAnthropic(bedrock, "anthropic.claude-3-haiku-20240307-v1:0", **kwargs)+lm = dspy.AWSAnthropic(bedrock, "anthropic.claude-3-haiku-20240307-v1:0", **kwargs)# For llama2 on Bedrock-lm = AWSMeta(bedrock, "meta.llama2-13b-chat-v1", **kwargs)+lm = dspy.AWSMeta(bedrock, "meta.llama2-13b-chat-v1", **kwargs)# initialize the sagemaker aws provider-sagemaker = Sagemaker(region_name="us-west-2")+sagemaker = dspy.Sagemaker(region_name="us-west-2")# For mistral on Sagemaker# Note: you need to create a Sagemaker endpoint for the mistral model first-lm = AWSMistral(sagemaker, "<YOUR_MISTRAL_ENDPOINT_NAME>", **kwargs)+lm = dspy.AWSMistral(sagemaker, "<YOUR_MISTRAL_ENDPOINT_NAME>", **kwargs)```