AWS Bedrock Client for LLMs

[ThePyProgrammer]

Something like a wrapper for this:

import boto3

session = boto3.Session(
    aws_access_key_id='<insert id>',
    aws_secret_access_key='<insert key>',
    region_name='<insert region>' # 'use-east-1'
)

client = session.client('bedrock-runtime', '<insert region>') # 'use-east-1'
def sut(prompt):
    conversation = [
        {
            "role": "user",
            "content": [{"text": prompt}],
        }
    ]

    response = client.converse(
        modelId="anthropic.claude-3-sonnet-20240229-v1:0",#"meta.llama2-13b-chat-v1",
        messages=conversation,
        inferenceConfig={"maxTokens":10,"temperature":0.5,"topP":0.9},
        additionalModelRequestFields={}
    )
    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    return response_text

but with the chat and complete methods.