Introduce Amazon Bedrock service

[ferruzzi]

Includes the basic doc page, hook, operator, unit tests, and system test.

Currently only supports invoking one of the prebuilt "foundation" models. Custom model support is coming next.

Sample DAG:

from airflow.models import DAG
from airflow.providers.amazon.aws.operators.bedrock import BedrockInvokeModelOperator
from airflow.utils.dates import days_ago

PROMPT = "What are the first ten digits of pi?"

with DAG(
    dag_id="bedrock_testing",
    schedule_interval=None,
    start_date=days_ago(1)
) as dag:

    invoke_llama = BedrockInvokeModelOperator(
        task_id="invoke_llama",
        model_id="meta.llama2-13b-chat-v1",
        input_data={"prompt": PROMPT},
    )

Log output from the above sample DAG run:

Manually tested as a DAG in Breeze:

This is the generated doc page, for easier viewing:

The link at the bottom of that screenshot beings you here

[ferruzzi]

@Taragolis - I added you to the review list since you saw the previous attempt at this, don't feel obligated though.

[Taragolis]

Some minor things

[eladkal]

LGTM