Amazon OpenSearch Service로 RAG

2024-06

1

실습

따라하기

https://catalog.us-east-1.prod.workshops.aws/workshops/48f303fe-bc6d-4183-858d-e4938f32136f/ko-KR

2

aws 콘솔 로그인

3

베드락이 가능한곳에서 진행

us-east1

4

cloud formation 실행

stack 이름은  아래 이름으로 해야함.

소스가 아래 스텍 이름으로  되어 있음.

opensearch-workshop

클라우드 포메인션 다운로드

https://github.com/atheanchu/opensearch-with-bedrock-workshop-kr/blob/main/setup.yaml

download file

5

미리 쿼터를 늘리거나 다른 인스턴스 선택.

세이즈메이커에서 다른 인스턴트 확인해서 다른 인스턴스 선택.

The account-level service limit 'ml.m5d.2xlarge for notebook instance usage' is 0 Instances, with current utilization of 0 Instances and a request delta of 1 Instances. Please use AWS Service Quotas to request an increase for this quota. If AWS Service Quotas is not available, contact AWS support to request an increase for this quota. (Service: AmazonSageMaker; Status Code: 400; Error Code: ResourceLimitExceeded; Request ID: 0ac5ac66-f677-457e-b06e-2ebd50bad543; Proxy: null)

암호는 형식에 맞게.

Resource handler returned message: "Invalid request provided: The master user password must contain at least one uppercase letter, one lowercase letter, one number, and one special character. (Service: OpenSearch, Status Code: 400, Request ID: 347fec9d-0ab5-44d5-9877-31a06ab72e96)" (RequestToken: 9bd4e6a7-c118-a26a-6233-fa23fd0d7ed2, HandlerErrorCode: InvalidRequest)