AWS Bedrock sync - The knowledge base storage configuration provided is invalid... The vector database encountered an error while processing the request: Unauthorized

Support
1

Hey there :wave:
I’m using AWS Bedrock Knowledge base with Pinecone vector database.
All was working well when I’m syncing by datasource with s3, but after a while, clicking on the “Sync” button again from AWS Console returned me an error in a red popup notification:
image

There are no change on the Connection string and Credentials secret ARN values.
Could you help me to understand please? :grinning:

2

Hi @tegomassria and welcome to the Pinecone community forums!

Thank you for your question and sorry you’re encountering this issue.

  1. Is this issue persisting still or is it intermittent?
  2. Can you try looking into your AWS account’s CloudTrail event history? (There are two - one automatically logs all API calls through your AWS account for 90 days). See if you can locate the same API call that errored out in CloudTrail events history, as this view often contains more verbose details and HTTP status codes / error messages.

Could you please share any relevant code - being careful not to include any secrets such as your Pinecone API key?

Best,
Zack

3

I have the exact same issue and there is nothing more verbose available in the error logs of that CloudTrail API Call:

{
    "eventVersion": "1.09",
    "userIdentity": {
        "type": "AssumedRole",
        "principalId": "AROAVH74TKMQXE5UM6Q64:x263453",
        "arn": "arn:aws:sts::360770130721:assumed-role/gt-emerg-184-developer/x263453",
        "accountId": "360770130721",
        "accessKeyId": "XXXXXXXXXXXXXXXX",
        "sessionContext": {
            "sessionIssuer": {
                "type": "Role",
                "principalId": "AROAVH74TKMQXE5UM6Q64",
                "arn": "arn:aws:iam::360770130721:role/gt-emerg-184-developer",
                "accountId": "360770130721",
                "userName": "gt-emerg-184-developer"
            },
            "attributes": {
                "creationDate": "2024-08-23T20:52:29Z",
                "mfaAuthenticated": "false"
            }
        }
    },
    "eventTime": "2024-08-23T21:09:31Z",
    "eventSource": "bedrock.amazonaws.com",
    "eventName": "StartIngestionJob",
    "awsRegion": "us-east-1",
    "sourceIPAddress": "161.151.119.200",
    "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36",
    "errorCode": "ValidationException",
    "requestParameters": {
        "dataSourceId": "DWXP9ZLNWL",
        "clientToken": "4b40d23b-e0cb-4ebe-b25c-83a78c8f9904",
        "knowledgeBaseId": "SLEUKNNA5O"
    },
    "responseElements": {
        "Access-Control-Expose-Headers": "x-amzn-Apigw-id,x-amzn-ErrorMessage,x-amzn-RequestId,x-amzn-ErrorType,x-amzn-Trace-id,refreshtoken,Date",
        "message": "The knowledge base storage configuration provided is invalid... The vector database encountered an error while processing the request."
    },
    "requestID": "743eafbe-0867-447e-9ae3-4a6520ebc6e1",
    "eventID": "65d3f189-3dc8-4e17-9e75-b244889ff999",
    "readOnly": false,
    "eventType": "AwsApiCall",
    "managementEvent": true,
    "recipientAccountId": "360770130721",
    "eventCategory": "Management"
}```
4

Hey there :wave:

This error occurred when the number of dimensions set in the embedding model differed from the number of dimensions set in Pinecone. Please check the number of dimensions you have set.