Added KB examples and tests and updated metadata file #7451
Conversation
github-actions
bot
added
the
Python
…agraphs in incorrect segments to correct custom blocks. Some information was lost, for list flows, which does not have a current scenario in metadata.
| parser = argparse.ArgumentParser( | ||
| description="Work with knowledge bases in your AWS account." | ||
| ) | ||
| parser.add_argument( |
There was a problem hiding this comment.
Is it possible to run these steps together as a set? For example: Create a KnowledgeBase, List, Get, Update, then Delete? With the role created as part of the process? Otherwise the user has to know what the required Role will look like, and provide the arn. We try to have scenarios be self-contained. For more information, see the example standards. If this is not possible for some reason and an exception needs to be made, let us know.
There was a problem hiding this comment.
Hey @gausekha, did you have a chance to review Rachel's note here?
There was a problem hiding this comment.
Hey @rlhagerm and @beqqrry-aws my apologies got caught up with a few things and didn't get a chance! Shall check and get back on this. It should be possible to run the examples in a set using the created role shall confirm and get back on it.
There was a problem hiding this comment.
@rlhagerm and @beqqrry-aws I just added the IAM role and a scenario: gausekha@0dec32e. I am trying to run this locally but keep running into an error about specifying the region. Could you please take a look?
There was a problem hiding this comment.
Hi @gausekha , I'm not getting any error about the region. Maybe you need to specify it in your profile? What I am getting is this, which seems to be a problem with the specified CollectionArn. I don't think it's supposed to be the same as the embeddingModelArn.
botocore.errorfactory.ValidationException: An error occurred (ValidationException) when calling the CreateKnowledgeBase operation: 1 validation error detected: Value 'arn:aws:bedrock:us-east-1::foundati on-model/amazon.titan-embed-text-v1' at 'storageConfiguration.opensearchServerlessConfiguration.collectionArn' failed to satisfy constraint: Member must satisfy regular expression pattern: arn:aws(-cn|- us-gov|-eusc|-iso(-[b-f])?)?:aoss:([a-z]{2,}-){2,}\d:\d{12}:collection/[a-z0-9-]{3,32}
There was a problem hiding this comment.
Ah, I see - got it that makes sense. Shall update it, thanks for catching it! And yes, shall try to update my profile as well and get a clean build before pushing the next commit.
There was a problem hiding this comment.
@rlhagerm Please LMK once you have a chance to look at this. Thanks!
There was a problem hiding this comment.
Is the CollectionArn something the user is supposed to provide? It looks like what is in there now is a placeholder, which may be fine, but we should include some information on how to provide the correct value and/or replace it in the code.
…-doc-sdk-examples into gausekha-kb-python-examples
| "storageConfiguration": { | ||
| "type": "OPENSEARCH_SERVERLESS", | ||
| "opensearchServerlessConfiguration": { | ||
| "collectionArn": "arn:aws:aoss:us-east-1::123456789012:collection/abcdefgh12345678defgh", |
There was a problem hiding this comment.
So, does the collection arn come from a pre-existing collection? Does the user need to configure it somewhere first and provide it as an input? It seems unclear how the arn is set.
This pull request adds code examples for the APIs CreateKnowledgeBase, GetKnowledgeBase, UpdateKnowledgeBase, DeleteKnowledgeBase, and ListKnowledgeBases APIs. The same submission was made earlier but running the writeme created a large number of file diffs. This submission hopes to avoid such a large commit.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.