Added AmazonBedrockVectorizer class

[dgallitelli]

There was no SentenceVectorizer that leveraged Amazon Bedrock. I've created one.

[arnavsinghvi11]

could this potentially be replaced with the existing DSPy AWS model integrations? would be neat to tie it in!

[dgallitelli]

I'm not exactly sure what you would like to see here to be honest 🤔

[arnavsinghvi11]

would appreciate a more informative exception message :).

[arnavsinghvi11]

Update with try/except block like in aws_providers.

[arnavsinghvi11]

Thanks @dgallitelli for the PR! left a few comments with the main change required in wrapping the import boto3 with a try/except block to pass the failing the tests.

Also, please run ruff check . --fix-only and push to pass the failing ruff test.

[dgallitelli]

Thanks @arnavsinghvi11 for your comments! I've addressed the wrapping of boto3 and the more explicit error messaging, and pushed the updates to the branch. Also, I've run the ruff test, with the following output:

warning: The top-level linter settings are deprecated in favour of their counterparts in the `lint` section. Please update the following options in `pyproject.toml`:
  - 'extend-unsafe-fixes' -> 'lint.extend-unsafe-fixes'
warning: Docstring at dspy/teleprompt/mipro_optimizer.py:111:9 contains implicit string concatenation; ignoring...
warning: Docstring at dspy/teleprompt/mipro_optimizer.py:122:9 contains implicit string concatenation; ignoring...

This makes me think that all is good so far.

I'm not sure your point about the existing DSPy AWS model integrations. What would you be looking for here? A new AWSBedrockEmbedding class? Just switching the boto3 client to the DSPy AWSProvider? I think that can be a separate Issue and PR.

[arnavsinghvi11]

Thanks @dgallitelli . Yes I was curious if the boto3 client could be switched to use the supported DSPy AWS providers. Would be a seamless way to tie in the DSPy library together.