add cachePoint to messages

[nalbion]

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Fixes # #17895

GA for Sonnet 3.7 & Haiku 3.5 as of today - https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html

Needs botocore 1.37.25 - boto/botocore@84c9bc4#diff-f8e2002ec5dd2b5567da9fc62aa733ebd26a8a0be2cbe6900d392526138ae5dd

Note: prompt caching for system prompt & tool specs can be enabled by adding the following kwargs to llm.achat_with_tools():

• system=[{"cachePoint": {"type": "default"}}]
• toolConfig={"tools": [{"cachePoint": {"type": "default"}}]}

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No

Type of Change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[nalbion]

@logan-markewich would you be able to help to get this passing CI?

[nalbion]

possibly blocked by aio-libs/aiobotocore#1315

[logan-markewich]

Hmm, is aioboto3 = "^13.1.1" the right dep here? Should it also be bumped? We could confirm this locally by running poetry lock I think

[yarikama]

This PR needs to wait until aiobotocore is updated to 2.22.1 and aioboto3 to 14.4.0. Otherwise, even though boto3 and aioboto3 can individually use prompt caching, there will be version conflicts when they coexist.
Note: boto3 needs to be 1.37.24 or later, and aioboto3 needs to be 14.2.0 or later. However, aioboto3 depends on aiobotocore (2.22.0), which restricts boto3 to be between 1.37.2 and 1.37.4.