feat: add support to include application inference profiles as models #131
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
theTechie
changed the title
|
@daixba can you review this please? |
- Remove complex is_matching_application_profile function - Implement O(1) lookup using dictionary mapping instead of O(n×m) iteration - Add comprehensive error handling and input validation - Add detailed logging for debugging and monitoring - Improve robustness with defensive programming patterns - Handle edge cases like missing ARNs, empty models, invalid data structures - More efficient model ID extraction from ARNs - Better separation of concerns between system and application profiles
- Remove excessive code formatting changes to improve review readability - Keep only essential functional improvements for application inference profiles - Maintain original code style from main branch - Preserve O(1) lookup optimization with dictionary mapping - Add basic error handling without verbose logging - Focus on core functionality: ENABLE_APPLICATION_INFERENCE_PROFILES support
…templates - Add arn:aws:bedrock:*:*:application-inference-profile/* to IAM policy resources - Required for invoking application-defined inference profiles - Update both Lambda (BedrockProxy.template) and Fargate (BedrockProxyFargate.template) templates - Ensures complete support for Application Inference Profiles feature in PR aws-samples#131
- Add Application Inference Profiles to features list - Include dedicated section with usage examples for both API and SDK - Provide sample code for using application inference profile ARNs - Document benefits: cost tracking, usage monitoring, tag-based cost allocation - Reference official AWS documentation for profile creation and management
|
@theTechie Thanks for your contribution. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
New feature support: Add support for listing application defined inference profiles as models
Description of changes:
As AWS uses system defined inference profiles for cross region inference models/profiles, we can also define custom application defined inference profiles based on foundation models.
This gives flexibility to define profiles for different purposes for segregation and cost tracking purposes. I am using it in a project for cost tracking purposes using AWS tags attached to application inference profiles.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.