New serverless pattern - s3-vectors-lambda-bedrock-cdk#3055
Open
NithinChandranR-AWS wants to merge 3 commits intoaws-samples:mainfrom
Open
Conversation
- Fix Bedrock model ID default (add -v1:0 suffix for inference profile) - Rename VectorBucketName output to avoid CfnParameter name collision Tested: CDK synth verified, deployed to AWS account
- Scope bedrock:InvokeModel to Titan Embeddings and Claude inference profile ARNs instead of wildcard - Add s3vectors:DeleteVectorBucket and s3vectors:DeleteVectorIndex to prevent stack rollback getting stuck in DELETE_FAILED - Note: s3vectors does not support resource-level ARNs yet
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 Serverless Pattern: S3 Vectors with Lambda and Amazon Bedrock RAG
Description
Deploys a serverless RAG (Retrieval-Augmented Generation) pipeline using Amazon S3 Vectors for cost-optimized vector storage, Lambda for orchestration, and Amazon Bedrock for embeddings (Titan V2) and generation (Claude).
Architecture
Ingest Lambda → Bedrock Titan Embeddings V2 → S3 Vector Index (1024-dim, cosine)
Query Lambda → Bedrock Titan Embeddings V2 → S3 Vectors (similarity search) → Bedrock Claude → Answer
Key Features
Framework / Language
Testing