Open
Conversation
This module provides production-ready configuration for Amazon Bedrock Knowledge Bases with vector database integration for RAG (Retrieval-Augmented Generation): - Knowledge base creation with vector embeddings - Multiple storage backends: OpenSearch Serverless, RDS (Aurora PostgreSQL), Pinecone - S3 data source integration with automatic ingestion - Customizable chunking strategies (fixed-size or none) - Support for multiple embedding models (Amazon Titan, Cohere) - Automatic IAM role and policy management - Document filtering with S3 inclusion prefixes Features: - OpenSearch Serverless configuration with custom field mappings - RDS Aurora PostgreSQL with pgvector support - Pinecone integration for external vector databases - Fixed-size chunking with configurable tokens and overlap - Data deletion policies for compliance - Comprehensive outputs including CLI and Python examples Includes: - Complete module implementation (main.tf, variables.tf, outputs.tf) - Basic test: Simple knowledge base with OpenSearch Serverless - Advanced test: Full production setup with custom chunking and filtering - Comprehensive documentation with RAG patterns and best practices
Contributor
|
✅ Terraform formatting has been automatically applied to this PR. |
Contributor
🔍 Terraform Check Results📊 Summary🔴 Some checks failed
🔍 TFLint Details (0 issue(s))🔒 Trivy Security Details (33 issue(s))👤 Pusher: @llama90 | 🔄 Action: |
Remove data source dependencies that require API calls: - Remove aws_caller_identity and aws_region data sources - Remove IAM role condition constraints that required account_id/region - Replace region in model ARN outputs with wildcards (*) - Remove region and account_id outputs This allows terraform plan to run without actual AWS credentials.
Contributor
🔍 Terraform Check Results📊 Summary🔴 Some checks failed
🔍 TFLint Details (0 issue(s))🔒 Trivy Security Details (33 issue(s))👤 Pusher: @llama90 | 🔄 Action: |
- Reduce from 483 lines to ~66 lines (ultra-minimal) - Remove all verbose use cases and tutorials - Remove duplicated code examples (vector databases, embedding models, etc) - Simplify Quick Start (removed S3/OpenSearch creation) - Add terraform-docs section with <details> - Follow exact structure: Features, Quick Start, Examples, Testing, Docs - Limit features to 8 items - Reference tests/ instead of duplicating code Follows DOCUMENTATION_GUIDELINES.md pattern like ec2 module.
Contributor
🔍 Terraform Check Results📊 Summary🔴 Some checks failed
🔍 TFLint Details (0 issue(s))🔒 Trivy Security Details (33 issue(s))👤 Pusher: @llama90 | 🔄 Action: |
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
2 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.
This module provides production-ready configuration for Amazon Bedrock Knowledge Bases with vector database integration for RAG (Retrieval-Augmented Generation):
Features:
Includes:
Type of Change
Checklist
Module Information
Module Path:
terraform/___________Purpose:
Key Resources:
Additional Notes
Related Issues
Closes #