ADR: Template-Enriched RAG for AI-Powered Template Generation #340
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
This ADR proposes a Template-Enriched RAG architecture for AI-powered OS image template generation. Key features include: - Self-describing templates with embedded metadata for semantic matching - Single search path with hybrid scoring (semantic + keyword + package) - Embedding cache strategy for fast startup - Conversational interaction for iterative template refinement - Query classification with adaptive scoring weights - Future agentic capabilities for auto-validation and self-correction The design enables natural language template generation grounded in real, working examples while maintaining simplicity and extensibility. Technical Area: AI/ML, Template Generation Status: Proposed
Contributor
There was a problem hiding this comment.
Copilot wasn't able to review any files in this pull request.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
arodage
requested review from
elvin03,
magerstam,
samueltaripin,
srmungar and
yockgen
The initial commit had empty content. This commit adds the full ADR document with: - Problem statement and context - Template metadata schema - High-level architecture with Mermaid diagrams - Query classification and hybrid scoring - Embedding cache strategy - Conversational interaction flow - Agentic capabilities (future enhancement) - Implementation phases and configuration
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Outdated suggestions cannot be applied.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.
Merge Checklist
All boxes should be checked before merging the PR
Description
This PR adds an Architecture Decision Record (ADR) proposing a Template-Enriched RAG architecture for AI-powered OS image template generation.
Summary:
The design embeds semantic metadata directly within template files, enabling self-describing templates that can be effectively indexed and retrieved using natural language queries. Users can interact conversationally to generate and iteratively refine templates through natural language.
Key Features:
Document Structure:
Any Newly Introduced Dependencies
None. This is a documentation-only change (ADR proposal).
How Has This Been Tested?