Implemented Schema-Aware In-Session Caching to Optimize LLM Visualization Recommendations#69
Open
ojumah20 wants to merge 1 commit into
Open
Conversation
Collaborator
|
Hi @ojumah20, there are some conflicts that need to be addressed before the merge; can you investigate, please? |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR introduces a robust in-session caching layer for the visualization recommendation pipeline.
It significantly improves performance, reduces duplicate LLM calls, and ensures deterministic, privacy-safe caching across sessions.
Key Changes
Added viz_cache.py:
Implements MemoryTTLCache (thread-safe, TTL, LRU, dogpile-safe).
Includes metrics (hits, misses, evictions, hit_rate, etc.).
Supports namespaced keys (model: / ensemble:).
Optional background cleanup and TTL jitter.
Updated recommender.py:
Integrated caching at model-response and ensemble-result levels.
Added version pins (code_version, prompt_version) to auto-invalidate old cache entries.
Added debug mode cache stats for visibility.
Introduced schema_signature()-based keys to ensure privacy (no row data stored).
Updated package-level init.py for clean imports and reusability.