docs: PLAN-v0.30 hybrid LLM knowledge-graph upgrade#9
Merged
Conversation
Design plan for a hybrid graph: deterministic structural core (default, zero-LLM, replay-safe) + an opt-in LLM semantic layer (OpenIE entity/relation triples via a local model) that closes the entity-composition multi-hop gap. ADD-only with structural precedence, so the existing REFERENCES/CONTAINS edges and the bit-identical default are never touched. Grounded in source; includes phased roadmap, eval gates, 10TB cost model, and risk register.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
docs/PLAN-v0.30-hybrid-llm-graph.md— a design plan for adding an opt-in LLM semantic layer (OpenIE entity/relation extraction via a local model) on top of the existing deterministic structural core.Key properties:
_openieand revertible.llm+openie_enabled); default path stays byte-for-byte zero-LLM (regression-gated).🤖 Generated with Claude Code