docs: vector subsystem evaluation#2
Open
sternryan wants to merge 1 commit into
Open
Conversation
Analyzes both parallel vector-search implementations that coexist after the upstream merge (internal/embedding/ vs internal/vector/) and makes an opinionated recommendation: keep upstream's internal/vector/, delete the fork's internal/embedding/ + internal/ai/. Primary driver: internal/embedding/ is hardcoded to Azure OpenAI and requires an internet-connected paid API for every search query — fundamentally incompatible with msgvault's offline/local-first goal. internal/vector/ accepts any OpenAI-compatible endpoint including local servers (Ollama, llama.cpp). Secondary drivers: ~12× more test coverage in B, generation lifecycle management, crash-safe pending queue, structured query filters, and a single-CTE hybrid path. The merge already rerouted --hybrid to B. Doc includes comparison matrix, migration plan for keeping B, and a concrete deletion checklist for A. https://claude.ai/code/session_01DSeN4Gajp1JpsDdLgnREjU
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Keep
internal/vector/(Subsystem B). Deleteinternal/embedding/+internal/ai/(Subsystem A).Subsystem A is hardcoded to Azure OpenAI — a paid cloud API required for every search query, including at search time — which is architecturally incompatible with msgvault's offline/local-first goal. Subsystem B accepts any OpenAI-compatible endpoint, including local servers (Ollama, llama.cpp), and runs search fully offline once the index is built.
See
docs/vector-subsystem-decision.mdfor the full analysis: comparison matrix across offline-alignment, maintainability, test coverage, and performance; migration plan for keeping B; and a concrete deletion checklist for A (files, schema migrations, flag removals, doc updates).Generated by Claude Code