Skip to content

Evaluate a local embedding router on semantic routing challenges #55

Closed

Description

@triggeredcode

Extend the offline routing experiment with semantic paraphrases and near-miss cases, then compare Lucid current deterministic routing with a small local embedding candidate.

Scope:

  • Keep this experiment-only; no runtime integration.
  • Add family-isolated semantic and negative challenge cases.
  • Support an optional local Ollama embedding adapter.
  • Record accuracy, high-confidence wrong direct actions, abstention/clarification behavior, and latency.
  • Test installed local embedding models without committing model files or generated reports.

Adoption rule: a local model must improve meaningful semantic coverage without introducing unsafe confident actions or unacceptable latency. If the deterministic router remains sufficient, record that result and do not add runtime complexity.

Activity

  1. triggeredcode commented on Oct 20, 2026

    @triggeredcode
    OwnerAuthor

    Implemented and measured in PR #56. The honest de-leaked result is: current 37/46, calibrated Nomic 42/46, calibrated Qwen 39/46. Nomic is smaller and faster, but its 55.6% semantic scope accuracy is not sufficient for runtime adoption, so this PR keeps the model path experiment-only.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions