Skip to content

v0.4.13 - Remove embedding models and semantic search for keyword-only matching and faster CI/CD.

Latest
Latest

Choose a tag to compare

View all tags
@LuizEduPP LuizEduPP released this 25 Jun 23:31
v0.4.13
f6a56b3
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Removed

  • sentence-transformers and numpy dependencies; embedding model code, /api/models, fetch-model CLI, and semantic config keys.
  • Dead embedding cache files (embeddings.npy, embeddings.hash) from store init, gitignore, and storage listings.
  • semantic_scope from write/consolidate APIs and MCP handlers; consolidate is section-scoped exact duplicate cleanup only.

Changed

  • Install and CI are much lighter without PyTorch or embedding model downloads; search remains keyword/token matching with agent-side relevance.
  • GitHub Actions uses uv with dependency caching, Python 3.12 only on PRs, path filters to skip docs-only runs, and Buildx cache for Docker smoke tests.
  • Documentation aligned with keyword-only runtime: README, COMPATIBILITY, SECURITY, and CONTRIBUTING.
Assets 2
Loading