Releases: feather-store/feather
Releases · feather-store/feather
v0.5.0 — Context Graph + Living Context Engine
What's New in v0.5.0
Context Graph
- Typed weighted edges —
Edgestruct{target_id, rel_type, weight}replaces flat links list - Reverse index —
get_incoming(id)for instant reverse-edge lookups, rebuilt on load db.link(from_id, to_id, rel_type, weight)— create typed directed edges between recordsdb.auto_link(modality, threshold, rel_type)— automatically link similar vectors by cosine threshold- 9 built-in relationship types via
RelType:related_to,caused_by,supports,part_of,derived_from,contradicts,precedes,references,multimodal_of
Living Context Engine
db.context_chain(query, k, hops, modality)— vector search + n-hop BFS graph expansion in one call, returnsContextChainResultwith scored nodes and traversed edges- Adaptive decay —
stickiness = 1 + log(1 + recall_count)makes frequently accessed records resist temporal decay
Graph Visualizer
visualize(db, output_path)— exports a fully self-contained D3 force-graph HTML (no CDN, works offline)export_graph_json(namespace_filter, entity_filter)— D3/Cytoscape-compatible JSON export- Dangling edge safety — edges referencing excluded nodes are automatically filtered
Inspector
feather_inspector.py— local HTTP inspector with force graph view, PCA embedding scatter, similarity search, edit and delete
New Methods
db.get_vector(id, modality)— retrieve raw vector as NumPy arraydb.get_all_ids(modality)— list all IDs in a modality indexdb.update_metadata(id, meta)— update metadata without touching the HNSW indexdb.update_importance(id, importance)— adjust importance score in-place
File Format
- Bumped to v5 — adds typed edges with rel_type + weight; v3/v4 files load transparently
Install
pip install feather-db
cargo install feather-db-cli