Documentation / API
API Reference.
Complete API reference for Feather v0.5.0. Explore the core DB methods alongside newly introduced Context Graph functions.
DB.open(filename, dim)
Initializes a new or existing Feather database using the flat binary format.
db = DB.open("vectors.feather", dim=384)Parameters
filename- Path to the `.feather` filedim- Vector dimension (globally scoped in v0.5.0)
db.add(id, vector, modality="text", metadata=None)
Injects a vector under a specific entity ID. The new modality parameter places this vector into a scoped HNSW index.
db.add(1, vector, modality="visual", metadata={"label": "example"})Parameters
id- Entity IDmodality- (v0.5.0) Multi-modal index targetmetadata- JSON-compatible metadata
NEW IN V0.5.0
db.context_chain(query, k=5, hops=2, modality="text")
Performs a semantic vector search, followed instantly by a configured N-hop BFS expansion across the Context Graph.
results = db.context_chain(query, k=3, hops=2, modality="text")Parameters
hops- BFS depth across tracked entity edgesmodality- The vector space to seed the graph expansion from
db.search(query, k=10, filter=None, time_weight=False)
Standard approximate nearest neighbor (ANN) search.
results = db.search(query, k=5, time_weight=True)