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` file
  • dim - 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 ID
  • modality - (v0.5.0) Multi-modal index target
  • metadata - 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 edges
  • modality - 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)