jeevesagent.memory.redis_facts

Redis-backed bi-temporal fact store.

Each fact lives in a Redis hash at {prefix}{id} (default prefix jeeves:fact:). Fields:

• id / subject / predicate / object — strings

• confidence — string-encoded float

• valid_from_ts / recorded_at_ts — string-encoded floats

• valid_until_ts — string-encoded float ("0" when still valid)

• currently_valid — b"1" / b"0" flag (mirror of valid_until_ts == 0)

• sources — JSON-encoded list of episode ids

• embedding — float32 BLOB (only present when an embedder is configured)

Supersession is a brute-force scan: SCAN for all fact keys, find those with matching subject + predicate that are currently valid and have a different object, and HSET each to flip currently_valid=False + stamp valid_until_ts. RediSearch with HNSW + numeric/tag indexes is a follow-up.

Attributes

DEFAULT_KEY_PREFIX

Classes

RedisFactStore

Bi-temporal fact store over plain Redis hashes.

Module Contents

class jeevesagent.memory.redis_facts.RedisFactStore(client: Any, *, embedder: jeevesagent.core.protocols.Embedder | None = None, key_prefix: str = DEFAULT_KEY_PREFIX)

Bi-temporal fact store over plain Redis hashes.

async aclose() → None

async all_facts() → list[jeevesagent.core.types.Fact]

async append(fact: jeevesagent.core.types.Fact) → str

classmethod connect(url: str = 'redis://localhost:6379/0', *, embedder: jeevesagent.core.protocols.Embedder | None = None, key_prefix: str = DEFAULT_KEY_PREFIX) → RedisFactStore

Async:

async query(*, subject: str | None = None, predicate: str | None = None, object_: str | None = None, valid_at: datetime.datetime | None = None, limit: int = 10, user_id: str | None = None) → list[jeevesagent.core.types.Fact]

async recall_text(query: str, *, limit: int = 5, valid_at: datetime.datetime | None = None, user_id: str | None = None) → list[jeevesagent.core.types.Fact]

property embedder: jeevesagent.core.protocols.Embedder

jeevesagent.memory.redis_facts.DEFAULT_KEY_PREFIX = 'jeeves:fact:'