Skip to main content

Module inspect

Module inspect 

Source
Expand description

Inspection — what memory actually holds, for a person rather than a program.

Nobody trusts a memory they cannot read. graph status counts rows and graph search answers questions, but neither answers the question a human actually has after a week of automatic ingestion: what do you think you know about me, and how sure are you?

Two shapes answer it.

MemoryOverview is the unprompted one: the strongest things the graph holds, grouped by entity type, next to an honest account of how well its relationships are believed — including the coherence tally, which is the one number that says “some of this confidence is me agreeing with myself”.

TopicReport is the prompted one. It runs the ordinary hybrid query — no second retrieval path, no second set of scoring weights — and then attaches the evidence behind each hit, which retrieval itself has no reason to carry.

Structs§

ConfidenceSummary
How well the live relationships are believed.
KnownEntity
One entity as an overview lists it.
MemoryOverview
What the graph holds, without being asked about anything in particular.
TopicEntity
One retrieved entity, with the claims it takes part in.
TopicReport
What the graph holds about one subject.
TypeGroup
One entity type, and the strongest entities in it.

Constants§

DOUBTFUL_CONFIDENCE
Below this posterior mean, a relationship is barely believed at all.
STRONG_CONFIDENCE
At or above this posterior mean, a relationship is held firmly.

Functions§

about
Answer “what do you know about X” through the ordinary hybrid query, then attach the evidence behind each hit.
overview
Summarise the whole graph, listing per_type entities of each type.