Skip to Content

Features

Ranking

The signals Docklee combines to decide which memories a recall returns, and in what order.

Similar words aren't enough to find the right memory. "What did the customer prefer before the redesign?" needs a memory that's about the customer, from the right time, and still trusted. Docklee ranks every recall on several signals at once.

Five signals

SignalAsks
RelevanceHow closely does this memory answer the question?
ValidityIs this memory still current, or has it been replaced?
ConfidenceHow much does Docklee trust this memory? See Confidence.
ConnectionsHow many other memories link to this one?
RecencyHow recently was this memory created or recalled?

The question shapes the weights

Before ranking, Docklee reads the question and decides which links to follow and which signals matter most.

The questionDocklee leans on
Names a person, company, or productEvery memory about that entity
Uses "before", "after", "when", or "timeline"Memories in time order
Uses "why", "because", or "led to"Cause and effect links
Anything elseMeaning

Meaning is always part of the search, so a recall never returns less than a plain search would.

Ask better questions

Instead ofAsk
"maya email""How does Maya like to be contacted?"
"renewal""What happened before Northwind renewed?"
"cancel""Why did the customer cancel?"
records = lynk.recall_sync("What happened before Northwind renewed?", top_k=10)

Pass the user's own message as the query. It already carries the names and time words that ranking uses.

Next steps

You know how recall decides. Capture memories automatically next.

On this page