Skip to Content

Core Concepts

How knowledge works

How your content becomes searchable knowledge, and how an engine turns a question into a cited answer.

Knowledge Engines answer questions from your own content. You connect sources or write with Dock. Docklee processes the content in containers, and an engine searches the sources linked to it when your app calls Lynk.

Read this page before you design your engines. It explains why an engine answers only from what you link to it, and how each answer is checked against your sources.

  1. 01ContentConnected sources, and Dock writes that declare a container.
  2. 02ContainerChunks, extracts, and embeds, or builds OKF concepts.
  3. 03EngineSearches its linked sources and ranks what it finds.
  4. 04LynkReturns a cited answer, a stream, or the context itself.
Content is processed once in a container. Any engine that links to it can then answer from it.

Without and with Docklee

Without DockleeWith Docklee
You build parsing, chunking, embeddings, and a vector store for each project.Containers do the processing, and engines share them.
Each assistant keeps its own copy of the same documents.A source connects once and links to any engine.
The model can cite things it never saw.Citations are checked against the chunks the engine used, and invalid ones are removed.
Answers drift beyond your content.The default mode answers only from your sources, and says so when the answer isn't there.
Keyword search and semantic search are separate systems.An engine searches vector and OKF sources together and merges the results.

What you send and what's stored

You sendDocklee stores
A 40-page product manual, connected in SourcesChunks with their page numbers and section titles, embedded in a vector container
dock.capture("Refunds are available within 30 days.", type="knowledge")A chunk in the container's API/SDK Feed source
A wiki connected to an OKF containerConcepts, one per topic, and the links between them

On ingest

  1. Arrive. Content comes from a connected source, or from Dock with a container. See Capture knowledge.
  2. Process. A vector container splits content into chunks, keeps page numbers and section titles, and embeds each chunk. An OKF container builds concepts and the links between them. See Containers.
  3. Wait for a link. Processed content belongs to a source. No engine reads it until you link that source to the engine. See Engines.

On query

  1. Search. The engine searches every source linked to it, by meaning in vector sources and by concepts and their links in OKF sources.
  2. Rank. The best results are re-ranked against your question, and the top chunks are kept.
  3. Answer. For lynk.query, a model writes the answer from those chunks only, following the engine's answer mode. For lynk.retrieve, the chunks themselves are returned.
  4. Check. Each citation is checked against the chunks the engine used. Citations to anything else are removed, and confidence is adjusted to match. See Citations and confidence.

Where knowledge lives

KnowledgeLives inRead by
A connected sourceA vector or OKF container, chosen when you add itEvery engine it's linked to
A Dock knowledge writeThe container's API/SDK Feed sourceEvery engine the feed is linked to
A Precision Mode answerIts container, prepared ahead of timeEvery engine that reads the container

Build with this flow

  • Link only the sources an engine should answer from. Every linked source can show up in its answers.
  • Keep one vector dimension per engine.
  • Use lynk.query when Docklee should write the answer, and lynk.retrieve when your own model should.
  • Show citations in your UI so people can check an answer against the source.
  • Treat a low confidence score as a reason to say "I'm not sure", not as an answer.

Next steps

You know how knowledge flows. Start by sending your own content.

On this page