Originally written in French. Translated by AI — the meaning has been preserved, not the prose.
Short definition
The operation by which a source enters a knowledge base: it is read, its reusable elements are drawn from it, and the notes already present are updated, linked or set in contradiction.
Full definition
In data processing, the word ordinarily designates the loading of documents or records into a system — an operation of transport, which leaves the material as it was and touches nothing already stored.
In the articles on this blog, the word keeps the gesture of entry and changes what happens in it: ingestion is a work of writing on the existing base. Its visible output isn't the source filed somewhere, it is the neighbouring notes that have moved — a standard or a book on industrial maintenance whose entry into the base touches ten to fifteen notes already written.
The operation is governed by written rules — the "ingestion rules" — which define each type of note, its criteria of validity, what must be detected and in what vocabulary it must be written. Those rules are part of the apparatus just as much as the notes.
Usage in the field
Used to talk about a base's cost and quality: you calibrate ingestion rules, you measure an ingestion by the number of notes touched, you re-ingest a corpus after tightening the rules.
Synonyms and variants
"ingesting a source" for the act; "ingestion rules" for the body of instructions that governs it; "extraction pass" when the emphasis falls on what is produced.
Not to be confused with
- indexing — building an index allowing a document to be found again. It adds an entry without modifying the previous ones; ingestion modifies the existing base.
- Capture — the gesture of gathering a source or a thought at the moment, with no processing. It builds the entry stock; ingestion is what makes something of it.
- Distillation — the work of reducing material to what is essential in it. It describes an operation on a content; ingestion describes the entry of a source into an already constituted set.
Examples
An ingested source that produces no new note and sharpens three glossary definitions: the operation succeeded, even though the base didn't grow.
Ambiguities / debates
The word circulates between two worlds that don't give it the same weight: on the data side, ingesting is neutral and automatic; on the knowledge side, ingesting presupposes trade-offs — what to retain, what to set aside, what to connect. Using the term without lifting that ambiguity makes people underestimate the work on rules it covers.