Prebuilt parent analyzer for a given modality (prebuilt-document, prebuilt-image, prebuilt-audio or prebuilt-video), from which a custom analyzer inherits by setting baseAnalyzerId.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Base analyzer in context, with comparison tables and the common traps.
Terms in this definition
- Content Understanding analyzer
Defines in Content Understanding how input is processed and what fields come out, either through a prebuilt analyzer or through a field schema you write yourself.
- General document model
A retired Document Intelligence model (
prebuilt-document) that pulled out key-value pairs. Since v4.0 the layout model with itskeyValuePairsfeature covers this job. - prebuilt-image
Base analyzer in Content Understanding for still images. PDFs are rejected and must go to a document analyzer instead.
- prebuilt-audio
Base Content Understanding analyzer for audio. Before any fields are extracted, it produces a WebVTT transcript with speakers separated by diarization.
- prebuilt-video
Base video analyzer in Content Understanding. It extracts the transcript, shots and keyframes, and can split the footage into scenes.
Related terms
- Custom analyzer (Content Understanding)
Built on top of a base analyzer like prebuilt-document, this is where you add a field schema, methods and validation instructions of your own in Content Understanding.
- prebuilt-document
Base analyzer in Content Understanding for forms, Office files and PDFs, scanned ones included. The OCR and layout analyzers are built on top of it.