Microsoft Azure · OpenAPI Overlay 1.0.0
API Evangelist conversational phrasing for Microsoft Azure Form Recognizer Client Custom API
9 actions
9 updates
phrasing
extends
openapi/microsoft-azure-custom-api-openapi.yml
Generated by API Evangelist
Written by API Evangelist tooling for Microsoft Azure's API. It is a proposal applied on top of the contract, not a document Microsoft Azure publishes.
What the actions change
x-apievangelist-phrasing
Targets 9
$.info
$.paths['/custom/models'].post
$.paths['/custom/models/{modelId}'].get
$.paths['/custom/models/{modelId}'].delete
$.paths['/custom/models/{modelId}/analyze'].post
$.paths['/custom/models/{modelId}/analyzeResults/{resultId}'].get
$.paths['/custom/models/{modelId}/copy'].post
$.paths['/custom/models/{modelId}/copyResults/{resultId}'].get
$.paths['/custom/models/copyAuthorization'].post
OpenAPI Overlay
# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
title: API Evangelist conversational phrasing for Microsoft Azure Form Recognizer Client Custom API
version: 1.0.0
extends: openapi/microsoft-azure-custom-api-openapi.yml
actions:
- target: $.info
update:
x-apievangelist-phrasing:
method: generated
generated: '2026-09-26'
generator: build-phrasing.py
label: Generated by API Evangelist
operations: 8
- target: $.paths['/custom/models'].post
update:
x-apievangelist-phrasing:
intent: Train a custom Form Recognizer model
effect: write
questions:
- How do I train a custom form model from documents in a blob container?
- Can I train using my own label files instead of unsupervised learning?
instructions:
- text: Train a custom model from training data at {source}.
slots:
source: requestBody.source
- text: Train custom model {modelName} from {source} using label files set to {useLabelFile}.
slots:
modelName: requestBody.modelName
source: requestBody.source
useLabelFile: requestBody.useLabelFile
method: generated
generated: '2026-09-26'
- target: $.paths['/custom/models/{modelId}'].get
update:
x-apievangelist-phrasing:
intent: Get details of a custom form model
effect: read
questions:
- Has my custom form model finished training, and what fields did it learn?
- Can I see the extracted keys a custom model recognizes?
instructions:
- text: Get custom model {modelId}.
slots:
modelId: path.modelId
- text: Show custom model {modelId} including its keys ({includeKeys}).
slots:
modelId: path.modelId
includeKeys: query.includeKeys
method: generated
generated: '2026-09-26'
- target: $.paths['/custom/models/{modelId}'].delete
update:
x-apievangelist-phrasing:
intent: Delete a custom form model
effect: destructive
questions:
- How do I get rid of a custom form model I no longer use?
- Are a deleted model's artifacts removed immediately or later?
instructions:
- text: Delete custom model {modelId}.
slots:
modelId: path.modelId
- text: Mark form model {modelId} for deletion.
slots:
modelId: path.modelId
method: generated
generated: '2026-09-26'
- target: $.paths['/custom/models/{modelId}/analyze'].post
update:
x-apievangelist-phrasing:
intent: Analyze a form with a custom model
effect: write
questions:
- How can I extract key-value pairs and tables from a PDF using my custom model?
- Which file types can I send to a custom model for analysis?
- Can I analyze only certain pages of a document?
instructions:
- text: Analyze this document with custom model {modelId}.
slots:
modelId: path.modelId
- text: Run custom model {modelId} on pages {pages} and include text details.
slots:
modelId: path.modelId
pages: query.pages
method: generated
generated: '2026-09-26'
- target: $.paths['/custom/models/{modelId}/analyzeResults/{resultId}'].get
update:
x-apievangelist-phrasing:
intent: Get the result of a custom form analysis
effect: read
questions:
- Is my custom model form analysis done, and what did it extract?
- Where do I pick up the output of an analyze form request?
instructions:
- text: Get analyze result {resultId} for custom model {modelId}.
slots:
resultId: path.resultId
modelId: path.modelId
- text: Check the status of form analysis {resultId}.
slots:
resultId: path.resultId
method: generated
generated: '2026-09-26'
- target: $.paths['/custom/models/{modelId}/copy'].post
update:
x-apievangelist-phrasing:
intent: Copy a custom model to another Form Recognizer resource
effect: write
questions:
- How do I move a trained custom model into a different Form Recognizer resource or region?
- What do I need from the target resource before copying a model?
instructions:
- text: Copy custom model {modelId} to resource {targetResourceId} in {targetResourceRegion} with authorization {copyAuthorization}.
slots:
modelId: path.modelId
targetResourceId: requestBody.targetResourceId
targetResourceRegion: requestBody.targetResourceRegion
copyAuthorization: requestBody.copyAuthorization
- text: Start copying model {modelId} into the target Form Recognizer resource {targetResourceId}.
slots:
modelId: path.modelId
targetResourceId: requestBody.targetResourceId
method: generated
generated: '2026-09-26'
- target: $.paths['/custom/models/{modelId}/copyResults/{resultId}'].get
update:
x-apievangelist-phrasing:
intent: Get the status of a custom model copy
effect: read
questions:
- Has my custom model copy to the other resource completed?
- Can I check whether a model copy operation failed?
instructions:
- text: Get copy result {resultId} for model {modelId}.
slots:
resultId: path.resultId
modelId: path.modelId
- text: Check progress of model copy {resultId}.
slots:
resultId: path.resultId
method: generated
generated: '2026-09-26'
- target: $.paths['/custom/models/copyAuthorization'].post
update:
x-apievangelist-phrasing:
intent: Generate authorization to copy a model into this resource
effect: write
questions:
- How do I authorize another Form Recognizer resource to copy a model into mine?
- Where does the copy authorization token for a model copy come from?
instructions:
- text: Generate a model copy authorization on this target resource.
- text: Create a copy authorization so a model can be copied into this Form Recognizer resource.
method: generated
generated: '2026-09-26'
Work with this as data
Every overlay here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for openapi overlays
4 MCP tools reach this
find_overlaysBrowse and filter every overlay in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This overlay
curl "https://apis.io/api/v1/overlays/microsoft-azure-custom-api-phrasing-overlay"
All openapi overlays
curl "https://apis.io/api/v1/overlays?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.