Loading source

Preparing the source view

Pulling the file list, source metadata, and syntax-aware rendering for this listing.

Source from repo

Azure AI Services

Guidance for building and deploying AI solutions on Azure using Azure AI services and Copilot for Azure

microsoftGitHub microsoftOfficialSource repo Original GitHub link Publisher page

Files

17

Skill

n/a

Size

28.2 KB

Entrypoint

SKILL.md

Format

git-repo

Open file

references/sdk/azure-ai-document-intelligence-ts.md

Syntax-highlighted preview of this file as included in the skill package.

Rendered Source

markdown34 linesFree

Azure Document Intelligence — TypeScript SDK Quick Reference

Condensed from azure-ai-document-intelligence-ts. Full patterns (custom models, classifiers, batch polling) in the azure-ai-document-intelligence-ts plugin skill if installed.

Install

npm install @azure-rest/ai-document-intelligence @azure/identity

Quick Start

Auth: DefaultAzureCredential is for local development. See auth-best-practices.md for production patterns.

import DocumentIntelligence, { isUnexpected, getLongRunningPoller, AnalyzeOperationOutput } from "@azure-rest/ai-document-intelligence";
const client = DocumentIntelligence(endpoint, new DefaultAzureCredential());

Non-Obvious Patterns

REST client — DocumentIntelligence is a function, not a class
Analyze path: client.path("/documentModels/{modelId}:analyze", "prebuilt-layout").post({...})
Must use getLongRunningPoller(client, initialResponse) then poller.pollUntilDone()
Local file: send as base64Source in body, not as binary stream
Pagination: import { paginate } from "@azure-rest/ai-document-intelligence"

Best Practices

Use getLongRunningPoller() — document analysis is async, always poll
Check isUnexpected() — type guard for proper error handling
Choose the right model — prebuilt when possible, custom for specialized docs
Handle confidence scores — set thresholds for your use case
Use paginate() helper for listing models
Prefer neural mode for custom models over template