azure-ai-formrecognizer
Microsoft Azure Form Recognizer Client Library for Python
Decision gist · record as of 2026-08-14
Yes, if you have an Azure subscription and need to extract structured data from documents at scale. The library is production-stable, actively maintained, has no known vulnerabilities, and integrates cleanly with the broader Azure SDK ecosystem. Install only if you are committed to using Azure's Document Intelligence service; it is not a standalone solution and requires cloud resources and API credentials.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an Azure subscription and a Form Recognizer or Cognitive Services resource with endpoint and API key.
- Low friction installation with a pure Python wheel.
- Actively maintained as of 2026-08-14 with no known vulnerabilities.
License · maintenance · safety
MIT License (permissive) — MIT License permits commercial and private use with minimal restrictions, making it suitable for most production scenarios.
last release 2024-04-09 (857 days) · last repo commit 2026-08-14 · 5,588 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,897,067 downloads/mo, #3,451 on PyPI
Alternatives
Verify before relying
pip install azure-ai-formrecognizer
from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer import DocumentAnalysisClient
endpoint = "https://<resource>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")
client = DocumentAnalysisClient(endpoint, credential)
result = client.begin_analyze_document_from_url("prebuilt-receipt", url).result()- Whether prebuilt models cover all document types your use case requires (receipts, invoices, business cards, ID documents, W-2 tax forms mentioned but completeness unclear).
- Performance characteristics and latency for large-batch document processing.
- Exact pricing and cost implications of using different API versions (2023-07-31 default vs. older versions).
What it is and what it does
Azure Form Recognizer is a Python client library for Microsoft's Document Intelligence cloud service, which uses machine learning to extract structured data from documents. It provides both prebuilt models for common document types (receipts, invoices, business cards, ID documents, tax forms) and the ability to train custom models on your own data. The library handles layout extraction (words, selection marks, tables), key-value pair analysis, document classification, and optional add-ons like barcode/QR code detection and formula extraction.
The package wraps Azure's REST API and requires an active Azure subscription with a Form Recognizer resource. It supports multiple service API versions (2.0, 2.1, 2022-08-31, 2023-07-31), with version 3.3.3 defaulting to 2023-07-31. Authentication is handled via API key or Azure Active Directory credentials. The library is production-stable, actively maintained, and has no reported security vulnerabilities.
Use it for
- Extract structured data from receipts and invoices for expense tracking or accounting automation.
- Build a custom model to extract specific fields from domain-specific documents (contracts, medical forms, etc.).
- Classify incoming documents by type before routing them to appropriate processing pipelines.
- Extract text and layout information from scanned or PDF documents for downstream NLP or indexing.
- Detect and extract barcodes or QR codes embedded in documents as part of a larger workflow.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you have an Azure subscription and need to extract structured data from documents at scale.
The library is production-stable, actively maintained, has no known vulnerabilities, and integrates cleanly with the broader Azure SDK ecosystem. Install only if you are committed to using Azure's Document Intelligence service; it is not a standalone solution and requires cloud resources and API credentials.
Install
azure-ai-formrecognizer on PyPI
Before you install
Low friction installation with a pure Python wheel. Actively maintained as of 2026-08-14 with no known vulnerabilities. Depends on azure-core, msrest, azure-common, and typing-extensions—all standard Azure SDK components.
Requires an Azure subscription and a Form Recognizer or Cognitive Services resource with endpoint and API key.
License in practice
MIT License permits commercial and private use with minimal restrictions, making it suitable for most production scenarios.
Quickstart
pip install azure-ai-formrecognizer
from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer import DocumentAnalysisClient
endpoint = "https://<resource>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")
client = DocumentAnalysisClient(endpoint, credential)
result = client.begin_analyze_document_from_url("prebuilt-receipt", url).result()Verify before relying
- Whether prebuilt models cover all document types your use case requires (receipts, invoices, business cards, ID documents, W-2 tax forms mentioned but completeness unclear).
- Performance characteristics and latency for large-batch document processing.
- Exact pricing and cost implications of using different API versions (2023-07-31 default vs. older versions).
Package facts
| License | MIT License permissive |
| Python support | Supports the current Python release >=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesazure-coremsrestazure-commontyping-extensions |
| Maintenance | Actively maintained 857 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,897,067 / month, #3,451 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableLicense :: OSI Approved :: MIT LicenseProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9 |
Evidence: azure_ai_formrecognizer-3.3.3-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “custom document models”
- azure-ai-formrecognizerExtracts text, structure, and key-value pairs from documents using…
- azure-ai-translation-documentTranslates documents stored in Azure Blob Storage across languages…
- unstructured-inferenceRuns inference on layout-parsing and document-analysis models to…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also azure-ai-documentintelligence · azure-ai-textanalytics · azure-ai-translation-document · azure-ai-contentsafety · azure-search-documents · azure-ai-language-questionanswering · azure-ai-vision-imageanalysis · azure-ai-contentunderstanding · azure-ai-translation-text · azure-ai-language-conversations