SDK do Azure AI Content Understanding para Python

Serviço de IA multimodal que extrai conteúdo semântico de documentos, vídeos, áudios e arquivos de imagem para RAG e fluxos de trabalho automatizados.

Instalação

pip install azure-ai-contentunderstanding

Variáveis de Ambiente

CONTENTUNDERSTANDING_ENDPOINT=https://<resource>.cognitiveservices.azure.com/

Autenticação

import os
from azure.ai.contentunderstanding import ContentUnderstandingClient
from azure.identity import DefaultAzureCredential

endpoint = os.environ["CONTENTUNDERSTANDING_ENDPOINT"]
credential = DefaultAzureCredential()
client = ContentUnderstandingClient(endpoint=endpoint, credential=credential)

Fluxo de Trabalho Principal

As operações de Content Understanding são operações assíncronas de longa duração:

1. Iniciar Análise — Inicie a operação de análise com begin_analyze() (retorna um poller)
2. Verificar Resultados — Verifique até que a análise seja concluída (o SDK cuida disso com .result())
3. Processar Resultados — Extraia resultados estruturados de AnalyzeResult.contents

Analisadores Pré-construídos

Analisar Documento

import os
from azure.ai.contentunderstanding import ContentUnderstandingClient
from azure.ai.contentunderstanding.models import AnalyzeInput
from azure.identity import DefaultAzureCredential

endpoint = os.environ["CONTENTUNDERSTANDING_ENDPOINT"]
client = ContentUnderstandingClient(
    endpoint=endpoint,
    credential=DefaultAzureCredential()
)

# Analyze document from URL
poller = client.begin_analyze(
    analyzer_id="prebuilt-documentSearch",
    inputs=[AnalyzeInput(url="https://example.com/document.pdf")]
)

result = poller.result()

# Access markdown content (contents is a list)
content = result.contents[0]
print(content.markdown)

Acessar Detalhes do Conteúdo do Documento

from azure.ai.contentunderstanding.models import MediaContentKind, DocumentContent

content = result.contents[0]
if content.kind == MediaContentKind.DOCUMENT:
    document_content: DocumentContent = content  # type: ignore
    print(document_content.start_page_number)

Analisar Imagem

from azure.ai.contentunderstanding.models import AnalyzeInput

poller = client.begin_analyze(
    analyzer_id="prebuilt-imageSearch",
    inputs=[AnalyzeInput(url="https://example.com/image.jpg")]
)
result = poller.result()
content = result.contents[0]
print(content.markdown)

Analisar Vídeo

from azure.ai.contentunderstanding.models import AnalyzeInput

poller = client.begin_analyze(
    analyzer_id="prebuilt-videoSearch",
    inputs=[AnalyzeInput(url="https://example.com/video.mp4")]
)

result = poller.result()

# Access video content (AudioVisualContent)
content = result.contents[0]

# Get transcript phrases with timing
for phrase in content.transcript_phrases:
    print(f"[{phrase.start_time} - {phrase.end_time}]: {phrase.text}")

# Get key frames (for video)
for frame in content.key_frames:
    print(f"Frame at {frame.time}: {frame.description}")

Analisar Áudio

from azure.ai.contentunderstanding.models import AnalyzeInput

poller = client.begin_analyze(
    analyzer_id="prebuilt-audioSearch",
    inputs=[AnalyzeInput(url="https://example.com/audio.mp3")]
)

result = poller.result()

# Access audio transcript
content = result.contents[0]
for phrase in content.transcript_phrases:
    print(f"[{phrase.start_time}] {phrase.text}")

Analisadores Personalizados

Crie analisadores personalizados com esquemas de campos para extração especializada:

# Criar analisador personalizado
analyzer = client.create_analyzer(
    analyzer_id="meu-analisador-fatura",
    analyzer={
        "description": "Analisador personalizado de faturas",
        "base_analyzer_id": "prebuilt-documentSearch",
        "field_schema": {
            "fields": {
                "nome_fornecedor": {"type": "string"},
                "total_fatura": {"type": "number"},
                "itens_linha": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {

…