Azure AI Contentunderstanding Py

pip install azure-ai-contentunderstanding

CONTENTUNDERSTANDING_ENDPOINT=https://<resource>.cognitiveservices.azure.com/  # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production

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

endpoint = os.environ["CONTENTUNDERSTANDING_ENDPOINT"]
# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()
with ContentUnderstandingClient(endpoint=endpoint, credential=credential) as client:
    analyzers = list(client.list_analyzers())

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"]
with ContentUnderstandingClient(
    endpoint=endpoint,
    credential=DefaultAzureCredential()
) as client:
    # 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)

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)

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)

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}")

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}")

# Create custom analyzer
analyzer = client.create_analyzer(
    analyzer_id="my-invoice-analyzer",
    analyzer={
        "description": "Custom invoice analyzer",
        "base_analyzer_id": "prebuilt-documentSearch",
        "field_schema": {
            "fields": {
                "vendor_name": {"type": "string"},
                "invoice_total": {"type": "number"},
                "line_items": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "description": {"type": "string"},
                            "amount": {"type": "number"}
                        }
                    }
                }
            }
        }
    }
)

# Use custom analyzer
from azure.ai.contentunderstanding.models import AnalyzeInput

poller = client.begin_analyze(
    analyzer_id="my-invoice-analyzer",
    inputs=[AnalyzeInput(url="https://example.com/invoice.pdf")]
)

result = poller.result()

# Access extracted fields
print(result.fields["vendor_name"])
print(result.fields["invoice_total"])

# List all analyzers
analyzers = client.list_analyzers()
for analyzer in analyzers:
    print(f"{analyzer.analyzer_id}: {analyzer.description}")

# Get specific analyzer
analyzer = client.get_analyzer("prebuilt-documentSearch")

# Delete custom analyzer
client.delete_analyzer("my-custom-analyzer")

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

async def analyze_document():
    endpoint = os.environ["CONTENTUNDERSTANDING_ENDPOINT"]
    async with DefaultAzureCredential() as credential:
        async with ContentUnderstandingClient(
            endpoint=endpoint,
            credential=credential
        ) as client:
            poller = await client.begin_analyze(
                analyzer_id="prebuilt-documentSearch",
                inputs=[AnalyzeInput(url="https://example.com/doc.pdf")]
            )
            result = await poller.result()
            content = result.contents[0]
            return content.markdown

asyncio.run(analyze_document())