azure-ai-textanalytics-py

The saved excerpt is a snapshot from when this skill was listed. The external source remains the complete and most current version.

---
name: azure-ai-textanalytics-py
description: |
  Azure AI Text Analytics SDK for sentiment analysis, entity recognition, key phrases, language detection, PII, and healthcare NLP. Use for natural language processing on text.
  Triggers: "text analytics", "sentiment analysis", "entity recognition", "key phrase", "PII detection", "TextAnalyticsClient".
license: MIT
metadata:
  author: Microsoft
  version: "1.0.0"
  package: azure-ai-textanalytics
---

# Azure AI Text Analytics SDK for Python

Client library for Azure AI Language service NLP capabilities including sentiment, entities, key phrases, and more.

## Installation

```bash
pip install azure-ai-textanalytics
```

## Environment Variables

```bash
AZURE_LANGUAGE_ENDPOINT=https://<resource>.cognitiveservices.azure.com  # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
AZURE_LANGUAGE_KEY=<your-api-key>  # Only required for the legacy API-key auth path below
```

## Authentication & Lifecycle

> **🔑 Two rules apply to every code sample below:**
>
> 1. **Prefer `DefaultAzureCredential`.** It works locally (Azure CLI / VS Code / Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account/API keys — they bypass Entra audit and rotation.
>    - Local dev: `DefaultAzureCredential` works as-is.
>    - Production: set `AZURE_TOKEN_CREDENTIALS=prod` (or `AZURE_TOKEN_CREDENTIALS=<specific_credential>`) to constrain the credential chain to production-safe credentials.
> 2. **Wrap every client in a context manager** so HTTP transports, sockets, and token caches are released deterministically:
>    - Sync: `with <Client>(...) as client:`
>    - Async: `async with <Client>(...) as client:` **and** `async with DefaultAzureCredential() as credential:` (from `azure.identity.aio`)
>
> Snippets may abbreviate this setup, but production code should always follow both rules.

```python
import os
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
from azure.ai.textanalytics import TextAnalyticsClient

# 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 TextAnalyticsClient(
    endpoint=os.environ["AZURE_LANGUAGE_ENDPOINT"],
    credential=credential,
) as client:
    languages = client.detect_language(["Hello, world!"])
```

### Legacy: API Key (existing keyed deployments)

New code should use `DefaultAzureCredential` above. Use `AzureKeyCredential` only if you have an existing keyed deployment that hasn't been migrated to Entra ID yet — for example, regulated environments still completing their Entra rollout.

```python
import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient

with TextAnalyticsClient(
    endpoint=os.environ["AZURE_LANGUAGE_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["AZURE_LANGUAGE_KEY"]),
) as client:
    languages = client.detect_language(["Hello, world!"])
```

## Sentiment Analysis

```python
documents = [
    "I had a wonderful trip to Seattle last week!",
    "The food was terrible and the service was slow."
]

result = client.analyze_sentiment(documents, show_opinion_mining=True)

for doc in result:
    if not doc.is_error:
        print(f"Sentiment: {doc.sentiment}")
        print(f"Scores: pos={doc.confidence_scores.positive:.2f}, "
              f"neg={doc.confidence_scores.negative:.2f}, "
              f"neu={doc.confidence_scores.neutral:.2f}")
        
        # Opinion mining (aspect-based sentiment)
        for sentence in doc.sentences:
            for opinion in sentence.mine