azure - Python - 分析法语文本。 法国参数？

Question

I don't really understand if I need to set something particular if I want to use it for french text. I've read the Azure documentation. They said to use "fr" code. But I don't really where to place it. Do you have any idea?

#Azure lib
from azure.ai.textanalytics import TextAnalyticsClient
from azure.core.credentials import AzureKeyCredential
azurekey = ""
azureendpoint = ""

def authenticate_client():
    ta_credential = AzureKeyCredential(azurekey)
    text_analytics_client = TextAnalyticsClient(
            endpoint=azureendpoint, 
            credential=ta_credential)
    return text_analytics_client

clientazure = authenticate_client()

if self.content:
            documents = [self.content]
            
            response = clientazure.analyze_sentiment(documents = documents)[0]
            try:
                self.emotion = "sentiment: {}".format(response.sentiment) + " detail: positive={0:.2f}; neutral={1:.2f}; negative={2:.2f} \n".format(response.confidence_scores.positive,response.confidence_scores.neutral,response.confidence_scores.negative,)
            except Exception as e:
                self.emotion = None
                
            result = clientazure.recognize_entities(documents = documents)[0]
            for entity in result.entities:
                try:
                    self.topic = entity.text
                except Exception as e:
                    self.topic = None
                try:
                    self.category = entity.category
                except Exception as e:
                    self.category = None

Answer 1

The language code can be placed per text document, or for the entire batch. Pass it into the call for analyze_sentiment() if you want "fr" to apply to all documents:

response = clientazure.analyze_sentiment(documents = documents, language="fr")

If only wanting the language code to apply to a single document, pass in the language code at the document level. Assuming that self.content contains the text you want to analyze, it would look like this:

documents = [{"id": "1", "language": "fr", "text": self.content}]