Wednesday, January 29, 2025

Azure AI services - Use an Azure AI Services Container

 Azure AI services - Use an Azure AI Services Container:

Source : https://github.com/MicrosoftLearning/mslearn-ai-services

Create these two services in Azure.
1. Azure AI services multi-service account
2. Azure Container Instances

2. Azure Container Instances:
az container create --resource-group <your-resource-Group> --name whizcontaineryourname --image mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment:latest --os-type Linux --cpu 1 --memory 8 --dns-name-label whizdnnsyourname --ports 5000 --location eastus --restart-policy OnFailure --secure-environment-variables ApiKey=<your-Api-key> Billing=<endpoint> --environment-variables Eula=accept --ip-address Public

az container create --resource-group rg1 --name sreecontainer1 --image mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment:latest --os-type Linux --cpu 1 --memory 8 --dns-name-label sreednns1 --ports 5000 --location eastus --restart-policy OnFailure --secure-environment-variables ApiKey=AjShjnYv3s56NZNIAkHBni7RCPQCOGAIif Billing=https://sreemultiserviceaccount1.cognitiveservices.azure.com/ --environment-variables Eula=accept --ip-address Public

For Docker:
docker run --rm -it -p 5000:5000 --memory 8g --cpus 1 mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment:latest Eula=accept Billing=<yourEndpoint> ApiKey=<yourKey>
 
Testing:
curl -X POST "http://<your_ACI_IP_address_or_FQDN>:5000/text/analytics/v3.1/sentiment" -H "Content-Type: application/json" --data-ascii "{'documents':[{'id':1,'text':'The performance was amazing! The sound could have been clearer.'},{'id':2,'text':'The food and service were unacceptable. While the host was nice, the waiter was rude and food was cold.'}]}"

curl -X POST "http://sreednns1.eastus.azurecontainer.io:5000/text/analytics/v3.1/sentiment" -H "Content-Type: application/json" --data-ascii "{'documents':[{'id':1,'text':'The performance was amazing! The sound could have been clearer.'},{'id':2,'text':'The food and service were unacceptable. While the host was nice, the waiter was rude and food was cold.'}]}"

OutPut:

{  
  "documents": [  
    {  
      "id": "1",  
      "sentiment": "positive",  
      "confidenceScores": {  
        "positive": 0.99,  
        "neutral": 0.0,  
        "negative": 0.0  
      },  
      "sentences": [  
        {  
          "sentiment": "positive",  
          "confidenceScores": {  
            "positive": 0.99,  
            "neutral": 0.0,  
            "negative": 0.0  
          },  
          "offset": 0,  
          "length": 29,  
          "text": "The performance was amazing! "  
        },  
        {  
          "sentiment": "neutral",  
          "confidenceScores": {  
            "positive": 0.19,  
            "neutral": 0.47,  
            "negative": 0.34  
          },  
          "offset": 29,  
          "length": 34,  
          "text": "The sound could have been clearer."  
        }  
      ],  
      "warnings": []  
    },  
    {  
      "id": "2",  
      "sentiment": "negative",  
      "confidenceScores": {  
        "positive": 0.0,  
        "neutral": 0.01,  
        "negative": 0.98  
      },  
      "sentences": [  
        {  
          "sentiment": "negative",  
          "confidenceScores": {  
            "positive": 0.0,  
            "neutral": 0.01,  
            "negative": 0.99  
          },  
          "offset": 0,  
          "length": 40,  
          "text": "The food and service were unacceptable. "  
        },  
        {  
          "sentiment": "negative",  
          "confidenceScores": {  
            "positive": 0.0,  
            "neutral": 0.02,  
            "negative": 0.98  
          },  
          "offset": 40,  
          "length": 63,  
          "text": "While the host was nice, the waiter was rude and food was cold."  
        }  
      ],  
      "warnings": []  
    }  
  ],  
  "errors": []  
}


4 comments:

Featured Post

Build a Secure MCP Server on Azure Functions for Copilot Studio Agents (Entra ID OAuth)

Model Context Protocol (MCP) is quickly becoming the standard way to give AI agents real tools. Copilot Studio can call any remote MCP serve...

Popular posts