Azure OpenAI Embeddings

Generate embeddings using Azure OpenAI Service

Overview

Azure OpenAI provides enterprise-grade embedding models with Azure’s security and compliance features.

Quick Start

from praisonaiagents import embedding

result = embedding(
    input="Hello world",
    model="azure/text-embedding-ada-002"
)
print(f"Dimensions: {len(result.embeddings[0])}")

CLI Usage

praisonai embed "Hello world" --model azure/text-embedding-ada-002

Setup

export AZURE_API_KEY="your-azure-api-key"
export AZURE_API_BASE="https://your-resource.openai.azure.com"
export AZURE_API_VERSION="2024-02-01"

Available Models

Model	Dimensions	Max Tokens
azure/text-embedding-ada-002	1536	8191
azure/text-embedding-3-small	1536	8191
azure/text-embedding-3-large	3072	8191

With Deployment Name

from praisonaiagents import embedding

result = embedding(
    input="Hello world",
    model="azure/my-embedding-deployment",
    api_base="https://my-resource.openai.azure.com",
    api_key="your-key"
)

Batch Embeddings

from praisonaiagents import embedding

texts = ["Document 1", "Document 2", "Document 3"]
result = embedding(
    input=texts,
    model="azure/text-embedding-ada-002"
)
print(f"Generated {len(result.embeddings)} embeddings")

Azure AD Authentication

from praisonaiagents import embedding
from azure.identity import DefaultAzureCredential

credential = DefaultAzureCredential()
token = credential.get_token("https://cognitiveservices.azure.com/.default")

result = embedding(
    input="Hello world",
    model="azure/text-embedding-ada-002",
    api_key=token.token
)

Related

• Embedding Providers Overview
• OpenAI Embeddings