Function createAzureOpenAIProvider

createAzureOpenAIProvider(config: AzureOpenAIProviderConfig): LlmProvider
Creates an Azure OpenAI LLM provider for use with evaluate.

Azure OpenAI requires a resource endpoint and API key (or managed identity). Pass an AzureOpenAI client from the openai package — it has the same .chat.completions.create() interface as the standard OpenAI client.

Custom / self-hosted endpoints (Ollama, LocalAI, vLLM, etc.) can use { type: 'openai' } with a custom baseURL instead:
```
import OpenAI from 'openai'
const client = new OpenAI({ baseURL: 'http://localhost:11434/v1', apiKey: 'ollama' })
evaluate({ provider: { type: 'openai', client, model: 'llama3' }, ... })
```
Parameters
- config: AzureOpenAIProviderConfig
  Provider configuration including the AzureOpenAI client instance.
Returns LlmProvider
An LlmProvider ready to be passed to evaluate().
Example
```
import { AzureOpenAI } from 'openai'
import { evaluate } from 'rageval'

const client = new AzureOpenAI({
  endpoint: 'https://my-resource.openai.azure.com',
  apiKey: process.env.AZURE_OPENAI_API_KEY,
  apiVersion: '2025-01-01-preview',
})

const results = await evaluate({
  provider: { type: 'azure', client, model: 'gpt-4o' },
  dataset: myDataset,
})
```
- Defined in src/providers/azure.ts:77