Adding azure documentation, and minor changes. (#31)

* Adding azure documentation, and minor changes.

* Fixing test case, and adding better exception message.

Author: rohitprasad15

aisuite/providers/azure_provider.py

@@ -1,20 +1,25 @@
 import urllib.request
 import json
+import os
+
 from aisuite.provider import Provider
 from aisuite.framework import ChatCompletionResponse
 
 
 class AzureProvider(Provider):
     def __init__(self, **config):
-        self.base_url = config.get("base_url")
-        self.api_key = config.get("api_key")
+        self.base_url = config.get("base_url") or os.getenv("AZURE_BASE_URL")
+        self.api_key = config.get("api_key") or os.getenv("AZURE_API_KEY")
         if not self.api_key:
-            raise ValueError("api_key is required in the config")
+            raise ValueError("For Azure, api_key is required.")
+        if not self.base_url:
+            raise ValueError(
+                "For Azure, base_url is required. Check your deployment page for a URL like this - https://<model-deployment-name>.<region>.models.ai.azure.com"
+            )
 
     def chat_completions_create(self, model, messages, **kwargs):
-        # TODO: Need to decide if we need to use base_url or just ignore it.
-        # TODO: Remove the hardcoded region name to use environment variable.
         url = f"https://{model}.westus3.models.ai.azure.com/v1/chat/completions"
+        url = f"https://{self.base_url}/chat/completions"
         if self.base_url:
             url = f"{self.base_url}/chat/completions"
 

examples/client.ipynb

@@ -128,8 +128,9 @@
    "source": [
     "client2 = ai.Client({\"azure\" : {\n",
     "  \"api_key\": os.environ[\"AZURE_API_KEY\"],\n",
+    "  \"base_url\": \"https://mistral-large-2407.westus3.models.ai.azure.com/v1/\",\n",
     "}});\n",
-    "azure_model = \"azure:aisuite-Meta-Llama-3-8B-Inst\"\n",
+    "azure_model = \"azure:mistral-large-2407\"\n",
     "response = client2.chat.completions.create(model=azure_model, messages=messages)\n",
     "print(response.choices[0].message.content)"
    ]

guides/azure.md

@@ -0,0 +1,58 @@
+# Azure AI
+
+To use Azure AI with the `aisuite` library, you'll need to set up an Azure account and configure your environment for Azure AI services.
+
+## Create an Azure Account and deploy a model from AI Studio
+
+1. Visit [Azure Portal](https://portal.azure.com/) and sign up for an account if you don't have one.
+2. Create a project and resource group.
+3. Choose a model from https://ai.azure.com/explore/models and deploy it. You can choose serverless deployment option.
+4. Give a deployment name. Lets say you choose to deploy Mistral-large-2407. You could leave the deployment names as "mistral-large-2407" or give a custom name.
+5. You can see the deployment from project/deployment option. Note the Target URI from the Endpoint panel. It should look something like this - "https://aisuite-Mistral-large-2407.westus3.models.ai.azure.com".
+6. Also note, that is provides a Chat completion URL. It should look like this - https://aisuite-Mistral-large-2407.westus3.models.ai.azure.com/v1/chat/completions
+
+
+## Obtain Necessary Details & set environment variables.
+
+After creating your deployment, you'll need to gather the following information:
+
+1. API Key: Found in the "Keys and Endpoint" section of your Azure OpenAI resource.
+2. Base URL: This can be obtained from your deployment details. It will look something like this - `https://aisuite-Mistral-large-2407.westus3.models.ai.azure.com/v1/`
+
+
+Set the following environment variables:
+
+```shell
+export AZURE_API_KEY="your-api-key"
+export AZURE_BASE_URL="https://deployment-name.region-name.models.ai.azure.com/v1"
+```
+
+## Create a Chat Completion
+
+With your account set up and environment configured, you can send a chat completion request:
+
+```python
+import aisuite as ai
+
+# Either set the environment variables or set the below two parameters.
+# Setting the params in ai.Client() will override the values from environment vars.
+client = ai.Client(
+    base_url=os.environ["AZURE_OPENAI_BASE_URL"],
+    api_key=os.environ["AZURE_OPENAI_API_KEY"]
+)
+
+model = "azure:aisuite-Mistral-large-2407"  # Replace with your deployment name.
+# The model name must match the deployment name in the base-url.
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's the weather like today?"},
+]
+
+response = client.chat.completions.create(
+    model=model,
+    messages=messages,
+)
+
+print(response.choices[0].message.content)
+```

tests/client/test_client.py

@@ -46,6 +46,7 @@ def test_client_chat_completions(
             },
             ProviderNames.AZURE: {
                 "api_key": "azure-api-key",
+                "base_url": "https://model.ai.azure.com",
             },
             ProviderNames.GROQ: {
                 "api_key": "groq-api-key",