feat: Support for Microsoft azure endpoints (#67)

* initial implementation to support Azure Endpoints

* update existing tests

* update lib.rs example

* use doc suggestion

* documentation

* test fix

* test update: remove deprecated codex example; run all tests using 'cargo make all'

* add example for azure openai service

* update example

* update example

* back to Client::new

* updates

* test fix

* update doc

async-openai/README.md

@@ -31,14 +31,13 @@
   - [x] Files
   - [x] Fine-Tuning (including SSE streaming)
   - [x] Images
-  - [ ] Microsoft Azure Endpoints / AD Authentication (see [issue](https://github.com/64bit/async-openai/issues/32))
+  - [x] Microsoft Azure Endpoints
   - [x] Models
   - [x] Moderations
 - Non-streaming requests are retried with exponential backoff when [rate limited](https://platform.openai.com/docs/guides/rate-limits) by the API server.
 - Ergonomic Rust library with builder pattern for all request objects.
 
-_Being a young project there could be rough edges._
-
+**Note on Azure OpenAI Service**:  `async-openai` primarily implements OpenAI APIs, and exposes same library for Azure OpenAI Service too. In reality Azure OpenAI Service provides only subset of OpenAI APIs.
 ## Usage
 
 The library reads [API key](https://platform.openai.com/account/api-keys) from the environment variable `OPENAI_API_KEY`.
@@ -104,7 +103,7 @@ async fn main() -> Result<(), Box<dyn Error>> {
 
 Thank you for your time to contribute and improve the project, I'd be happy to have you!
 
-A good starting point would be an [open issue](https://github.com/64bit/async-openai/issues).
+A good starting point would be existing [open issues](https://github.com/64bit/async-openai/issues).
 
 ## License
 

async-openai/src/audio.rs

@@ -1,4 +1,5 @@
 use crate::{
+    config::Config,
     error::OpenAIError,
     types::{
         CreateTranscriptionRequest, CreateTranscriptionResponse, CreateTranslationRequest,
@@ -10,12 +11,12 @@ use crate::{
 
 /// Turn audio into text
 /// Related guide: [Speech to text](https://platform.openai.com/docs/guides/speech-to-text)
-pub struct Audio<'c> {
-    client: &'c Client,
+pub struct Audio<'c, C: Config> {
+    client: &'c Client<C>,
 }
 
-impl<'c> Audio<'c> {
-    pub fn new(client: &'c Client) -> Self {
+impl<'c, C: Config> Audio<'c, C> {
+    pub fn new(client: &'c Client<C>) -> Self {
         Self { client }
     }
 

async-openai/src/chat.rs

@@ -1,4 +1,5 @@
 use crate::{
+    config::Config,
     error::OpenAIError,
     types::{
         ChatCompletionResponseStream, CreateChatCompletionRequest, CreateChatCompletionResponse,
@@ -7,12 +8,12 @@ use crate::{
 };
 
 /// Given a chat conversation, the model will return a chat completion response.
-pub struct Chat<'c> {
-    client: &'c Client,
+pub struct Chat<'c, C: Config> {
+    client: &'c Client<C>,
 }
 
-impl<'c> Chat<'c> {
-    pub fn new(client: &'c Client) -> Self {
+impl<'c, C: Config> Chat<'c, C> {
+    pub fn new(client: &'c Client<C>) -> Self {
         Self { client }
     }