From 00989ce123f2ee7ad9bcf3f2033eb66c39e246bd Mon Sep 17 00:00:00 2001
From: jtaub <65861679+jtaub@users.noreply.github.com>
Date: Fri, 24 Nov 2023 13:10:18 -0500
Subject: [PATCH] chore: add documentation for maven and custom hosts (#265)

---
 README.md                | 31 +++++++++++++++++++++++++++--
 guides/GettingStarted.md | 43 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 71 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index c7b5aadb..d2261b3a 100644
--- a/README.md
+++ b/README.md
@@ -38,11 +38,38 @@ dependencies {
 }
 ```
 
-### Multiplaform
+### Multiplatform
 
 In multiplatform projects, add openai client dependency to `commonMain`, and choose
 an [engine](https://ktor.io/docs/http-client-engines.html) for each target.
 
+### Maven
+
+Gradle is required for multiplatform support, but there's nothing stopping you from using the jvm client in a Maven
+project. You still need to add to your dependencies one
+of [Ktor's engines](https://ktor.io/docs/http-client-engines.html). For example:
+
+```xml
+<dependencies>
+    <!-- https://mvnrepository.com/artifact/com.aallam.openai/openai-client-jvm -->
+    <dependency>
+        <groupId>com.aallam.openai</groupId>
+        <artifactId>openai-client-jvm</artifactId>
+        <version>3.6.0</version>
+    </dependency>
+            
+    <!-- https://mvnrepository.com/artifact/io.ktor/ktor-client-okhttp-jvm -->
+    <dependency>
+        <groupId>io.ktor</groupId>
+        <artifactId>ktor-client-okhttp-jvm</artifactId>
+        <version>2.3.2</version>
+        <scope>runtime</scope>
+    </dependency>
+</dependencies>
+```
+
+The BOM is not supported for Maven projects.
+
 ## ⚡️ Getting Started
 
 > **Note**: OpenAI encourages using environment variables for the API key. [Read more](https://help.openai.com/en/articles/5112595-best-practices-for-api-key-safety).
@@ -131,7 +158,7 @@ repositories {
 
 </details>
 
-## 🛠️ Throubleshooting
+## 🛠️ Troubleshooting
 
 For common issues and their solutions, check the [Troubleshooting Guide](TROUBLESHOOTING.md).
 
diff --git a/guides/GettingStarted.md b/guides/GettingStarted.md
index c2a58a2a..247f3798 100644
--- a/guides/GettingStarted.md
+++ b/guides/GettingStarted.md
@@ -39,7 +39,10 @@ Use your `OpenAI` instance to make API requests.
     - [Retrieve file](#retrieve-file)
     - [Retrieve file content](#retrieve-file-content)
 - [Moderations](#moderations)
-    - [Create moderation](#create-moderation)- 
+    - [Create moderation](#create-moderation)
+- [Hosts](#hosts)
+    - [Azure](#azure)
+    - [Other hosts](#other-hosts)
 
 #### Beta
 
@@ -391,6 +394,44 @@ val moderation = openAI.moderations(
 )
 ````
 
+## Hosts
+
+This library has support for custom ChatGPT URLs. The host used by default is `https://api.openai.com/v1/`, as you would
+expect, and support for Azure hosted ChatGPT is built in as well.
+
+### Azure
+
+To connect to an Azure hosted instance, use the `OpenAIHost.azure` function like so:
+
+````kotlin
+val host = OpenAIHost.azure(
+    resourceName = "The name of your Azure OpenAI Resource.",
+    deploymentId = "The name of your model deployment.",
+    apiVersion = "The API version to use for this operation. This parameter should follow the YYYY-MM-DD format.",
+)
+val config = OpenAIConfig(
+    host = host,
+    token = "Your API token",
+)
+val openAI = OpenAI(config)
+````
+
+### Other hosts
+
+You can connect to whatever host you like by constructing your own `OpenAIHost` instance. Otherwise, it's exactly the
+same as the above Azure example.
+
+````kotlin
+val host = OpenAIHost(
+    baseUrl = "http://localhost:8080",
+)
+val config = OpenAIConfig(
+    host = host,
+    token = "Your API token",
+)
+val openAI = OpenAI(config)
+````
+
 ---
 
 ## Completions