Version 0.4.1

Author: peterbanda

README.md

@@ -1,5 +1,5 @@
 # OpenAI Scala Client 🤖
-[![version](https://img.shields.io/badge/version-0.4.0-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT) ![GitHub Stars](https://img.shields.io/github/stars/cequence-io/openai-scala-client?style=social) [![Twitter Follow](https://img.shields.io/twitter/follow/0xbnd?style=social)](https://twitter.com/0xbnd) ![GitHub CI](https://github.com/cequence-io/openai-scala-client/actions/workflows/continuous-integration.yml/badge.svg)
+[![version](https://img.shields.io/badge/version-0.4.1-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT) ![GitHub Stars](https://img.shields.io/github/stars/cequence-io/openai-scala-client?style=social) [![Twitter Follow](https://img.shields.io/twitter/follow/0xbnd?style=social)](https://twitter.com/0xbnd) ![GitHub CI](https://github.com/cequence-io/openai-scala-client/actions/workflows/continuous-integration.yml/badge.svg)
 
 This is a no-nonsense async Scala client for OpenAI API supporting all the available endpoints and params **including streaming**, the newest **ChatGPT completion**, and **voice routines** (as defined [here](https://beta.openai.com/docs/api-reference)), provided in a single, convenient service called [OpenAIService](./openai-core/src/main/scala/io/cequence/openaiscala/service/OpenAIService.scala). The supported calls are: 
 
@@ -17,11 +17,13 @@ This is a no-nonsense async Scala client for OpenAI API supporting all the avail
 Note that in order to be consistent with the OpenAI API naming, the service function names match exactly the API endpoint titles/descriptions with camelcase.
 Also, we aimed the lib to be self-contained with the fewest dependencies possible therefore we ended up using only two libs `play-ahc-ws-standalone` and `play-ws-standalone-json` (at the top level). Additionally, if dependency injection is required we use `scala-guice` lib as well.  
 
-**✔️ Important**: this is a "community-maintained" library and, as such, has no relation to OpenAI company.
+🔥 **New**: This lib supports also "OpenAI-API-compatible" providers such as [FastChat](https://github.com/lm-sys/FastChat), [Azure](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/reference), or any other service with a custom URL. Check the examples below for more details. 
 
 👉 Check out an article about the lib/client on [Medium](https://medium.com/@0xbnd/openai-scala-client-is-out-d7577de934ad).
 
-**🔥 New**: Try out also our [Scala client for Pinecone vector database](https://github.com/cequence-io/pinecone-scala), or use both clients together! [This demo project](https://github.com/cequence-io/pinecone-openai-scala-demo) shows how to generate and store OpenAI embeddings (with `text-embedding-ada-002` model) into Pinecone and query them afterward. The OpenAI + Pinecone combo is commonly used for autonomous AI agents, such as [babyAGI](https://github.com/yoheinakajima/babyagi) and [AutoGPT](https://github.com/Significant-Gravitas/Auto-GPT).
+Try out also our [Scala client for Pinecone vector database](https://github.com/cequence-io/pinecone-scala), or use both clients together! [This demo project](https://github.com/cequence-io/pinecone-openai-scala-demo) shows how to generate and store OpenAI embeddings (with `text-embedding-ada-002` model) into Pinecone and query them afterward. The OpenAI + Pinecone combo is commonly used for autonomous AI agents, such as [babyAGI](https://github.com/yoheinakajima/babyagi) and [AutoGPT](https://github.com/Significant-Gravitas/Auto-GPT).
+
+**✔️ Important**: this is a "community-maintained" library and, as such, has no relation to OpenAI company.
 
 ## Installation 🚀
 
@@ -30,7 +32,7 @@ The currently supported Scala versions are **2.12, 2.13**, and **3**.
 To pull the library you have to add the following dependency to your *build.sbt*
 
 ```
-"io.cequence" %% "openai-scala-client" % "0.4.0"
+"io.cequence" %% "openai-scala-client" % "0.4.1"
 ```
 
 or to *pom.xml* (if you use maven)
@@ -39,11 +41,11 @@ or to *pom.xml* (if you use maven)
 <dependency>
     <groupId>io.cequence</groupId>
     <artifactId>openai-scala-client_2.12</artifactId>
-    <version>0.4.0</version>
+    <version>0.4.1</version>
 </dependency>
 ```
 
-If you want a streaming support use `"io.cequence" %% "openai-scala-client-stream" % "0.4.0"` instead.
+If you want a streaming support use `"io.cequence" %% "openai-scala-client-stream" % "0.4.1"` instead.
 
 ## Config ⚙️
 
@@ -83,6 +85,34 @@ Then you can obtain a service in one of the following ways.
   )
 ```
 
+- Minimal `OpenAICoreService` supporting `listModels`, `createCompletion`, `createChatCompletion`, and `createEmbeddings` calls - e.g. [FastChat](https://github.com/lm-sys/FastChat) service running on the port 8000 (🔥 new)
+
+```scala
+  val service = OpenAICoreServiceFactory("http://localhost:8000/v1/")
+```
+
+- For Azure with API Key (🔥 new)
+
+```scala
+  val service = OpenAIServiceFactory.forAzureWithApiKey(
+    resourceName = "your-resource-name",
+    deploymentId = "your-deployment-id",
+    apiVersion = "2023-05-15", // example
+    apiKey = "your_api_key"
+  )
+```
+
+- For Azure with Access Token (🔥 new)
+
+```scala
+  val service = OpenAIServiceFactory.forAzureWithAccessToken(
+    resourceName = "your-resource-name",
+    deploymentId = "your-deployment-id",
+    apiVersion = "2023-05-15", // example
+    accessToken = "your_access_token"
+  )
+```
+
 **✔️ Important**: If you want streaming support use `OpenAIServiceStreamedFactory` from `openai-scala-client-stream` lib instead of `OpenAIServiceFactory` (in the three examples above). Three additional functions - `createCompletionStreamed`, `createChatCompletionStreamed`, and `listFineTuneEventsStreamed` provided by [OpenAIServiceStreamedExtra](./openai-client-stream/src/main/scala/io/cequence/openaiscala/service/OpenAIServiceStreamedExtra.scala) will be then available.
 
 - Via dependency injection (requires `openai-scala-guice` lib)
@@ -194,7 +224,7 @@ For this to work you need to use `OpenAIServiceStreamedFactory` from `openai-sca
   }
 ```
 
-- Create chat completion for functions (🔥 new) 
+- Create chat completion for functions 
 
 ```scala
   val messages = Seq(
@@ -242,9 +272,9 @@ This extension of the standard chat completion is currently supported by the fol
 - `gpt-3.5-turbo-0613` (default), `gpt-3.5-turbo-16k-0613`, `gpt-4-0613`, and `gpt-4-32k-0613`.
 
 
-**✔️ Important Note**: After you are done using the service, you should close it by calling (🔥 new) `service.close`. Otherwise, the underlying resources/threads won't be released.
+**✔️ Important Note**: After you are done using the service, you should close it by calling `service.close`. Otherwise, the underlying resources/threads won't be released.
 
-**III. Using multiple services (🔥 new)**
+**III. Using multiple services**
 
 - Load distribution with `OpenAIMultiServiceAdapter` - _round robin_ (_rotation_) type
 
@@ -289,10 +319,10 @@ import scala.concurrent.duration.DurationInt
 import scala.concurrent.{ExecutionContext, Future}
 
 class MyCompletionService @Inject() (
-                                      val actorSystem: ActorSystem,
-                                      implicit val ec: ExecutionContext,
-                                      implicit val scheduler: Scheduler
-                                    )(val apiKey: String)
+  val actorSystem: ActorSystem,
+  implicit val ec: ExecutionContext,
+  implicit val scheduler: Scheduler
+)(val apiKey: String)
   extends RetryHelpers {
   val service: OpenAIService = OpenAIServiceFactory(apiKey)
   implicit val retrySettings: RetrySettings =
@@ -315,7 +345,7 @@ class MyCompletionService @Inject() (
   val serviceAux = ... // your service
 
   implicit val retrySettings: RetrySettings = 
-    RetrySettings(maxAttempts = 10).constantInterval(10.seconds)
+    RetrySettings(maxRetries = 10).constantInterval(10.seconds)
   // wrap it with the retry adapter
   val service = OpenAIRetryServiceAdapter(serviceAux)
 

build.sbt

@@ -7,7 +7,7 @@ val scala3 = "3.2.2"
 
 ThisBuild / organization := "io.cequence"
 ThisBuild / scalaVersion := scala212
-ThisBuild / version := "0.4.0"
+ThisBuild / version := "0.4.1"
 ThisBuild / isSnapshot := false
 
 lazy val commonSettings = Seq(

openai-client-stream/README.md

@@ -1,4 +1,4 @@
-# OpenAI Scala Client - Stream Support [![version](https://img.shields.io/badge/version-0.4.0-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
+# OpenAI Scala Client - Stream Support [![version](https://img.shields.io/badge/version-0.4.1-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
 
 This module provides streaming support for the client. Note that the full project documentation can be found [here](../README.md).
 
@@ -9,7 +9,7 @@ The currently supported Scala versions are **2.12, 2.13**, and **3**.
 To pull the library you have to add the following dependency to your *build.sbt*
 
 ```
-"io.cequence" %% "openai-scala-client-stream" % "0.4.0"
+"io.cequence" %% "openai-scala-client-stream" % "0.4.1"
 ```
 
 or to *pom.xml* (if you use maven)
@@ -18,6 +18,6 @@ or to *pom.xml* (if you use maven)
 <dependency>
     <groupId>io.cequence</groupId>
     <artifactId>openai-scala-client-stream_2.12</artifactId>
-    <version>0.4.0</version>
+    <version>0.4.1</version>
 </dependency>
 ```

openai-client/README.md

@@ -1,4 +1,4 @@
-# OpenAI Scala Client - Client [![version](https://img.shields.io/badge/version-0.4.0-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
+# OpenAI Scala Client - Client [![version](https://img.shields.io/badge/version-0.4.1-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
 
 This module provides the actual meat, i.e. WS client implementation ([OpenAIServiceImpl and OpenAIServiceFactory](./src/main/scala/io/cequence/openaiscala/service/OpenAIServiceImpl.scala)).
 Note that the full project documentation can be found [here](../README.md).
@@ -10,7 +10,7 @@ The currently supported Scala versions are **2.12, 2.13**, and **3**.
 To pull the library you have to add the following dependency to your *build.sbt*
 
 ```
-"io.cequence" %% "openai-scala-client" % "0.4.0"
+"io.cequence" %% "openai-scala-client" % "0.4.1"
 ```
 
 or to *pom.xml* (if you use maven)
@@ -19,6 +19,6 @@ or to *pom.xml* (if you use maven)
 <dependency>
     <groupId>io.cequence</groupId>
     <artifactId>openai-scala-client_2.12</artifactId>
-    <version>0.4.0</version>
+    <version>0.4.1</version>
 </dependency>
 ```

openai-core/README.md

@@ -1,4 +1,4 @@
-# OpenAI Scala Client - Core [![version](https://img.shields.io/badge/version-0.4.0-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
+# OpenAI Scala Client - Core [![version](https://img.shields.io/badge/version-0.4.1-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
 
 This is the core module, which contains mostly domain classes and the [OpenAIService](./src/main/scala/io/cequence/openaiscala/service/OpenAIService.scala) definition.
 Note that the full project documentation can be found [here](../README.md).
@@ -10,7 +10,7 @@ The currently supported Scala versions are **2.12, 2.13**, and **3**.
 To pull the library you have to add the following dependency to your *build.sbt*
 
 ```
-"io.cequence" %% "openai-scala-core" % "0.4.0"
+"io.cequence" %% "openai-scala-core" % "0.4.1"
 ```
 
 or to *pom.xml* (if you use maven)
@@ -19,6 +19,6 @@ or to *pom.xml* (if you use maven)
 <dependency>
     <groupId>io.cequence</groupId>
     <artifactId>openai-scala-core_2.12</artifactId>
-    <version>0.4.0</version>
+    <version>0.4.1</version>
 </dependency>
 ```

openai-guice/README.md

@@ -1,4 +1,4 @@
-# OpenAI Scala Client - Guice [![version](https://img.shields.io/badge/version-0.4.0-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
+# OpenAI Scala Client - Guice [![version](https://img.shields.io/badge/version-0.4.1-green.svg)](https://cequence.io) [![License](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://opensource.org/licenses/MIT)
 
 This module provides dependency injection for the OpenAI Scala client with a help of `Guice` library.
 Note that the full project documentation can be found [here](../README.md).
@@ -10,7 +10,7 @@ The currently supported Scala versions are **2.12, 2.13**, and **3**.
 To pull the library you have to add the following dependency to your *build.sbt*
 
 ```
-"io.cequence" %% "openai-scala-guice" % "0.4.0"
+"io.cequence" %% "openai-scala-guice" % "0.4.1"
 ```
 
 or to *pom.xml* (if you use maven)
@@ -19,6 +19,6 @@ or to *pom.xml* (if you use maven)
 <dependency>
     <groupId>io.cequence</groupId>
     <artifactId>openai-scala-guice_2.12</artifactId>
-    <version>0.4.0</version>
+    <version>0.4.1</version>
 </dependency>
 ```