Support for GitHub Models using the Azure AI Inference API (langchain…

…4j#1807)

Fix langchain4j#1719

This adds GitHub Models (see https://github.com/marketplace/models )
support with the new Azure AI Inference API Java SDK.

docs/docs/integrations/language-models/github-models.md

@@ -0,0 +1,151 @@
+---
+sidebar_position: 6
+---
+
+# GitHub Models
+
+If you want to develop a generative AI application, you can use GitHub Models to find and experiment with AI models for free.
+Once you are ready to bring your application to production, you can switch to a token from a paid Azure account.
+
+## GitHub Models Documentation
+
+- [GitHub Models Documentation](https://docs.github.com/en/github-models)
+- [GitHub Models Marketplace](https://github.com/marketplace/models)
+
+## Maven Dependency
+
+### Plain Java
+
+```xml
+<dependency>
+    <groupId>dev.langchain4j</groupId>
+    <artifactId>langchain4j-github-models</artifactId>
+    <version>0.34.0</version>
+</dependency>
+```
+
+## GitHub token
+
+To use GitHub Models, you need to use a GitHub token for authentication.
+
+Token are created and managed in [GitHub Developer Settings > Personal access tokens](https://github.com/settings/tokens).
+
+Once you have a token, you can set it as an environment variable and use it in your code:
+
+```bash
+export GITHUB_TOKEN="<your-github-token-goes-here>"
+```
+
+## Creating a `GitHubModelsChatModel` with a GitHub token
+
+### Plain Java
+
+```java
+GitHubModelsChatModel model = GitHubModelsChatModel.builder()
+        .gitHubToken(System.getenv("GITHUB_TOKEN"))
+        .modelName("gpt-4o-mini")
+        .build();
+```
+
+This will create an instance of `GitHubModelsChatModel`.
+Model parameters (e.g. `temperature`) can be customized by providing values in the `GitHubModelsChatModel`'s builder.
+
+### Spring Boot
+
+Create a `GitHubModelsChatModelConfiguration` Spring Bean:
+
+```Java
+package com.example.demo.configuration.github;
+
+import dev.langchain4j.model.chat.ChatLanguageModel;
+import dev.langchain4j.model.github.GitHubModelsChatModel;
+import org.springframework.beans.factory.annotation.Value;
+import org.springframework.context.annotation.Bean;
+import org.springframework.context.annotation.Configuration;
+import org.springframework.context.annotation.Profile;
+
+@Configuration
+@Profile("github")
+public class GitHubModelsChatModelConfiguration {
+
+    @Value("${GITHUB_TOKEN}")
+    private String gitHubToken;
+
+    @Bean
+    ChatLanguageModel gitHubModelsChatLanguageModel() {
+        return GitHubModelsChatModel.builder()
+                .gitHubToken(gitHubToken)
+                .modelName("gpt-4o-mini")
+                .logRequestsAndResponses(true)
+                .build();
+    }
+}
+```
+
+This configuration will create an `GitHubModelsChatModel` bean,
+which can be either used by an [AI Service](https://docs.langchain4j.dev/tutorials/spring-boot-integration/#langchain4j-spring-boot-starter)
+or autowired where needed, for example:
+
+```java
+@RestController
+class ChatLanguageModelController {
+
+    ChatLanguageModel chatLanguageModel;
+
+    ChatLanguageModelController(ChatLanguageModel chatLanguageModel) {
+        this.chatLanguageModel = chatLanguageModel;
+    }
+
+    @GetMapping("/model")
+    public String model(@RequestParam(value = "message", defaultValue = "Hello") String message) {
+        return chatLanguageModel.generate(message);
+    }
+}
+```
+
+## Creating a `GitHubModelsStreamingChatModel` with a GitHub token
+
+### Plain Java
+
+```java
+GitHubModelsStreamingChatModel model = GitHubModelsStreamingChatModel.builder()
+        .gitHubToken(System.getenv("GITHUB_TOKEN"))
+        .modelName("gpt-4o-mini")
+        .logRequestsAndResponses(true)
+        .build();
+```
+
+### Spring Boot
+
+Create a `GitHubModelsStreamingChatModelConfiguration` Spring Bean:
+```Java
+package com.example.demo.configuration.github;
+
+import dev.langchain4j.model.chat.ChatLanguageModel;
+import dev.langchain4j.model.github.GitHubModelsChatModel;
+import org.springframework.beans.factory.annotation.Value;
+import org.springframework.context.annotation.Bean;
+import org.springframework.context.annotation.Configuration;
+import org.springframework.context.annotation.Profile;
+
+@Configuration
+@Profile("github")
+public class GitHubModelsStreamingChatModelConfiguration {
+
+    @Value("${GITHUB_TOKEN}")
+    private String gitHubToken;
+
+    @Bean
+    GitHubModelsStreamingChatModel gitHubModelsStreamingChatLanguageModel() {
+        return GitHubModelsStreamingChatModel.builder()
+                .gitHubToken(System.getenv("GITHUB_TOKEN"))
+                .modelName("gpt-4o-mini")
+                .logRequestsAndResponses(true)
+                .build();
+    }
+}
+```
+
+## Examples
+
+- [GitHub Models Examples](https://github.com/langchain4j/langchain4j-examples/tree/main/github-models-examples/src/main/java)

docs/docs/integrations/language-models/google-ai-gemini.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 6
+sidebar_position: 7
 ---
 
 # Google AI Gemini

docs/docs/integrations/language-models/google-palm.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 8
+sidebar_position: 9
 ---
 
 # Google Vertex AI PaLM 2

docs/docs/integrations/language-models/google-vertex-ai-gemini.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 7
+sidebar_position: 8
 ---
 
 # Google Vertex AI Gemini

docs/docs/integrations/language-models/hugging-face.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 9
+sidebar_position: 10
 ---
 
 # Hugging Face

docs/docs/integrations/language-models/index.md

@@ -11,6 +11,7 @@ sidebar_position: 0
 | [Azure OpenAI](/integrations/language-models/azure-open-ai)                      | ✅                                          | ✅                         | ✅                                             | text, image                    | ✅                                         |                                                   |        |                             |
 | [ChatGLM](/integrations/language-models/chatglm)                                 |                                            |                           |                                               | text                           |                                           |                                                   |        |                             |
 | [DashScope](/integrations/language-models/dashscope)                             | ✅                                          | ✅                         |                                               | text, image, audio             | ✅                                         |                                                   |        |                             |
+| [GitHub Models](/integrations/language-models/github-models)                     | ✅                                          | ✅                         | ✅                                             | text                    | ✅                                         |                                                   |        |                             |
 | [Google AI Gemini](/integrations/language-models/google-ai-gemini)               |                                            | ✅                         | ✅                                             | text, image, audio, video, PDF | ✅                                         |                                                   |        |                             |
 | [Google Vertex AI Gemini](/integrations/language-models/google-vertex-ai-gemini) | ✅                                          | ✅                         | ✅                                             | text, image, audio, video, PDF | ✅                                         |                                                   |        |                             |
 | [Google Vertex AI PaLM 2](/integrations/language-models/google-palm)             |                                            |                           |                                               | text                           |                                           |                                                   | ✅      |                             |

docs/docs/integrations/language-models/jlama.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 10
+sidebar_position: 11
 ---
 
 # Jlama

docs/docs/integrations/language-models/local-ai.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 11
+sidebar_position: 12
 ---
 
 # LocalAI

docs/docs/integrations/language-models/mistral-ai.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 12
+sidebar_position: 13
 ---
 
 # MistralAI

docs/docs/integrations/language-models/ollama.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 13
+sidebar_position: 14
 ---
 
 # Ollama

docs/docs/integrations/language-models/open-ai.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 14
+sidebar_position: 15
 ---
 
 # OpenAI

docs/docs/integrations/language-models/qianfan.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 15
+sidebar_position: 16
 ---
 
 # Qianfan

docs/docs/integrations/language-models/workers-ai.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 16
+sidebar_position: 17
 ---
 
 # Cloudflare Workers AI

docs/docs/integrations/language-models/zhipu-ai.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 17
+sidebar_position: 18
 ---
 
 # Zhipu AI

langchain4j-azure-open-ai/src/main/java/dev/langchain4j/model/azure/AzureOpenAiStreamingChatModel.java

@@ -148,10 +148,12 @@ public AzureOpenAiStreamingChatModel(String endpoint,
                                          Map<String, String> customHeaders) {
 
         this(deploymentName, tokenizer, maxTokens, temperature, topP, logitBias, user, n, stop, presencePenalty, frequencyPenalty, dataSources, enhancements, seed, responseFormat, listeners);
-        if(useAsyncClient)
+        if(useAsyncClient) {
             this.asyncClient = setupAsyncClient(endpoint, serviceVersion, apiKey, timeout, maxRetries, proxyOptions, logRequestsAndResponses, userAgentSuffix, customHeaders);
-        else
-            this.client = setupSyncClient(endpoint, serviceVersion, apiKey, timeout, maxRetries, proxyOptions, logRequestsAndResponses, userAgentSuffix, customHeaders);  }
+        } else {
+            this.client = setupSyncClient(endpoint, serviceVersion, apiKey, timeout, maxRetries, proxyOptions, logRequestsAndResponses, userAgentSuffix, customHeaders);
+        }
+    }
 
     public AzureOpenAiStreamingChatModel(String endpoint,
                                          String serviceVersion,