tessl/maven-dev-langchain4j--langchain4j-github-models
This package provides a deprecated integration module that enables Java applications to interact with GitHub Models through the LangChain4j framework. It offers chat models (both synchronous and streaming), embedding models, and support for AI services with tool integration, JSON schema responses, and responsible AI features. The module wraps Azure AI Inference SDK to provide a unified API for accessing various language models hosted on GitHub Models, including chat completion capabilities, embeddings generation, and content filtering management. As of version 1.10.0, this module has been marked for deprecation and future removal, with users recommended to migrate to the langchain4j-openai-official module for enhanced functionality and better integration. The library is designed for reusability as a foundational component in LLM-powered Java applications that need to leverage GitHub-hosted AI models, offering builder patterns for configuration, support for proxy options, custom timeouts, and comprehensive model service versioning capabilities.
—
Quality
Pending
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
streaming-chat-model-api.mddocs/api/
Streaming Chat Model API Reference
API reference for GitHubModelsStreamingChatModel - streaming chat completion with real-time token generation.
Class
package dev.langchain4j.model.github;
public class GitHubModelsStreamingChatModel implements StreamingChatModel {
public void chat(ChatRequest request, StreamingChatResponseHandler handler);
public List<ChatModelListener> listeners();
public ModelProvider provider();
public static Builder builder();
}Methods
chat
public void chat(ChatRequest request, StreamingChatResponseHandler handler);Execute streaming chat completion with real-time token delivery.
Parameters:
request: ChatRequest - Messages, tools, and parametershandler: StreamingChatResponseHandler - Handler for streaming events
Throws:
- UnsupportedFeatureException - On unsupported features
Note: Errors delivered via handler.onError(), not thrown
listeners
public List<ChatModelListener> listeners();Get registered listeners.
Returns:
- List<ChatModelListener> - Registered listeners
provider
public ModelProvider provider();Get model provider identifier.
Returns:
- ModelProvider - Returns
ModelProvider.GITHUB_MODELS
builder
public static Builder builder();Create builder instance. Uses SPI factory if registered.
Returns:
- Builder - Builder instance
Builder API
public static class Builder {
// Required
public Builder gitHubToken(String gitHubToken);
public Builder modelName(String modelName);
public Builder modelName(GitHubModelsChatModelName modelName);
// Endpoint
public Builder endpoint(String endpoint);
public Builder serviceVersion(ModelServiceVersion serviceVersion);
// Sampling
public Builder temperature(Double temperature);
public Builder topP(Double topP);
public Builder maxTokens(Integer maxTokens);
public Builder presencePenalty(Double presencePenalty);
public Builder frequencyPenalty(Double frequencyPenalty);
public Builder seed(Long seed);
public Builder stop(List<String> stop);
// Response Format
public Builder responseFormat(ChatCompletionsResponseFormat responseFormat);
// Network
public Builder timeout(Duration timeout);
public Builder maxRetries(Integer maxRetries);
public Builder proxyOptions(ProxyOptions proxyOptions);
public Builder customHeaders(Map<String, String> customHeaders);
// Advanced
public Builder chatCompletionsAsyncClient(ChatCompletionsAsyncClient client);
public Builder listeners(List<ChatModelListener> listeners);
public Builder logRequestsAndResponses(boolean logRequestsAndResponses);
public Builder userAgentSuffix(String userAgentSuffix);
public GitHubModelsStreamingChatModel build();
}Builder Methods
See Chat Model API for detailed parameter documentation. Streaming builder methods are identical except:
chatCompletionsAsyncClient: Uses async client instead of sync client- No
strictJsonSchemamethod (not available for streaming)
chatCompletionsAsyncClient
public Builder chatCompletionsAsyncClient(ChatCompletionsAsyncClient client);Set custom Azure AI async client (overrides other config).
Parameters:
client: ChatCompletionsAsyncClient - Custom async client
Returns:
- Builder
StreamingChatResponseHandler Interface
public interface StreamingChatResponseHandler {
void onPartialResponse(String token);
void onCompleteResponse(ChatResponse response);
void onError(Throwable error);
}onPartialResponse
void onPartialResponse(String token);Called for each token as it's generated.
Parameters:
token: String - Generated token text
Threading: Called on background thread
onCompleteResponse
void onCompleteResponse(ChatResponse response);Called when streaming completes successfully.
Parameters:
response: ChatResponse - Complete response with metadata
Threading: Called on background thread
onError
void onError(Throwable error);Called if an error occurs during streaming.
Parameters:
error: Throwable - The error
Threading: Called on background thread
Types
import dev.langchain4j.model.chat.StreamingChatModel;
import dev.langchain4j.model.chat.request.ChatRequest;
import dev.langchain4j.model.chat.response.StreamingChatResponseHandler;
import dev.langchain4j.model.chat.response.ChatResponse;
import dev.langchain4j.model.chat.listener.ChatModelListener;
import dev.langchain4j.model.ModelProvider;
import com.azure.ai.inference.ChatCompletionsAsyncClient;
import com.azure.ai.inference.ModelServiceVersion;
import com.azure.ai.inference.models.ChatCompletionsResponseFormat;
import com.azure.core.http.ProxyOptions;
import java.time.Duration;
import java.util.List;
import java.util.Map;Install with Tessl CLI
npx tessl i tessl/maven-dev-langchain4j--langchain4j-github-models@1.11.0docs