feat: implement OpenAI LLM client with full API support #3017
+912
−9
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Implements OpenAiLlmClient with complete functionality for OpenAI API: - chat(): Synchronous chat completion with response parsing for choices[0].message.content, finish_reason, model, and usage tokens - streamChat(): Server-Sent Events (SSE) based streaming with proper "data: " prefix handling and "[DONE]" marker detection - isAvailable(): API availability check using /models endpoint with API key validation Also adds comprehensive unit tests for both OpenAI and Ollama clients: - OpenAiLlmClientTest: Tests for getName, isAvailable (various cases), buildRequestBody, convertMessage, and HTTP client initialization - OllamaLlmClientTest: Matching test coverage for Ollama client The implementation follows the same patterns as OllamaLlmClient for consistency, using OkHttpClient and Jackson ObjectMapper.
Updates the default model for OpenAI LLM client from gpt-4o to gpt-5-mini in both configuration and test files.
Contributor
There was a problem hiding this comment.
Pull request overview
This PR implements a fully functional OpenAI LLM client with synchronous and streaming chat capabilities, along with API availability checking. It also adds comprehensive unit test coverage for both the new OpenAI client and the existing Ollama client.
Changes:
- Implemented complete OpenAI chat API integration with proper response parsing and SSE streaming support
- Added unit tests for OpenAI and Ollama LLM clients covering all core functionality
- Updated default OpenAI model configuration from gpt-4o to gpt-5-mini
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| src/main/java/org/codelibs/fess/llm/openai/OpenAiLlmClient.java | Implements chat(), streamChat(), and isAvailable() methods with full OpenAI API support including HTTP client management and JSON processing |
| src/test/java/org/codelibs/fess/llm/openai/OpenAiLlmClientTest.java | Comprehensive unit tests for OpenAI client covering availability checks, message conversion, request body building, and HTTP client initialization |
| src/test/java/org/codelibs/fess/llm/ollama/OllamaLlmClientTest.java | Matching test coverage for Ollama client to maintain consistency across LLM client implementations |
| src/main/resources/fess_config.properties | Updates default model configuration to gpt-5-mini |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implements OpenAiLlmClient with complete functionality for OpenAI API:
choices[0].message.content, finish_reason, model, and usage tokens
"data: " prefix handling and "[DONE]" marker detection
API key validation
Also adds comprehensive unit tests for both OpenAI and Ollama clients:
buildRequestBody, convertMessage, and HTTP client initialization
The implementation follows the same patterns as OllamaLlmClient for
consistency, using OkHttpClient and Jackson ObjectMapper.