- Removed the verbose logging feature from the OllamaAPI class and related classes.
- Updated logging statements to use debug level instead of info for model requests and responses.
- Cleaned up related test cases to reflect the removal of verbosity settings.
Improved descriptions in README and blog posts, removed outdated info from pull-model API docs, and updated several npm dependencies in package.json and package-lock.json for better compatibility and security.
Added new documentation for 'chat-with-thinking' and 'generate-thinking' APIs, including usage examples and streamed output. Updated existing API docs to improve example clarity, response formatting, and added more interactive output using TypewriterTextarea. Removed deprecated 'list-library-models' doc and made minor README updates.
fixes: #138
- Added error field to ModelPullResponse
- Enhanced error handling in doPullModel to check for errors in response body and throw OllamaBaseException with the specific error message
- Updated docs – Enhanced DBQueryFunction to validate input arguments and throw a RuntimeException if required arguments are missing.
- Updated docs – Refactored tool specifications for fuel price, weather, and employee details to use a unified prompt function structure. (Addresses #116).
- Improved javadoc for `chatStreaming()` API. (Addresses #115).
- Introduced `ToolInvocationException` to handle errors during tool invocation in OllamaAPI. (Addresses #117).
- Updated integration tests to include `ToolInvocationException` in method signatures for better error handling.
Introduced an examples section in the README to highlight the `ollama4j-examples` repository. Added an iframe and link in the chat API documentation for better reference. Adjusted formatting for improved readability and consistency.
