Added support to download binary data from the result grid.
Added support for custom LLM provider URLs for OpenAI and Anthropic, allowing use of OpenAI-compatible providers such as LM Studio, EXO, and LiteLLM.
Fixed an issue where AI features (AI Assistant tab, AI Reports menus, and AI Preferences) were visible in the UI even when LLM_ENABLED is set to False.
Allow copying of text from the AI Assistant chat panel.
Bugs/Housekeeping:
Fixed an issue where selecting all in the Query Tool's Messages tab would select the entire page content.
Fixed an issue where OAuth2 authentication fails with 'object has no attribute' if OAUTH2_AUTO_CREATE_USER is False.
Ensure that the Geometry Viewer refreshes when re-running queries or switching geometry columns, preventing stale data from being displayed.
Fixed an issue where the default fillfactor value for B-tree indexes was incorrect.
Fixed an issue where AI Reports are grayed out after setting an API key by auto-selecting the default provider.
Fixed an issue where AI Assistant does not notify that No API Key or Provider is Set.
Fixed an issue where AI Reports fail with OpenAI models that do not support the temperature parameter.
Improve the AI Assistant user prompt to be more descriptive of the actual functionality.
Fix an issue where the AI Assistant was not retaining conversation context between messages, with chat history compaction to manage token budgets
Support /v1/responses for OpenAI models.
Builds for Windows and macOS are available now, along with a Python Wheel, Docker Container, RPM, DEB Package, and source code tarball from:
