Offline part 2 #61
Merged
Offline part 2 #61
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
- Add proactive model availability checking before LLM operations - Improve error detection to focus on specific 'try pulling it first' errors - Implement automatic model syncing from /root/.ollama/models/ to /models/ after successful pulls - Enhance rsync commands with --progress flag for better visibility - Fix nil pointer dereferences in timestamps.go for improved stability - Update schema version handling to use dynamic versions instead of hardcoded values - Set GIN web framework to release mode to eliminate debug warnings - Expand test coverage with comprehensive error detection tests - Add detailed logging for model operations and sync processes This commit significantly improves the robustness of Ollama model handling, ensures model persistence across container restarts, and provides better user feedback during model operations.
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Outdated suggestions cannot be applied.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.
This changes coordinates both changes forrm the 'kdeps/schema' repo, to be able to use embedded PKL assets. The assets pipeline was now being used by default in Kdeps to ensure it can evaluate the PKL without internet connection.
In addition, there are several fixes to Websockets and Ollama model caching to persistent storage.