-
Notifications
You must be signed in to change notification settings - Fork 150
Improved performance, implemented caching improved error handling #102
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
- Applied Black formatting (line-length: 88) - Sorted imports with isort (black profile) - Applied Ruff auto-fixes Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
…or OpenAI integration
…ng, connection pooling, and background task management
Code Formatting CheckGreat job! Your code is already properly formatted according to our standards:
No changes needed! |
Warning Security Scan ResultsSome security scans failed, were skipped, or found issues.
View detailed reports in the workflow artifacts (if available). |
Warning Security Scan ResultsSome security scans failed, were skipped, or found issues.
View detailed reports in the workflow artifacts (if available). |
Code Formatting CheckGreat job! Your code is already properly formatted according to our standards:
No changes needed! |
This pull request introduces Memori version 2.3.1, focusing on major performance optimizations, improved stability, and enhanced logging and error handling. The release includes significant caching for context and search results, thread pool management for background tasks, and better database connection pooling—especially for remote databases. Additionally, there are improvements to logging clarity, error reporting, and resource cleanup. Several code changes also address recursion issues in search operations and ensure more robust integration with third-party services.
Performance & Stability Improvements:
Database Search & Recursion Fixes:
retrieval_agent.pyto useSearchServicedirectly, preventing recursive context injection and improving reliability for keyword and category searches. [1] [2] [3]Logging & Error Handling:
OpenAI Integration & Safety:
Security & Maintenance:
These changes collectively result in faster, safer, and more reliable operation, particularly when working with remote databases and high-concurrency environments.