mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-04-26 09:16:22 +02:00
f4b2ab0899
- Improved in-memory rate limiting by evicting timestamps outside the current window and cleaning up empty keys. - Updated LLM router service to cache context profiles and avoid redundant computations. - Introduced cache eviction logic for MCP tools and sandbox instances to manage memory usage effectively. - Added garbage collection triggers in chat streaming functions to reclaim resources promptly. |
||
|---|---|---|
| .. | ||
| celery_tasks | ||
| chat | ||
| connector_indexers | ||
| document_processors | ||
| __init__.py | ||
| composio_indexer.py | ||
| surfsense_docs_indexer.py | ||