mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-04-26 01:06:23 +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. |
||
|---|---|---|
| .. | ||
| agents | ||
| config | ||
| connectors | ||
| indexing_pipeline | ||
| prompts | ||
| retriever | ||
| routes | ||
| schemas | ||
| services | ||
| tasks | ||
| utils | ||
| __init__.py | ||
| app.py | ||
| celery_app.py | ||
| db.py | ||
| users.py | ||