v0.10.8
-
Paid Subscription Support (Beta): Added support for a paid subscription model.
-
System Performance Monitoring: Introduced system performance monitoring. When enabled, the system will reject new Relay requests (e.g.,
/v1,/v1beta) if resource usage exceeds configured thresholds, ensuring system stability. -
Cache Optimization: Further optimized caching functionality to reduce memory usage during large request bodies.
-
Bug Fix: Fixed an issue where
Chat2Responsescould not retrieve the chain of thought. -
Header Pass-through Support: Added support for full request header pass-through based on Go Regex rules. Please refer to the PR description for usage details: https://github.com/QuantumNous/new-api/pull/2840
-
Multi-language Backend Support: Added backend support for multiple languages, respecting user-level language preferences and the
Accept-Languagerequest header.