Expand description
Response Cache Module
This module provides intelligent response caching with TTL (Time To Live) functionality
for OpenAI API responses. Following the “Thin Client, Rich API” principle, this module
offers configurable caching strategies without automatic behaviors.
This module is feature-gated behind the caching feature flag.
Modules§
- exposed
- Exposed namespace of the module.
- orphan
- Orphan namespace of the module.
- own
- Own namespace of the module.
- prelude
- Prelude to use essentials:
use my_module ::prelude :: *.
Structs§
- Cache
Config - Configuration for response caching behavior
- Cache
Entry - Cached response entry with metadata
- Cache
Key - Cache key generation and management
- Cache
Statistics - Cache statistics for monitoring and analysis
- Cached
Client - Cache-aware HTTP client wrapper
- Response
Cache - Advanced response cache with TTL and intelligent management