Added caching for bing and llm result (for performance and result consistency)
Usage
To load from cache, change main.py line 5 to True
load_from_cache = True
If cache is not available, API is called to fetch result instead.
Result are auto-cached after fetching. One search text will have one cache per type (e.g. bing_search/openai/goose_ai) only, overwritten by latest API call.
Number of cache are limited in config.yaml line 26.
max_number_of_cache: 10
Changes
Usage To load from cache, change main.py line 5 to True
load_from_cache = True
If cache is not available, API is called to fetch result instead.Result are auto-cached after fetching. One search text will have one cache per type (e.g. bing_search/openai/goose_ai) only, overwritten by latest API call. Number of cache are limited in config.yaml line 26.
max_number_of_cache: 10