[Feature] search only operation support

[wybryan]

What is it: adds a switch to configure GPTCache in search only mode, i.e. if cache misses, return None directly without calling LLM API.

Motivation: In certain application, we want to have full control on what to cache and when to update the cache, therefore whenever a cache miss happens, we don't want to call LLM API directly because the query used in cache search may be totally different to the query used in actual LLM call. if cache misses, we just want the code return with None so we know cache missd.

[sre-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: wybryan
To complete the pull request process, please assign simfg after the PR has been reviewed.
You can assign the PR to them by writing /assign @simfg in a comment when ready.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[sre-ci-robot]

Welcome @wybryan! It looks like this is your first PR to zilliztech/GPTCache 🎉

[wybryan]

/assign @SimFG

[codecov]

Codecov Report

Merging #445 (1fd33fb) into dev (10dcfae) will decrease coverage by 0.03%.
The diff coverage is 66.66%.

Additional details and impacted files

@@            Coverage Diff             @@
##              dev     #445      +/-   ##
==========================================
- Coverage   93.89%   93.87%   -0.03%     
==========================================
  Files          90       90              
  Lines        3327     3330       +3     
==========================================
+ Hits         3124     3126       +2     
- Misses        203      204       +1     

Impacted Files	Coverage Δ
gptcache/adapter/adapter.py	86.66% <66.66%> (-0.32%)	⬇️