zilliztech/GPTCache
Auf GitHub ansehen[Feature]: Support more configs for openAI models
Open
#237 geöffnet am 18. Apr. 2023
help wanted
Repository-Metriken
- Stars
- (5.857 Stars)
- PR-Merge-Metriken
- (Keine gemergten PRs in 30 T)
Beschreibung
Is your feature request related to a problem? Please describe.
Due to the document of openAI, we missed some major parameters of openAI document, see:
https://platform.openai.com/docs/api-reference/completions/create
- max_tokens? just bypass to GPT for now
- temperature: there are couple things we can do,
- randomly pick answer from returned result if they are all very similar.
- edit the answer with another small model:For instance image -> https://huggingface.co/lambdalabs/sd-image-variations-diffusers
- n -> if there no enough cached result, we will need to generate from OpenAI anyway.
- bestof -> control the topk numbers we want to retrieved from cache
Describe the solution you'd like.
No response
Describe an alternate solution.
No response
Anything else? (Additional Context)
No response