zilliztech/GPTCache

[Feature]: Support more configs for openAI models

Open

#237 opened on Apr 18, 2023

View on GitHub
 (3 comments) (0 reactions) (1 assignee)Python (407 forks)batch import
help wanted

Repository metrics

Stars
 (5,857 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

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

  1. max_tokens? just bypass to GPT for now
  2. temperature: there are couple things we can do,
    1. randomly pick answer from returned result if they are all very similar.
    2. edit the answer with another small model：For instance image -> https://huggingface.co/lambdalabs/sd-image-variations-diffusers
  3. n -> if there no enough cached result, we will need to generate from OpenAI anyway.
  4. 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

Contributor guide

Research direction
Implement missing OpenAI completion parameters (max tokens, temperature, n, best of) in GPTCache. Study the current parameter handling and OpenAI API docs to add support for these fields.
Tech stack
python
Domain
backend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonOpenAI API
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60