[Feature Request] More LLM support #147

Activity

1. anc95

   added

   enhancementNew feature or requestNew feature or request

   on Nov 5, 2024
2. yirikanjinchanganhua commented on Dec 16, 2025

   

   yirikanjinchanganhua

   on Dec 16, 2025

   More actions

   So how's it going now? hopefully it will be available soon. @anc95
3. anc95 commented on Dec 20, 2025

   

   anc95

   on Dec 20, 2025

   Owner

   More actions

   like below example

   1. it's available to use the models provide by github
   2. as we changed to use openai library for llm calling, so you could revise the OPENAI_API_KEY and OPENAI_API_ENDPOINT to use other model provider as long as it follows the open ai api schema

   name: Code Review
   
   permissions:
     contents: read
     pull-requests: write
     models: true # if you choose use github models, set this to be true
   
   on:
     pull_request:
       types: [opened, reopened, synchronize]
   
   jobs:
     test:
       # if: ${{ contains(github.event.*.labels.*.name, 'gpt review') }} # Optional; to run only when a label is attached
       runs-on: ubuntu-latest
       steps:
         - uses: anc95/ChatGPT-CodeReview@main
           env:
             GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
   
             # if use github models https://github.com/marketplace/models
             USE_GITHUB_MODELS: true
             MODEL: openai/gpt-4o
   
             # else if use azure deployment
             AZURE_API_VERSION: xx
             AZURE_DEPLOYMENT: xx
   
             # else use standard llm model
             OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
             OPENAI_API_ENDPOINT: https://api.openai.com/v1
             MODEL: gpt-3.5-turbo # https://platform.openai.com/docs/models
   
             # common
             LANGUAGE: Chinese
             PROMPT: # example: Please check if there are any confusions or irregularities in the following code diff:
             top_p: 1 # https://platform.openai.com/docs/api-reference/chat/create#chat/create-top_p
             temperature: 1 # https://platform.openai.com/docs/api-reference/chat/create#chat/create-temperature
             max_tokens: 10000
             MAX_PATCH_LENGTH: 10000 # if the patch/diff length is large than MAX_PATCH_LENGTH, will be ignored and won't review. By default, with no MAX_PATCH_LENGTH set, there is also no limit for the patch/diff length.
             IGNORE_PATTERNS: /node_modules/**/*,*.md # glob pattern or regex pattern to ignore files, separated by comma
             INCLUDE_PATTERNS: *.js,*.ts # glob pattern or regex pattern to include files, separated by comma