refactor: Enhance prompt, abstract const #14
Conversation
Update model, instruct wasn't working
WalkthroughThe codebase has been updated to refine the AI model interaction and enhance the code review process. The AI model default has been switched to a more specific version, and a new Changes
Poem
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (invoked as PR comments)
Additionally, you can add CodeRabbit Configration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Review Status
Actionable comments generated: 1
Configuration used: CodeRabbit UI
Files selected for processing (3)
- main.go (3 hunks)
- openai.go (1 hunks)
- prompt.go (1 hunks)
Files skipped from review due to trivial changes (1)
- prompt.go
Additional comments: 4
openai.go (2)
- 11-11: The method signature for
GetCompletionhas been updated to include apromptparameter. Ensure that all implementations and usages of this interface method are updated accordingly.- 16-16: The implementation of
GetCompletioninOpenAICompletionServicenow uses thepromptparameter. Verify that thepromptformat string is correctly designed to accept thediffas a formatting argument.Verification successful
The
promptparameter in theGetCompletionmethod of theOpenAICompletionServiceis correctly designed to accept thediffas a formatting argument, as evidenced by the linefullPrompt := fmt.Sprintf(prompt, diff)in the method implementation.Scripts Executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Verify that the prompt format string is correctly designed to accept the diff as a formatting argument. # This will search for the prompt variable definition and usage to ensure it's correctly formatted. rg --type go --context 5 'prompt :='Length of output: 38
Script:
#!/bin/bash # Search for the usage of the `prompt` parameter within the `GetCompletion` method in `openai.go`. ast-grep --lang go --pattern 'func ($_ *OpenAICompletionService) GetCompletion($_, $_, $_, prompt string) (string, error) { $$$ }'Length of output: 1031
main.go (2)
- 62-62: The
getCodeReviewsfunction now accepts apromptparameter. Ensure that all calls to this function have been updated to pass the new parameter.- 117-125: The concurrency implementation in
getCodeReviewsuses goroutines and channels. Ensure that there is proper synchronization and error handling for concurrent operations.
| @@ -15,7 +15,7 @@ import ( | |||
|
|
|||
| const ( | |||
| DefaultFilePerms = 0o644 | |||
| DefaultOpenAIModel = "gpt-3.5-turbo-instruct" | |||
| DefaultOpenAIModel = "gpt-3.5-turbo" | |||
There was a problem hiding this comment.
The search results confirm that the DefaultOpenAIModel constant is used in main.go and has been updated to "gpt-3.5-turbo". Additionally, the constant is referenced in the assignment of cliArgs.CompletionModel, which suggests that the change is indeed reflected in the code where it's used.
However, the search also reveals that the old model name "gpt-3.5-turbo-instruct" is still present in the README.md file. This indicates that the documentation has not been updated to reflect the change in the default model.
Based on these findings:
- The change to the
DefaultOpenAIModelconstant is reflected in the codebase. - The documentation in
README.mdneeds to be updated to align with the new default model.
Analysis chain
The DefaultOpenAIModel constant has been updated. Confirm that this change is reflected wherever the constant is used and that the new model is compatible with existing functionality.
Scripts Executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Confirm that the DefaultOpenAIModel constant change is reflected throughout the codebase.
rg --type go 'DefaultOpenAIModel'
# Additionally, check if there's any documentation or configuration that needs to be updated with the new model.
rg --type md --type yaml --type json 'gpt-3.5-turbo-instruct'
Length of output: 286
Update model, instruct wasn't working
Summary by CodeRabbit
New Features
Refactor