auto-commit v0.1.5 fails with 'Couldn't complete prompt' error on macOS
Closed this issue · 1 comments
kieranklaassen commented
Summary:
Auto Commit 0.1.5 encounters a runtime error when analyzing a codebase on macOS (Darwin-aarch64). The error message suggests that the required model 'code-davinci-002' does not exist.
Installed version:
Auto Commit 0.1.5 (Darwin-aarch64)
Installation method:
Installed using the following command:
curl -fsSL https://raw.githubusercontent.com/m1guelpf/auto-commit/main/install.sh | sh -Error Message
Loading Data...
▐ ⠈ ▌ Analyzing Codebase...thread 'main' panicked at 'Couldn't complete prompt.: Api(ErrorMessage { message: "The model: `code-davinci-002` does not exist", error_type: "invalid_request_error" })', src/main.rs:137:10
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
▐ ⠂ ▌ Analyzing Codebase...
Steps to reproduce:
- Install Auto Commit 0.1.5 on macOS (Darwin-aarch64) using the provided installation command.
- Run auto-commit in a terminal.
- Observe the error message displayed during the "Analyzing Codebase" step.
Expected behavior:
Auto Commit should analyze the codebase without encountering any errors.
Actual behavior:
Auto Commit fails with a 'Couldn't complete prompt' error related to a missing model 'code-davinci-002'.
m1guelpf commented
Should be fixed in the latest release! 😄