convert

package

v0.1.0 Latest Latest Go to latest Published: Jul 18, 2026 License: AGPL-3.0 Imports: 5 Imported by: 0

Details

Valid go.mod file
Redistributable license
Tagged version
Stable version
Learn more about best practices

Repository

github.com/0xmhha/code-knowledge-vector

Links

Open Source Insights

Documentation ¶

Overview ¶

Package convert wraps external model conversion tools (optimum-cli, coremltools) as subprocess calls. CKV does not implement conversion logic itself — it delegates to well-tested Python tools.

Supported conversions:

PyTorch/SafeTensors → ONNX (via HuggingFace optimum-cli)
ONNX → CoreML .mlpackage (via Apple coremltools)

Index ¶

func DetectFormat(modelDir string) (hasONNX, hasCoreML, hasSafeTensors bool)
func ToCoreML(ctx context.Context, inputPath, outputPath string) error
func ToONNX(ctx context.Context, modelID, outputDir string) error

Constants ¶

This section is empty.

Variables ¶

This section is empty.

Functions ¶

func DetectFormat ¶

func DetectFormat(modelDir string) (hasONNX, hasCoreML, hasSafeTensors bool)

DetectFormat inspects a model directory and returns which formats are available.

func ToCoreML ¶

func ToCoreML(ctx context.Context, inputPath, outputPath string) error

ToCoreML converts an ONNX model to CoreML .mlpackage format using coremltools. inputPath is the path to model.onnx. outputPath is the destination .mlpackage directory.

Requires: pip install coremltools

func ToONNX ¶

func ToONNX(ctx context.Context, modelID, outputDir string) error

ToONNX converts a HuggingFace model to ONNX format using optimum-cli. modelID is the HuggingFace model identifier (e.g. "BAAI/bge-m3") or a local directory containing a PyTorch model. outputDir receives the converted ONNX files.

Requires: pip install optimum[exporters]

Types ¶

This section is empty.

Source Files ¶

View all Source files

convert.go

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL