cli/internal/cmd/ml/cmd_publish.go
Claude e025577092
refactor: split CLI from monorepo, import core/go as library
- Change module from forge.lthn.ai/core/go to forge.lthn.ai/core/cli
- Remove pkg/ directory (now served from core/go)
- Add require + replace for forge.lthn.ai/core/go => ../go
- Update go.work to include ../go workspace module
- Fix all internal/cmd/* imports: pkg/ refs → forge.lthn.ai/core/go/pkg/
- Rename internal/cmd/sdk package to sdkcmd (avoids conflict with pkg/sdk)
- Remove SDK library files from internal/cmd/sdk/ (now in core/go/pkg/sdk/)
- Remove duplicate RAG helper functions from internal/cmd/rag/
- Remove stale cmd/core-ide/ (now in core/ide repo)
- Update IDE variant to remove core-ide import
- Fix test assertion for new module name
- Run go mod tidy to sync dependencies

core/cli is now a pure CLI application importing core/go for packages.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 14:22:18 +00:00

40 lines
1.3 KiB
Go

package ml
import (
"forge.lthn.ai/core/go/pkg/cli"
"forge.lthn.ai/core/go/pkg/ml"
)
var (
publishInputDir string
publishRepo string
publishPublic bool
publishToken string
publishDryRun bool
)
var publishCmd = &cli.Command{
Use: "publish",
Short: "Upload Parquet dataset to HuggingFace Hub",
Long: "Uploads train/valid/test Parquet files and an optional dataset card to a HuggingFace dataset repository.",
RunE: runPublish,
}
func init() {
publishCmd.Flags().StringVar(&publishInputDir, "input-dir", "", "Directory containing Parquet files (required)")
publishCmd.Flags().StringVar(&publishRepo, "repo", "lthn/LEM-golden-set", "HuggingFace dataset repo ID")
publishCmd.Flags().BoolVar(&publishPublic, "public", false, "Make dataset public")
publishCmd.Flags().StringVar(&publishToken, "token", "", "HuggingFace API token (defaults to HF_TOKEN env)")
publishCmd.Flags().BoolVar(&publishDryRun, "dry-run", false, "Show what would be uploaded without uploading")
_ = publishCmd.MarkFlagRequired("input-dir")
}
func runPublish(cmd *cli.Command, args []string) error {
return ml.Publish(ml.PublishConfig{
InputDir: publishInputDir,
Repo: publishRepo,
Public: publishPublic,
Token: publishToken,
DryRun: publishDryRun,
}, cmd.OutOrStdout())
}