feat: HF /scan endpoint (#2566)

* start by checking /scan during the checksum update

Signed-off-by: Dave Lee <dave@gray101.com>

* add back in golang side features: downloader/uri gets struct and scan function, gallery uses it, and secscan/models calls it.

Signed-off-by: Dave Lee <dave@gray101.com>

* add a param to scan specific urls - useful for debugging

Signed-off-by: Dave Lee <dave@gray101.com>

* helpful printouts

Signed-off-by: Dave Lee <dave@gray101.com>

* fix offsets

Signed-off-by: Dave Lee <dave@gray101.com>

* fix error and naming

Signed-off-by: Dave Lee <dave@gray101.com>

* expose error

Signed-off-by: Dave Lee <dave@gray101.com>

* fix json tags

Signed-off-by: Dave Lee <dave@gray101.com>

* slight wording change

Signed-off-by: Dave Lee <dave@gray101.com>

* go mod tidy - getting warnings

Signed-off-by: Dave Lee <dave@gray101.com>

* split out python to make editing easier, add some simple code  to delete contaminated entries from gallery

Signed-off-by: Dave Lee <dave@gray101.com>

* o7 to my favorite part of our old name, go-skynet

Signed-off-by: Dave Lee <dave@gray101.com>

* merge fix

Signed-off-by: Dave Lee <dave@gray101.com>

* merge fix

Signed-off-by: Dave Lee <dave@gray101.com>

* merge fix

Signed-off-by: Dave Lee <dave@gray101.com>

* address review comments

Signed-off-by: Dave Lee <dave@gray101.com>

* forgot secscan could accept multiple URL at once

Signed-off-by: Dave Lee <dave@gray101.com>

* invert naming and actually use it

Signed-off-by: Dave Lee <dave@gray101.com>

* missed cli/models.go

Signed-off-by: Dave Lee <dave@gray101.com>

* Update .github/check_and_update.py

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Dave <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Dave 2024-07-10 07:18:32 -04:00 committed by GitHub
parent cbb93bd8ec
commit 133987b1fb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 282 additions and 125 deletions

View file

@ -1,6 +1,7 @@
package gallery
import (
"errors"
"fmt"
"os"
"path/filepath"
@ -94,7 +95,7 @@ func ReadConfigFile(filePath string) (*Config, error) {
return &config, nil
}
func InstallModel(basePath, nameOverride string, config *Config, configOverrides map[string]interface{}, downloadStatus func(string, string, string, float64)) error {
func InstallModel(basePath, nameOverride string, config *Config, configOverrides map[string]interface{}, downloadStatus func(string, string, string, float64), enforceScan bool) error {
// Create base path if it doesn't exist
err := os.MkdirAll(basePath, 0750)
if err != nil {
@ -112,9 +113,18 @@ func InstallModel(basePath, nameOverride string, config *Config, configOverrides
if err := utils.VerifyPath(file.Filename, basePath); err != nil {
return err
}
// Create file path
filePath := filepath.Join(basePath, file.Filename)
if enforceScan {
scanResults, err := downloader.HuggingFaceScan(file.URI)
if err != nil && !errors.Is(err, downloader.ErrNonHuggingFaceFile) {
log.Error().Str("model", config.Name).Strs("clamAV", scanResults.ClamAVInfectedFiles).Strs("pickles", scanResults.DangerousPickles).Msg("Contains unsafe file(s)!")
return err
}
}
if err := downloader.DownloadFile(file.URI, filePath, file.SHA256, i, len(config.Files), downloadStatus); err != nil {
return err
}