LocalAI/core/gallery/models.go

222 lines
5.9 KiB
Go
Raw Normal View History

package gallery
import (
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>
2024-07-10 11:18:32 +00:00
"errors"
"fmt"
"os"
"path/filepath"
"dario.cat/mergo"
lconfig "github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/pkg/downloader"
"github.com/mudler/LocalAI/pkg/utils"
"github.com/rs/zerolog/log"
"gopkg.in/yaml.v2"
)
/*
description: |
foo
license: ""
urls:
-
-
name: "bar"
config_file: |
# Note, name will be injected. or generated by the alias wanted by the user
threads: 14
files:
- filename: ""
sha: ""
uri: ""
prompt_templates:
- name: ""
content: ""
*/
// Config is the model configuration which contains all the model details
2023-06-25 20:51:02 +00:00
// This configuration is read from the gallery endpoint and is used to download and install the model
// It is the internal structure, separated from the request
type Config struct {
Description string `yaml:"description"`
Icon string `yaml:"icon"`
License string `yaml:"license"`
URLs []string `yaml:"urls"`
Name string `yaml:"name"`
ConfigFile string `yaml:"config_file"`
Files []File `yaml:"files"`
PromptTemplates []PromptTemplate `yaml:"prompt_templates"`
}
type File struct {
Filename string `yaml:"filename" json:"filename"`
SHA256 string `yaml:"sha256" json:"sha256"`
URI string `yaml:"uri" json:"uri"`
}
type PromptTemplate struct {
Name string `yaml:"name"`
Content string `yaml:"content"`
}
func GetGalleryConfigFromURL(url string, basePath string) (Config, error) {
var config Config
uri := downloader.URI(url)
err := uri.DownloadWithCallback(basePath, func(url string, d []byte) error {
return yaml.Unmarshal(d, &config)
})
if err != nil {
log.Error().Err(err).Str("url", url).Msg("failed to get gallery config for url")
return config, err
}
return config, nil
}
func ReadConfigFile(filePath string) (*Config, error) {
// Read the YAML file
yamlFile, err := os.ReadFile(filePath)
if err != nil {
return nil, fmt.Errorf("failed to read YAML file: %v", err)
}
// Unmarshal YAML data into a Config struct
var config Config
err = yaml.Unmarshal(yamlFile, &config)
if err != nil {
return nil, fmt.Errorf("failed to unmarshal YAML: %v", err)
}
return &config, nil
}
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>
2024-07-10 11:18:32 +00:00
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 {
return fmt.Errorf("failed to create base path: %v", err)
}
if len(configOverrides) > 0 {
log.Debug().Msgf("Config overrides %+v", configOverrides)
}
// Download files and verify their SHA
for i, file := range config.Files {
log.Debug().Msgf("Checking %q exists and matches SHA", file.Filename)
if err := utils.VerifyPath(file.Filename, basePath); err != nil {
return err
}
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>
2024-07-10 11:18:32 +00:00
// Create file path
filePath := filepath.Join(basePath, file.Filename)
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>
2024-07-10 11:18:32 +00:00
if enforceScan {
scanResults, err := downloader.HuggingFaceScan(downloader.URI(file.URI))
if err != nil && errors.Is(err, downloader.ErrUnsafeFilesFound) {
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>
2024-07-10 11:18:32 +00:00
log.Error().Str("model", config.Name).Strs("clamAV", scanResults.ClamAVInfectedFiles).Strs("pickles", scanResults.DangerousPickles).Msg("Contains unsafe file(s)!")
return err
}
}
uri := downloader.URI(file.URI)
if err := uri.DownloadFile(filePath, file.SHA256, i, len(config.Files), downloadStatus); err != nil {
return err
}
}
// Write prompt template contents to separate files
for _, template := range config.PromptTemplates {
if err := utils.VerifyPath(template.Name+".tmpl", basePath); err != nil {
return err
}
// Create file path
filePath := filepath.Join(basePath, template.Name+".tmpl")
// Create parent directory
err := os.MkdirAll(filepath.Dir(filePath), 0750)
if err != nil {
return fmt.Errorf("failed to create parent directory for prompt template %q: %v", template.Name, err)
}
// Create and write file content
err = os.WriteFile(filePath, []byte(template.Content), 0600)
if err != nil {
return fmt.Errorf("failed to write prompt template %q: %v", template.Name, err)
}
log.Debug().Msgf("Prompt template %q written", template.Name)
}
name := config.Name
if nameOverride != "" {
name = nameOverride
}
if err := utils.VerifyPath(name+".yaml", basePath); err != nil {
return err
}
// write config file
if len(configOverrides) != 0 || len(config.ConfigFile) != 0 {
configFilePath := filepath.Join(basePath, name+".yaml")
// Read and update config file as map[string]interface{}
configMap := make(map[string]interface{})
err = yaml.Unmarshal([]byte(config.ConfigFile), &configMap)
if err != nil {
return fmt.Errorf("failed to unmarshal config YAML: %v", err)
}
configMap["name"] = name
if err := mergo.Merge(&configMap, configOverrides, mergo.WithOverride); err != nil {
return err
}
// Write updated config file
updatedConfigYAML, err := yaml.Marshal(configMap)
if err != nil {
return fmt.Errorf("failed to marshal updated config YAML: %v", err)
}
backendConfig := lconfig.BackendConfig{}
err = yaml.Unmarshal(updatedConfigYAML, &backendConfig)
if err != nil {
return fmt.Errorf("failed to unmarshal updated config YAML: %v", err)
}
if !backendConfig.Validate() {
return fmt.Errorf("failed to validate updated config YAML")
}
err = os.WriteFile(configFilePath, updatedConfigYAML, 0600)
if err != nil {
return fmt.Errorf("failed to write updated config file: %v", err)
}
log.Debug().Msgf("Written config file %s", configFilePath)
}
// Save the model gallery file for further reference
modelFile := filepath.Join(basePath, galleryFileName(name))
data, err := yaml.Marshal(config)
if err != nil {
return err
}
log.Debug().Msgf("Written gallery file %s", modelFile)
return os.WriteFile(modelFile, data, 0600)
//return nil
}
func galleryFileName(name string) string {
return "._gallery_" + name + ".yaml"
}