mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 02:24:59 +00:00
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
GitHub
parent
cbb93bd8ec
commit
133987b1fb
15 changed files with 282 additions and 125 deletions
|
|
@ -2,6 +2,7 @@ package cli
|
|||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
|
||||
cliContext "github.com/mudler/LocalAI/core/cli/context"
|
||||
|
|
@ -24,7 +25,8 @@ type ModelsList struct {
|
|||
}
|
||||
|
||||
type ModelsInstall struct {
|
||||
ModelArgs []string `arg:"" optional:"" name:"models" help:"Model configuration URLs to load"`
|
||||
DisablePredownloadScan bool `env:"LOCALAI_DISABLE_PREDOWNLOAD_SCAN" help:"If true, disables the best-effort security scanner before downloading any files." group:"hardening" default:"false"`
|
||||
ModelArgs []string `arg:"" optional:"" name:"models" help:"Model configuration URLs to load"`
|
||||
|
||||
ModelsCMDFlags `embed:""`
|
||||
}
|
||||
|
|
@ -88,9 +90,15 @@ func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
|
|||
return err
|
||||
}
|
||||
|
||||
err = gallery.SafetyScanGalleryModel(model)
|
||||
if err != nil && !errors.Is(err, downloader.ErrNonHuggingFaceFile) {
|
||||
return err
|
||||
}
|
||||
|
||||
log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
|
||||
}
|
||||
err = startup.InstallModels(galleries, "", mi.ModelsPath, progressCallback, modelName)
|
||||
|
||||
err = startup.InstallModels(galleries, "", mi.ModelsPath, !mi.DisablePredownloadScan, progressCallback, modelName)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
|
|
|||
|
|
@ -42,26 +42,27 @@ type RunCMD struct {
|
|||
Threads int `env:"LOCALAI_THREADS,THREADS" short:"t" help:"Number of threads used for parallel computation. Usage of the number of physical cores in the system is suggested" group:"performance"`
|
||||
ContextSize int `env:"LOCALAI_CONTEXT_SIZE,CONTEXT_SIZE" default:"512" help:"Default context size for models" group:"performance"`
|
||||
|
||||
Address string `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
|
||||
CORS bool `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
|
||||
CORSAllowOrigins string `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
|
||||
LibraryPath string `env:"LOCALAI_LIBRARY_PATH,LIBRARY_PATH" help:"Path to the library directory (for e.g. external libraries used by backends)" default:"/usr/share/local-ai/libs" group:"backends"`
|
||||
CSRF bool `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
|
||||
UploadLimit int `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
|
||||
APIKeys []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
|
||||
DisableWebUI bool `env:"LOCALAI_DISABLE_WEBUI,DISABLE_WEBUI" default:"false" help:"Disable webui" group:"api"`
|
||||
OpaqueErrors bool `env:"LOCALAI_OPAQUE_ERRORS" default:"false" help:"If true, all error responses are replaced with blank 500 errors. This is intended only for hardening against information leaks and is normally not recommended." group:"api"`
|
||||
Peer2Peer bool `env:"LOCALAI_P2P,P2P" name:"p2p" default:"false" help:"Enable P2P mode" group:"p2p"`
|
||||
Peer2PeerToken string `env:"LOCALAI_P2P_TOKEN,P2P_TOKEN,TOKEN" name:"p2ptoken" help:"Token for P2P mode (optional)" group:"p2p"`
|
||||
ParallelRequests bool `env:"LOCALAI_PARALLEL_REQUESTS,PARALLEL_REQUESTS" help:"Enable backends to handle multiple requests in parallel if they support it (e.g.: llama.cpp or vllm)" group:"backends"`
|
||||
SingleActiveBackend bool `env:"LOCALAI_SINGLE_ACTIVE_BACKEND,SINGLE_ACTIVE_BACKEND" help:"Allow only one backend to be run at a time" group:"backends"`
|
||||
PreloadBackendOnly bool `env:"LOCALAI_PRELOAD_BACKEND_ONLY,PRELOAD_BACKEND_ONLY" default:"false" help:"Do not launch the API services, only the preloaded models / backends are started (useful for multi-node setups)" group:"backends"`
|
||||
ExternalGRPCBackends []string `env:"LOCALAI_EXTERNAL_GRPC_BACKENDS,EXTERNAL_GRPC_BACKENDS" help:"A list of external grpc backends" group:"backends"`
|
||||
EnableWatchdogIdle bool `env:"LOCALAI_WATCHDOG_IDLE,WATCHDOG_IDLE" default:"false" help:"Enable watchdog for stopping backends that are idle longer than the watchdog-idle-timeout" group:"backends"`
|
||||
WatchdogIdleTimeout string `env:"LOCALAI_WATCHDOG_IDLE_TIMEOUT,WATCHDOG_IDLE_TIMEOUT" default:"15m" help:"Threshold beyond which an idle backend should be stopped" group:"backends"`
|
||||
EnableWatchdogBusy bool `env:"LOCALAI_WATCHDOG_BUSY,WATCHDOG_BUSY" default:"false" help:"Enable watchdog for stopping backends that are busy longer than the watchdog-busy-timeout" group:"backends"`
|
||||
WatchdogBusyTimeout string `env:"LOCALAI_WATCHDOG_BUSY_TIMEOUT,WATCHDOG_BUSY_TIMEOUT" default:"5m" help:"Threshold beyond which a busy backend should be stopped" group:"backends"`
|
||||
Federated bool `env:"LOCALAI_FEDERATED,FEDERATED" help:"Enable federated instance" group:"federated"`
|
||||
Address string `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
|
||||
CORS bool `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
|
||||
CORSAllowOrigins string `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
|
||||
LibraryPath string `env:"LOCALAI_LIBRARY_PATH,LIBRARY_PATH" help:"Path to the library directory (for e.g. external libraries used by backends)" default:"/usr/share/local-ai/libs" group:"backends"`
|
||||
CSRF bool `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
|
||||
UploadLimit int `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
|
||||
APIKeys []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
|
||||
DisableWebUI bool `env:"LOCALAI_DISABLE_WEBUI,DISABLE_WEBUI" default:"false" help:"Disable webui" group:"api"`
|
||||
DisablePredownloadScan bool `env:"LOCALAI_DISABLE_PREDOWNLOAD_SCAN" help:"If true, disables the best-effort security scanner before downloading any files." group:"hardening" default:"false"`
|
||||
OpaqueErrors bool `env:"LOCALAI_OPAQUE_ERRORS" default:"false" help:"If true, all error responses are replaced with blank 500 errors. This is intended only for hardening against information leaks and is normally not recommended." group:"hardening"`
|
||||
Peer2Peer bool `env:"LOCALAI_P2P,P2P" name:"p2p" default:"false" help:"Enable P2P mode" group:"p2p"`
|
||||
Peer2PeerToken string `env:"LOCALAI_P2P_TOKEN,P2P_TOKEN,TOKEN" name:"p2ptoken" help:"Token for P2P mode (optional)" group:"p2p"`
|
||||
ParallelRequests bool `env:"LOCALAI_PARALLEL_REQUESTS,PARALLEL_REQUESTS" help:"Enable backends to handle multiple requests in parallel if they support it (e.g.: llama.cpp or vllm)" group:"backends"`
|
||||
SingleActiveBackend bool `env:"LOCALAI_SINGLE_ACTIVE_BACKEND,SINGLE_ACTIVE_BACKEND" help:"Allow only one backend to be run at a time" group:"backends"`
|
||||
PreloadBackendOnly bool `env:"LOCALAI_PRELOAD_BACKEND_ONLY,PRELOAD_BACKEND_ONLY" default:"false" help:"Do not launch the API services, only the preloaded models / backends are started (useful for multi-node setups)" group:"backends"`
|
||||
ExternalGRPCBackends []string `env:"LOCALAI_EXTERNAL_GRPC_BACKENDS,EXTERNAL_GRPC_BACKENDS" help:"A list of external grpc backends" group:"backends"`
|
||||
EnableWatchdogIdle bool `env:"LOCALAI_WATCHDOG_IDLE,WATCHDOG_IDLE" default:"false" help:"Enable watchdog for stopping backends that are idle longer than the watchdog-idle-timeout" group:"backends"`
|
||||
WatchdogIdleTimeout string `env:"LOCALAI_WATCHDOG_IDLE_TIMEOUT,WATCHDOG_IDLE_TIMEOUT" default:"15m" help:"Threshold beyond which an idle backend should be stopped" group:"backends"`
|
||||
EnableWatchdogBusy bool `env:"LOCALAI_WATCHDOG_BUSY,WATCHDOG_BUSY" default:"false" help:"Enable watchdog for stopping backends that are busy longer than the watchdog-busy-timeout" group:"backends"`
|
||||
WatchdogBusyTimeout string `env:"LOCALAI_WATCHDOG_BUSY_TIMEOUT,WATCHDOG_BUSY_TIMEOUT" default:"5m" help:"Threshold beyond which a busy backend should be stopped" group:"backends"`
|
||||
Federated bool `env:"LOCALAI_FEDERATED,FEDERATED" help:"Enable federated instance" group:"federated"`
|
||||
}
|
||||
|
||||
func (r *RunCMD) Run(ctx *cliContext.Context) error {
|
||||
|
|
@ -92,6 +93,7 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
|
|||
config.WithApiKeys(r.APIKeys),
|
||||
config.WithModelsURL(append(r.Models, r.ModelArgs...)...),
|
||||
config.WithOpaqueErrors(r.OpaqueErrors),
|
||||
config.WithEnforcedPredownloadScans(!r.DisablePredownloadScan),
|
||||
}
|
||||
|
||||
token := ""
|
||||
|
|
|
|||
|
|
@ -1,16 +1,22 @@
|
|||
package cli
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
|
||||
"github.com/rs/zerolog/log"
|
||||
|
||||
cliContext "github.com/mudler/LocalAI/core/cli/context"
|
||||
"github.com/mudler/LocalAI/core/config"
|
||||
"github.com/mudler/LocalAI/core/gallery"
|
||||
"github.com/mudler/LocalAI/pkg/downloader"
|
||||
gguf "github.com/thxcode/gguf-parser-go"
|
||||
)
|
||||
|
||||
type UtilCMD struct {
|
||||
GGUFInfo GGUFInfoCMD `cmd:"" name:"gguf-info" help:"Get information about a GGUF file"`
|
||||
HFScan HFScanCMD `cmd:"" name:"hf-scan" help:"Checks installed models for known security issues. WARNING: this is a best-effort feature and may not catch everything!"`
|
||||
}
|
||||
|
||||
type GGUFInfoCMD struct {
|
||||
|
|
@ -18,6 +24,12 @@ type GGUFInfoCMD struct {
|
|||
Header bool `optional:"" default:"false" name:"header" help:"Show header information"`
|
||||
}
|
||||
|
||||
type HFScanCMD struct {
|
||||
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
|
||||
Galleries string `env:"LOCALAI_GALLERIES,GALLERIES" help:"JSON list of galleries" group:"models" default:"${galleries}"`
|
||||
ToScan []string `arg:""`
|
||||
}
|
||||
|
||||
func (u *GGUFInfoCMD) Run(ctx *cliContext.Context) error {
|
||||
if u.Args == nil || len(u.Args) == 0 {
|
||||
return fmt.Errorf("no GGUF file provided")
|
||||
|
|
@ -53,3 +65,37 @@ func (u *GGUFInfoCMD) Run(ctx *cliContext.Context) error {
|
|||
|
||||
return nil
|
||||
}
|
||||
|
||||
func (hfscmd *HFScanCMD) Run(ctx *cliContext.Context) error {
|
||||
log.Info().Msg("LocalAI Security Scanner - This is BEST EFFORT functionality! Currently limited to huggingface models!")
|
||||
if len(hfscmd.ToScan) == 0 {
|
||||
log.Info().Msg("Checking all installed models against galleries")
|
||||
var galleries []config.Gallery
|
||||
if err := json.Unmarshal([]byte(hfscmd.Galleries), &galleries); err != nil {
|
||||
log.Error().Err(err).Msg("unable to load galleries")
|
||||
}
|
||||
|
||||
err := gallery.SafetyScanGalleryModels(galleries, hfscmd.ModelsPath)
|
||||
if err == nil {
|
||||
log.Info().Msg("No security warnings were detected for your installed models. Please note that this is a BEST EFFORT tool, and all issues may not be detected.")
|
||||
} else {
|
||||
log.Error().Err(err).Msg("! WARNING ! A known-vulnerable model is installed!")
|
||||
}
|
||||
return err
|
||||
} else {
|
||||
var errs error = nil
|
||||
for _, uri := range hfscmd.ToScan {
|
||||
log.Info().Str("uri", uri).Msg("scanning specific uri")
|
||||
scanResults, err := downloader.HuggingFaceScan(uri)
|
||||
if err != nil && !errors.Is(err, downloader.ErrNonHuggingFaceFile) {
|
||||
log.Error().Err(err).Strs("clamAV", scanResults.ClamAVInfectedFiles).Strs("pickles", scanResults.DangerousPickles).Msg("! WARNING ! A known-vulnerable model is included in this repo!")
|
||||
errs = errors.Join(errs, err)
|
||||
}
|
||||
}
|
||||
if errs != nil {
|
||||
return errs
|
||||
}
|
||||
log.Info().Msg("No security warnings were detected for your installed models. Please note that this is a BEST EFFORT tool, and all issues may not be detected.")
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue