dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat: queue up requests if not running parallel requests (#1296)

Browse source 
Return a GRPC which handles a lock in case it is not meant to be
parallel.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2023-11-16 22:20:16 +01:00 • committed by GitHub
parent 2addb9f99a
commit 548959b50f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 64 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

7
api/localai/backend_monitor.go
View file

@ -123,13 +123,12 @@ func BackendMonitorEndpoint(bm BackendMonitor) func(c *fiber.Ctx) error {
return err
}
client := bm.options.Loader.CheckIsLoaded(backendId)
if client == "" {
model := bm.options.Loader.CheckIsLoaded(backendId)
if model == "" {
return fmt.Errorf("backend %s is not currently loaded", backendId)
}
status, rpcErr := client.GRPC().Status(context.TODO())
status, rpcErr := model.GRPC(false).Status(context.TODO())
if rpcErr != nil {
log.Warn().Msgf("backend %s experienced an error retrieving status info: %s", backendId, rpcErr.Error())
val, slbErr := bm.SampleLocalBackendProcess(backendId)