feat(embeddings): do not require to be configured (#1842)

Certain engines requires to know during model loading
if the embedding feature has to be enabled, however, it is impractical
to have to set it to ALL the backends that supports embeddings.

There are transformers and sentencentransformers that seamelessly handle
both cases, without having this settings to be explicitly enabled.

The case sussist only for ggml-based models that needs to enable
featuresets during model loading (and thus settings `embedding` is
required), however most of the other engines does not require this.

This change disables the check done at code side, making easier to use
embeddings by not having to specify explicitly `embeddings: true`.

Part of: https://github.com/mudler/LocalAI/issues/1373
This commit is contained in:
Ettore Di Giacinto 2024-03-15 18:14:23 +01:00 committed by GitHub
parent ae2e4fc2fe
commit 89351f1a7d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -10,10 +10,6 @@ import (
)
func ModelEmbedding(s string, tokens []int, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() ([]float32, error), error) {
if !backendConfig.Embeddings {
return nil, fmt.Errorf("endpoint disabled for this model by API configuration")
}
modelFile := backendConfig.Model
grpcOpts := gRPCModelOpts(backendConfig)