Add Support for Custom Embeddings

[raduburtea]

Add support for custom embeddings in the embedding folder.

This new class, that inherits from EmbeddingModel, would provide a generic template for calling any custom model that is deployed as an AzureML endpoint.

A new file called custom_embedding_model.py will be created in which the CustomEmbeddingModel class will be defined. This class should contain several methods to make an HTTP request, package the chunk to be embedded in a format readable by the endpoint and then retrieve the result from the endpoint.

Another case should be added in factory.py to support this new embedding type.

This idea has been vetted with @ritesh-modi