Embedding Settings

This component determines the details to be sent along with the Embedding request in the Embedding client. These values determine the behaviour of the mebdding client:

1. Embedding Model: The model to use for the mbedding request, this is the model that will be used to generate the embedding.
2. Token Limit: The maximum number of tokens to send to the embedding model, this is used to limit the amount of data sent to the model, and is used to ensure that the model does not exceed the maximum token limit for the model.
3. Max Tokens: The maximum number of tokens to return from the model, this is used to limit the amount of data returned from the model, and is used to ensure that the model does not exceed the maximum token limit for the model.
4. Chunk Size (Sentences): The number of sentences to chunk any body of text into. This setting is only used in conjunction with the Text Collections feature.