Configuration - General Information

Name

Identifying name of the assistant that can be customized according to your preferences.

Description

Detailed description of the purpose and capabilities of your assistant. This is a place to provide information about how the assistant enhances the end user experience.

Status

Indicates whether the assistant is enabled or disabled for use. 

Embeddings Settings

Specific parameters related to embeddings and related model characteristics:

• Provider Name

  Determines the language model service provider used by your RAG assistant. 
  This is a mandatory parameter that can take any of the following values:
  • azureopenai: To use Azure OpenAI.
  • fake: A fictitious value that could be useful for testing or simulation purposes.
  • googlevertexai: To use Google Vertex AI.
  • google: Check valid models here, you can set for example embedding-001, text-embedding-004 embeddings models⁽¹⁾ of 768 Dimensions. 
  • openai: To use OpenAI.

• Model Name

  Specific name of the model being used; supported values depend on the Provider Name selected.

  For example, if the Provider Name parameter has the "openai" value, Model Name takes the value 'text-embedding-ada-002' for assistants created up to 4/11/2024 and 'text-embedding-3-small' onwards.

• apiKey

  API authentication key provided to access the language model service.

For example, if the Provider parameter is "azureopenai", you must specify "apiKey" with the authentication key.

• Type

  It allows configuring the information processing approach for the embeddings model. It only applies for the following providers:

• CoHere (using awsprovider): search_document (default), search_query, classification, clustering.
• Google: RETRIEVAL_DOCUMENT (default), RETRIEVAL_QUERY, SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING, TASK_TYPE_UNSPECIFIED
• nvidia: passage, query

• endpoint

The URL pointing to the language model service (advanced).

• Dimensions 

It allows configuring the index dimensionality in the vectorStore. Each model has a specific dimension, and the default value is 1536, associated with the OpenAI provider.

⁽¹⁾ : Depending on the Provider Name and Model Name selected for your embeddings you will need to check the Dimensions value. By default is assumes 1536 which is valid for openAI text-embedding-ada-002, text-embedding-3-small and text-embedding-3-large (3072) shrinked to that value, check the troubleshooting section for more detail.

Notes:

• Please contact the help desk  if you want to use a Model Name with a Dimensions value other than 1536, as it must match the Vector Store Provider configuration in the Index section.
• If you change the Provider Name, Model Name, Dimensions it is recommended to reingest all your data.