Embedding Provider Options

Embedding providers allow ServerAssistantAI to find relevant information from the server's documents to include in the context sent to the chat providers.

Built-in Providers

Cohere

• Availability: Built-in, always available

• Name: cohere

• Options:

  • model (required): The name of the Cohere embedding model to use.

  • timeout (default: 120): The request timeout in seconds.

OpenAI

• Availability: Built-in, always available

• Name: openai

• Options:

  • model (required): The name of the OpenAI embedding model to use.

  • timeout (default: 120): The request timeout in seconds.

  • organization_id (default: ''): The ID of your OpenAI organization. Leave empty if not applicable.

  • base_url (default: 'https://api.openai.com/v1'): The base URL for the OpenAI API. You can use any OpenAI-compatible API by changing this value.

  • max_retries (default: 3): The maximum number of retries for failed requests.

  • max_request_segments (default: ''): Maximum number of segments per embedding request for OpenAI providers to split large embedding requests into smaller batches.

  • dimensions (default: 0): The number of dimensions in the embedding vector. Set to 0 for the default value.

Addon Providers

Azure OpenAI

• Availability: Azure OpenAI Addon

• Name: azure-openai

• Options:

  • deployment_name (required): The name of the Azure OpenAI deployment (model) to use.

  • timeout (default: 120): The request timeout in seconds.

  • max_retries (default: 3): The maximum number of retries for failed requests.

Google AI Studio

• Availability: Google AI Studio Addon

• Name: google-aistudio

• Options:

  • model (required): The name of the Google AI Studio embedding model to use.

  • timeout (default: 120): The request timeout in seconds.

HuggingFace

• Availability: HuggingFace Addon

• Name: huggingface

• Options:

  • model (required): The name of the HuggingFace embedding model to use.

  • timeout (default: 120): The request timeout in seconds.

Mistral AI

• Availability: Mistral AI Addon

• Name: mistralai

• Options:

  • model (required): The name of the Mistral AI embedding model to use.

  • timeout (default: 120): The request timeout in seconds.

  • base_url (default: 'https://api.mistral.ai/v1'): The base URL for the Mistral AI API. You can use any Mistral AI-compatible API by changing this value.

  • max_retries (default: 3): The maximum number of retries for failed requests.

Please note that the list of addon providers above may not include all available providers, as developers can create their own custom addons using the ServerAssistantAI API.