azureMachineLearningIndexChatExtensionParameters

Parameters for the Azure Machine Learning vector index chat extension.

API ManagementCloudCloud ComputingEnterpriseInfrastructure as a ServicePlatform as a ServiceT1

Properties

Name	Type	Description
authentication	object
top_n_documents	integer	The configured top number of documents to feature for the configured query.
in_scope	boolean	Whether queries should be restricted to use of indexed data.
strictness	integer	The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.
role_information	string	Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses.
project_resource_id	string	The resource ID of the Azure Machine Learning project.
name	string	The Azure Machine Learning vector index name.
version	string	The version of the Azure Machine Learning vector index.
filter	string	Search filter. Only supported if the Azure Machine Learning vector index is of type AzureSearch.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/azureMachineLearningIndexChatExtensionParameters",
  "title": "azureMachineLearningIndexChatExtensionParameters",
  "required": [
    "authentication",
    "name",
    "project_resource_id",
    "version"
  ],
  "type": "object",
  "properties": {
    "authentication": {
      "oneOf": [
        {
          "$ref": "#/components/schemas/onYourDataAccessTokenAuthenticationOptions"
        },
        {
          "$ref": "#/components/schemas/onYourDataSystemAssignedManagedIdentityAuthenticationOptions"
        },
        {
          "$ref": "#/components/schemas/onYourDataUserAssignedManagedIdentityAuthenticationOptions"
        }
      ]
    },
    "top_n_documents": {
      "type": "integer",
      "description": "The configured top number of documents to feature for the configured query.",
      "format": "int32"
    },
    "in_scope": {
      "type": "boolean",
      "description": "Whether queries should be restricted to use of indexed data."
    },
    "strictness": {
      "maximum": 5,
      "minimum": 1,
      "type": "integer",
      "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.",
      "format": "int32"
    },
    "role_information": {
      "type": "string",
      "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit."
    },
    "project_resource_id": {
      "type": "string",
      "description": "The resource ID of the Azure Machine Learning project."
    },
    "name": {
      "type": "string",
      "description": "The Azure Machine Learning vector index name."
    },
    "version": {
      "type": "string",
      "description": "The version of the Azure Machine Learning vector index."
    },
    "filter": {
      "type": "string",
      "description": "Search filter. Only supported if the Azure Machine Learning vector index is of type AzureSearch."
    }
  },
  "description": "Parameters for the Azure Machine Learning vector index chat extension."
}