AzureMachineLearningIndexChatExtensionConfiguration interface
A specific representation of configurable options for Azure Machine Learning vector index when using it as an Azure OpenAI chat extension.
Properties
authentication | The authentication method to use when accessing the defined data source. Each data source type supports a specific set of available authentication methods; please see the documentation of the data source for supported mechanisms. If not otherwise provided, On Your Data will attempt to use System Managed Identity (default credential) authentication. |
filter | Search filter. Only supported if the Azure Machine Learning vector index is of type AzureSearch. |
in |
Whether queries should be restricted to use of indexed data. |
name | The Azure Machine Learning vector index name. |
project |
The resource ID of the Azure Machine Learning project. |
role |
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. |
strictness | The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer. |
top |
The configured top number of documents to feature for the configured query. |
type | The type label to use when configuring Azure OpenAI chat extensions. This should typically not be changed from its default value for Azure Machine Learning vector index. |
version | The version of the Azure Machine Learning vector index. |
Property Details
authentication
The authentication method to use when accessing the defined data source. Each data source type supports a specific set of available authentication methods; please see the documentation of the data source for supported mechanisms. If not otherwise provided, On Your Data will attempt to use System Managed Identity (default credential) authentication.
authentication?: OnYourDataAuthenticationOptionsUnion
Property Value
filter
Search filter. Only supported if the Azure Machine Learning vector index is of type AzureSearch.
filter?: string
Property Value
string
inScope
Whether queries should be restricted to use of indexed data.
inScope?: boolean
Property Value
boolean
name
The Azure Machine Learning vector index name.
name: string
Property Value
string
projectResourceId
The resource ID of the Azure Machine Learning project.
projectResourceId: string
Property Value
string
roleInformation
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.
roleInformation?: string
Property Value
string
strictness
The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.
strictness?: number
Property Value
number
topNDocuments
The configured top number of documents to feature for the configured query.
topNDocuments?: number
Property Value
number
type
The type label to use when configuring Azure OpenAI chat extensions. This should typically not be changed from its default value for Azure Machine Learning vector index.
type: "azure_ml_index"
Property Value
"azure_ml_index"
version
The version of the Azure Machine Learning vector index.
version: string
Property Value
string
Azure SDK for JavaScript