sempy_labs.rti package
Module contents
- sempy_labs.rti.nl_to_kql(kql_database: str | UUID, billing_item: str | UUID, billing_item_type: Literal['KQLQueryset', 'KQLDashboard', 'Eventhouse'], prompt: str, chat_messages: dict | List[dict] | None = None, user_shots: List[dict] | None = None, workspace: str | UUID | None = None) str
Returns a KQL query generated from natural language.
This is a wrapper function for the following API: Copilot - NL To KQL.
Service Principal Authentication is supported (see here for examples).
- Parameters:
kql_database (str | uuid.UUID) – The name or UUID of the KQL database.
billing_item (str | uuid.UUID) – The name or ID of the item for the request. This can be a KQLQueryset, KQLDashboard, or Eventhouse item. This item is used for billing the request.
billing_item_type (Literal["KQLQueryset", "KQLDashboard", "Eventhouse"]) – The type of the billing item.
prompt (str) – The natural language to generate the KQL query from.
chat_messages (Optional[str | List[str]], default=None) –
The chat messages for the request. The chat messages provide additional context for generating the KQL query if necessary.
- Example:
- chat_messages = [
- {
“content”: “Content….”, “role”: “User”
}, {
”content”: “Content…”, “role”: “Assistant”
}
]
user_shots (Optional[List[str]], default=None) –
The user shots for the request. This consists of user provided pairs of natural language and KQL queries in order to help in generating the current requested KQL query.
- Example:
- user_shots = [
- {
“kqlQuery”: “KQL Query….”, “naturalLanguage”: “Natural language….”
}, {
”kqlQuery”: “KQL Query…”, “naturalLanguage”: “Natural language…”
}
]
workspace (str | uuid.UUID, default=None) – The Fabric workspace name or ID. Defaults to None which resolves to the workspace of the attached lakehouse or if no lakehouse attached, resolves to the workspace of the notebook.
- Returns:
The generated KQL query.
- Return type: