Omni Analytics

Gets data by generating and executing a query from natural language. Use this when the user has a question that is asking for data. For example, "how many users do I have?", "what was sales like last month?". When using this tool, if a user provides SQL, study the SQL, be succinct, and convert the SQL to a plain english question that describes what data the SQL is querying, and then call this tool with the prompt as that plain english description. IMPORTANT: You MUST have a topicId before calling getData. If no topic is currently selected, you MUST call pickTopic first to obtain a topicId. The topicId is a unique identifier for the topic and should not be modified. If modelId was not configured via headers, you must pass it as a parameter (call pickModel first to see available models). The tool returns both the generated query and the result set as a JSON object. This tool returns: 1. JSON Query results, 2. The Omni Query JSON blob that produced those results, (optional) 3. A workbook URL to view the full analysis within the Omni application -- If a workbook URL is present, always show it to the user.

Returns a list of models available to the current API key. Each model has an id, name, and label. Use this tool to discover which models are available before calling pickTopic or getData. For admin API keys, this returns all models in the organization. For user-scoped API keys, this returns only the models the user has access to. After calling this tool, select the most appropriate model for the user query and use its id when calling pickTopic and getData.

Select the most appropriate topic based on the provided prompt. Returns a topicId that should be used when calling getData. If no topic is currently selected, you must call this tool first to select a topic before getting data. If modelId was not configured via headers, you must pass it as a parameter (call pickModel first to see available models).