AI & ML
Aiml
Explore the data types and operations available in Aiml.
88 operations
Lists every available Magic Query noun with a short description and its options — the discovery entry point.
listMLModelConfigsQueryList ML model configs with pagination and filtering. Requires mlmodelconfig:list permission.
listMLModelConfigVersionsQueryList versions for an ML model config, newest first, with pagination. Requires mlmodelconfig:read permission.
magicQueryQueryExecutes a Magic Query string and returns the predefined query's JSON result. On a bad noun or parameter, returns a structured error whose 'extensions' carry 'code', 'actionable_message', and 'suggestions' for self-correction.
markKnowledgeNotesContradictMutationRecord that two notes contradict each other; the conflict is surfaced by `retrieveKnowledge` via `KnowledgeHit.contradicts`. Requires knowledgeNote:write permission.
mlExperimentQueryOpen one of your ML experiments, which marks it active; null when you have no such experiment. Requires mlmodelconfig:execute permission and a signed-in user.
mlExperimentRunStatusSubscriptionStream one of your experiment runs: its current state, then its result when it finishes. Requires mlmodelconfig:execute permission and a signed-in user.
mlModelTrainingStatusSubscriptionStream real-time training status events for an ML model config.
myMLExperimentsQueryYour ML experiments, most recently active first, ordered as stored when each page is read: an experiment opened while you page moves to the front and may be skipped or repeated. Requires mlmodelconfig:execute permission and a signed-in user.
pingQueryHealth check endpoint
pinMLExperimentRunMutationPin or unpin one of your experiment runs. A pinned run never expires. Pinning is refused once the experiment has the workspace's maxPinnedRuns pinned runs ("Unpin a run first"), or when that setting is 0 ("Pinning is turned off in Settings"); unpinning never is. Requires mlmodelconfig:execute permission and a signed-in user.
predictMLExperimentRunMutationTry one of your experiment runs: predict with its model. Expired and forecast runs are refused. Requires mlmodelconfig:execute permission and a signed-in user.
predictMLModelMutationRun a prediction using a trained ML model. Requires mlmodelconfig:execute permission.
previewMLExperimentPipelineMutationRun an experiment's data pipeline over a sample of its CSV WITHOUT training and return the emitted fields. Requires mlmodelconfig:execute permission and a signed-in user.
previewMLModelPipelineMutationRun the data pipeline over a sample WITHOUT training and return the emitted fields. Requires mlmodelconfig:execute permission.
publishMLModelVersionMutationSet a version as the published version used for predictions. Requires mlmodelconfig:write permission.
renderSchemaXMLQueryRender JSON Schema as native XML without dropping unsupported keywords or changing a saved document.
reportQueryQueryExecute a MicroSQL reporting query against the analytics schema. Supports SELECT with WHERE, JOIN, ORDER BY, GROUP BY, LIMIT. Tenant isolation is enforced automatically. Covers production (jobs, components, operations, milestones), prepress, scheduling (work_centers, planned_operations, schedule_allocations), sales (estimates, orders, invoices), cost accounting, catalog/inventory (products, substrates, warehouse_stock), logistics (shipments), tasks, time-series (metric_points, progress_points), and people (users, teams). Per-table IAM authorization is enforced — requires :list on each table's resource.
retrainSystemModelsMutationManually trigger retraining of all system-managed ML models for the current tenant. Requires mlmodelconfig:execute permission.
retrieveKnowledgeQueryThe retrieval (RAG) entry point. Given the entities in context (`seeds`) and an optional `query`, returns the most relevant knowledge in two buckets — graph-reached and semantically-supporting — each ranked by a blended relevance score. Requires knowledgeNote:read permission.
schemaAuthoringCatalogQueryCompiler-owned vocabulary for the standalone XML JSON Schema dialect, including native form annotations.
searchHelpQuerySearch human-facing manuals using shared semantic and text retrieval.
sendChatMessageMutationSend a message to a chat session and receive an AI response. Requires chatsession:write permission.
testAIAdapterMutationVerify provider credentials and all effective configured models using provider model endpoints. Does not generate content. Requires aiadapter:read permission.
trainMLExperimentMutationTrain an experiment's current XML on its CSV as a new numbered run. One run trains at a time per experiment, and at most two per workspace. Older unpinned runs beyond the workspace's keepUnpinnedRuns setting expire. Requires mlmodelconfig:execute permission and a signed-in user.
trainMLModelMutationTrigger training for an ML model. Requires mlmodelconfig:execute permission.
unmarkKnowledgeNotesContradictMutationRemove a previously recorded contradiction between two notes. Requires knowledgeNote:write permission.
updateAIAdapterMutationUpdate an AI adapter. Only provided fields are changed. Requires aiadapter:write permission.
updateAIAgentMutationUpdate an AI agent. Only provided fields are changed. Requires aiAgent:write permission.
updateChatSessionMutationUpdate an existing chat session. Requires chatsession:write permission.
updateConceptMutationRename or reclassify an existing concept. Requires concept:write permission.
updateKnowledgeNoteMutationEdit a note's body or scope, or supersede it with a replacement. The attachment is immutable. Requires knowledgeNote:write permission.
updateMLExperimentMutationRename one of your ML experiments or change its draft XML. Requires mlmodelconfig:execute permission and a signed-in user.
updateMLModelConfigMutationUpdate an ML model config. Only provided fields are changed. Requires mlmodelconfig:write permission.
upsertAIAdapterMutationCreate or update an AI adapter. Requires aiadapter:write permission.
upsertAIAgentMutationCreate or update an AI agent. Requires aiAgent:write permission.
upsertMLModelConfigMutationCreate or update an ML model config. Requires mlmodelconfig:write permission.
upsertMLModelSourceMutationCreate or replace ML XML authoring source. Updates require the observed authoring revision and preserve training and publication state.