# AI and ML AI adapters and agents, chat sessions, knowledge notes, ML models and their configurations. ## Operations ```graphql # AI and ML (ai-ml) # AI adapters and agents, chat sessions, knowledge notes, ML models and their configurations. # Query chatAIAvailability: ChatAIAvailability! # Report configured adapter eligibility for this tenant compileSchemaXML: String! # Compile standalone XML schema syntax into JSON Schema without persisting it; host restrictions apply when embedded concept: Concept # Fetch a single concept by ID concepts: ConceptConnection! # List the tenant's concepts with pagination describeQuerySchema: QuerySchemaPayload! # Analyze a MicroSQL query and return the inferred result schema (column names, data types) without executing it exportMLModelConfig: ExportMLModelConfigPayload! # Export an ML model config as JSON or YAML generateDefaultDataQuery: String # Generate a default GraphQL data query for an event topic getAIAdapter: AIAdapterOutput # Fetch an AI adapter by ID getAIAgent: AIAgentState # Fetch an AI agent by ID getChatSession: ChatSessionState # Fetch a chat session by ID getMLModelConfig: MLModelConfigOutput # Fetch an ML model config by ID getMLModelConfigVersion: MLModelConfigVersionOutput # Get a specific ML model config version by ID getMagicQueryGraphQL: MagicQueryOperation! # Resolves a Magic Query string to the real GraphQL operation and variables it runs, so consumers can graduate from the façade to raw GraphQL getMagicQuerySchema: MagicQuerySchema! # Returns the input JSON Schema and output introspection for a Magic Query noun, so consumers (especially LLMs) can learn its contract before calling magicQuery helpChapter: HelpChapter # Read a chapter of the current published manual edition helpChapters: [HelpChapterInfo!]! # List human-facing manual chapters from the running deployment iacGuides: [IaCGuide!]! # Every authoring guide, for a tool that syncs them to a folder iacSchema: IaCSchemaDocument! # The infrastructure-only view of this schema, for declarative tooling iacSchemaDocument: IaCSchemaDocumentPayload! # Fetch the JSON Schema document a SCHEMA-kind validator references, for declarative tooling iacValidate: IaCValidationResult! # Validate an infrastructure artifact knowledgeNote: KnowledgeNote # Fetch a single knowledge note by ID knowledgeNotes: KnowledgeNoteConnection! # List knowledge notes with pagination and filtering listAIAdapters: AIAdapterConnection! # List AI adapters with pagination and filtering listAIAgents: AIAgentConnection! # List AI agents with pagination listChatSessions: ChatSessionConnection! # List chat sessions with pagination and filtering listDataChangeEventTopics: [DataChangeEventGroup!]! # List all valid data change event topics, grouped by resource listMLModelConfigVersions: MLModelConfigVersionConnection! # List versions for an ML model config, newest first, with pagination listMLModelConfigs: MLModelConfigConnection! # List ML model configs with pagination and filtering listMagicQueries: [MagicQueryInfo!]! # Lists every available Magic Query noun with a short description and its options — the discovery entry point magicQuery: JSON! # Executes a Magic Query string and returns the predefined query's JSON result ping: String! # Health check endpoint renderSchemaXML: String! # Render JSON Schema as native XML without dropping unsupported keywords or changing a saved document reportQuery: ReportQueryPayload! # Execute a MicroSQL reporting query against the analytics schema retrieveKnowledge: KnowledgeRetrieval! # The retrieval (RAG) entry point schemaAuthoringCatalog: JSON! # Compiler-owned vocabulary for the standalone XML JSON Schema dialect, including native form annotations searchHelp: HelpSearchResult! # Search human-facing manuals using shared semantic and text retrieval # Mutation captureKnowledge: CaptureKnowledgePayload! # Capture a knowledge subgraph — concepts, a note, and instance/semantic edges — in one atomic transaction clearChatMessages: ChatSessionPayload! # Clear all messages from a chat session confirmKnowledgeNote: KnowledgeNotePayload! # Endorse a note: increments its confirmation count (raising its retrieval trust weight) and promotes a PENDING note to LIVE createAIAdapter: UpsertAIAdapterPayload! # Create a new AI adapter createAIAgent: UpsertAIAgentPayload! # Create a new AI agent createChatSession: ChatSessionPayload! # Create a new chat session createConcept: ConceptPayload! # Manually author a concept in the ontology createKnowledgeNote: KnowledgeNotePayload! # Contribute a knowledge note about a concept or an entity createMLModelConfig: UpsertMLModelConfigPayload! # Create a new ML model config deleteAIAdapter: DeletePayload! # Delete an AI adapter deleteAIAgent: DeletePayload! # Delete an AI agent deleteChatSession: DeletePayload! # Delete a chat session deleteConcept: DeletePayload! # Delete a concept deleteKnowledgeNote: DeletePayload! # Delete a note and any graph edges it sourced deleteMLModelConfig: DeletePayload! # Delete an ML model config forecastMLModel: ForecastMLModelPayload! # Forecast future values using a trained time-series model importMLModelConfig: ImportMLModelConfigPayload! # Import an ML model config from JSON or YAML markKnowledgeNotesContradict: KnowledgeNotePayload! # Record that two notes contradict each other; the conflict is surfaced by `retrieveKnowledge` via `KnowledgeHit predictMLModel: PredictMLModelPayload! # Run a prediction using a trained ML model previewMLModelPipeline: DataScriptPreview! # Run the data pipeline over a sample WITHOUT training and return the emitted fields publishMLModelVersion: PublishMLModelVersionPayload! # Set a version as the published version used for predictions retrainSystemModels: RetrainSystemModelsPayload! # Manually trigger retraining of all system-managed ML models for the current tenant sendChatMessage: ChatMessageResponse! # Send a message to a chat session and receive an AI response testAIAdapter: TestAIAdapterPayload! # Verify provider credentials and all effective configured models using provider model endpoints trainMLModel: TrainMLModelPayload! # Trigger training for an ML model unmarkKnowledgeNotesContradict: KnowledgeNotePayload! # Remove a previously recorded contradiction between two notes updateAIAdapter: UpsertAIAdapterPayload! # Update an AI adapter updateAIAgent: UpsertAIAgentPayload! # Update an AI agent updateChatSession: ChatSessionPayload! # Update an existing chat session updateConcept: ConceptPayload! # Rename or reclassify an existing concept updateKnowledgeNote: KnowledgeNotePayload! # Edit a note's body or scope, or supersede it with a replacement updateMLModelConfig: UpsertMLModelConfigPayload! # Update an ML model config upsertAIAdapter: UpsertAIAdapterPayload! # Create or update an AI adapter upsertAIAgent: UpsertAIAgentPayload! # Create or update an AI agent upsertMLModelConfig: UpsertMLModelConfigPayload! # Create or update an ML model config upsertMLModelSource: UpsertMLModelConfigPayload! # Create or replace ML XML authoring source # Subscription chatMessageStream: ChatSessionStreamChunk! # Stream AI responses for a chat message in real-time dataChangeEvents: DataChangeEvent! # Subscribe to real-time data change events mlModelTrainingStatus: MLModelTrainingStatusEvent! # Stream real-time training status events for an ML model config # Call describe_operation(name) for arguments and input types. ``` ## Exact schema Download [complete SDL](/schemas/ai-ml.graphql) (144295 bytes). Use the SDL to validate operations; the digest omits argument signatures. ## Guides