H2O.ai · Schema
AiAssistantCreateRequest
CompanyArtificial IntelligenceMachine LearningMLOpsGenerative AILLMRAGData ScienceModel DeploymentAI AgentsEnterprise AI
Properties
| Name | Type | Description |
|---|---|---|
| name | string | |
| description | string | |
| system_prompt | string | |
| llm | string | |
| llm_args | object | |
| custom_tool_definition | string | |
| mcp_servers | array | |
| credential_ids | array | |
| memory_block_id | string | |
| notification_email | string | |
| history_management | string | |
| history_max_chars | integer | |
| history_recent_chars | integer | Maximum characters of recent chat history kept uncompacted (default 10000) |
| history_retrieval_chars | integer | Maximum characters retrieved from vector DB for semantic retrieval (default 100000) |
| allowed_tool_actions | arraynull | List of allowed tool action names. NULL means all actions allowed (default). Empty array means no actions allowed. |
| allowed_trigger_types | arraynull | List of allowed trigger types. NULL means all triggers allowed (default). Valid values: user_message, forum_post, forum_mention, scheduled_task, manual, custom_event, assistant_message. |
| default_wake_period | integernull | Default periodic wake interval in seconds. When set, the system automatically wakes the assistant at this interval with its name and description as context. Min 60 (1 min), max 86400 (24 hours). Defau |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/api-evangelist/h2o-ai/main/json-schema/h2o-ai-ai-assistant-create-request-schema.json",
"title": "AiAssistantCreateRequest",
"x-generated": "2026-10-03",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/h2o-ai-ai-assistants-api-openapi.yml#/components/schemas/AiAssistantCreateRequest",
"required": [
"name",
"llm"
],
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"system_prompt": {
"type": "string"
},
"llm": {
"type": "string"
},
"llm_args": {
"type": "object"
},
"custom_tool_definition": {
"type": "string"
},
"mcp_servers": {
"type": "array",
"items": {
"type": "object"
}
},
"credential_ids": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
}
},
"memory_block_id": {
"type": "string",
"format": "uuid"
},
"notification_email": {
"type": "string"
},
"history_management": {
"type": "string",
"enum": [
"compactification",
"truncation",
"semantic_retrieval"
],
"default": "semantic_retrieval"
},
"history_max_chars": {
"type": "integer"
},
"history_recent_chars": {
"type": "integer",
"description": "Maximum characters of recent chat history kept uncompacted (default 10000)"
},
"history_retrieval_chars": {
"type": "integer",
"description": "Maximum characters retrieved from vector DB for semantic retrieval (default 100000)"
},
"allowed_tool_actions": {
"type": [
"array",
"null"
],
"items": {
"type": "string"
},
"description": "List of allowed tool action names. NULL means all actions allowed (default). Empty array means no actions allowed.\n"
},
"allowed_trigger_types": {
"type": [
"array",
"null"
],
"items": {
"type": "string"
},
"description": "List of allowed trigger types. NULL means all triggers allowed (default). Valid values: user_message, forum_post, forum_mention, scheduled_task, manual, custom_event, assistant_message.\n"
},
"default_wake_period": {
"type": [
"integer",
"null"
],
"description": "Default periodic wake interval in seconds. When set, the system automatically wakes the assistant at this interval with its name and description as context. Min 60 (1 min), max 86400 (24 hours). Default NULL (no periodic wake).\n"
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/h2o-ai-ai-assistant-create-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.