Cognee · Schema

Cognee Search Payload

Request body for the POST /api/v1/search endpoint

Artificial IntelligenceMemoryKnowledge GraphRAGAgentsGraph DatabaseVector SearchLLMOpen-Source

Properties

Name Type Description
search_type string Type of search to perform against the knowledge graph
datasets arraynull Dataset names to scope the search (resolved to datasets owned by caller)
dataset_ids arraynull Dataset UUIDs to scope the search (allows cross-user access if permitted)
query string The natural language search query
system_prompt stringnull System prompt to use for completion-type searches
node_name arraynull Filter results to specific node_sets defined during the add pipeline
top_k integernull Maximum number of results to return
only_context boolean Return only context without making an LLM completion call
verbose boolean Return verbose result details
skills arraynull Skills to enable for agentic search modes
tools arraynull Tools to enable for agentic search modes
max_iter integernull Maximum number of iterations for agentic search
View JSON Schema on GitHub

JSON Schema

cognee-search-payload.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://api.cognee.ai/schemas/search-payload",
  "title": "Cognee Search Payload",
  "description": "Request body for the POST /api/v1/search endpoint",
  "type": "object",
  "required": ["query"],
  "properties": {
    "search_type": {
      "type": "string",
      "enum": [
        "SUMMARIES",
        "CHUNKS",
        "RAG_COMPLETION",
        "TRIPLET_COMPLETION",
        "GRAPH_COMPLETION",
        "GRAPH_COMPLETION_DECOMPOSITION",
        "GRAPH_SUMMARY_COMPLETION",
        "CYPHER",
        "NATURAL_LANGUAGE",
        "GRAPH_COMPLETION_COT",
        "GRAPH_COMPLETION_CONTEXT_EXTENSION",
        "FEELING_LUCKY",
        "TEMPORAL",
        "CODING_RULES",
        "CHUNKS_LEXICAL",
        "AGENTIC_COMPLETION"
      ],
      "default": "GRAPH_COMPLETION",
      "description": "Type of search to perform against the knowledge graph"
    },
    "datasets": {
      "type": ["array", "null"],
      "items": {
        "type": "string"
      },
      "description": "Dataset names to scope the search (resolved to datasets owned by caller)"
    },
    "dataset_ids": {
      "type": ["array", "null"],
      "items": {
        "type": "string",
        "format": "uuid"
      },
      "description": "Dataset UUIDs to scope the search (allows cross-user access if permitted)"
    },
    "query": {
      "type": "string",
      "description": "The natural language search query",
      "default": "What is in the document?"
    },
    "system_prompt": {
      "type": ["string", "null"],
      "description": "System prompt to use for completion-type searches",
      "default": "Answer the question using the provided context. Be as brief as possible."
    },
    "node_name": {
      "type": ["array", "null"],
      "items": {
        "type": "string"
      },
      "description": "Filter results to specific node_sets defined during the add pipeline"
    },
    "top_k": {
      "type": ["integer", "null"],
      "minimum": 1,
      "default": 10,
      "description": "Maximum number of results to return"
    },
    "only_context": {
      "type": "boolean",
      "default": false,
      "description": "Return only context without making an LLM completion call"
    },
    "verbose": {
      "type": "boolean",
      "default": false,
      "description": "Return verbose result details"
    },
    "skills": {
      "type": ["array", "null"],
      "items": {
        "type": "string"
      },
      "description": "Skills to enable for agentic search modes"
    },
    "tools": {
      "type": ["array", "null"],
      "items": {
        "type": "string"
      },
      "description": "Tools to enable for agentic search modes"
    },
    "max_iter": {
      "type": ["integer", "null"],
      "minimum": 1,
      "description": "Maximum number of iterations for agentic search"
    }
  }
}

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.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/cognee-search-payload"
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.