Cognee · Schema

Cognee Search Payload

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

AIMemoryKnowledge 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

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$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"
    }
  }
}