Korely · Schema

SearchBody

Artificial IntelligenceMemoryBi-temporalAgents

Properties

Name Type Description
query string
user_id object
agent_id object
run_id object Scope to one run/session.
metadata object Filter on the metadata you stored at write time, e.g. {"tier": "pro"}. Keys are ANDed. A value matches the stored value compared as text (true, false and numbers as JSON writes them, so "5" matches 5)
limit integer
exclude_sessions boolean Leave out the work sessions (memories written with `kind: session`, what a coding assistant's hooks save), for a read that wants what was said and decided. Default false: everything.
min_score object Leave out the memories whose `score` is below this, 0 to 1 (a cosine similarity, compared as the response shows it). Absent: no floor, every nearest memory comes back. Fewer than `limit` results can c
types array What to search, a list of kinds, each once: `memories` (the default, alone) the memories, as before 1.0.13; `facts` the facts true now (those GET /v1/facts lists, the ones written with POST /v1/facts
full_text boolean Also return each result's whole text as `content`: a memory's as it is stored, a fact's line (`subject · predicate · object`, its dates). `snippet` stays its first 280 characters. Default false: no `c
View JSON Schema on GitHub

JSON Schema

korely-ai-search-body-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/korely-ai/json-schema/korely-ai-search-body-schema.json",
  "title": "SearchBody",
  "x-generated": "2026-11-14",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/korely-ai-openapi.json#/components/schemas/SearchBody",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1,
      "title": "Query"
    },
    "user_id": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 255
        },
        {
          "type": "null"
        }
      ],
      "title": "User Id"
    },
    "agent_id": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 255
        },
        {
          "type": "null"
        }
      ],
      "title": "Agent Id"
    },
    "run_id": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 255
        },
        {
          "type": "null"
        }
      ],
      "title": "Run Id",
      "description": "Scope to one run/session."
    },
    "metadata": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "title": "Metadata",
      "description": "Filter on the metadata you stored at write time, e.g. {\"tier\": \"pro\"}. Keys are ANDed. A value matches the stored value compared as text (true, false and numbers as JSON writes them, so \"5\" matches 5), a number also matches an equal number (5 and 5.0), and null matches a stored null. Strings, numbers, booleans and null only: an object or an array is a 422. At most 32 keys and 8,192 bytes, what stored metadata may hold: past either it is a 422."
    },
    "limit": {
      "type": "integer",
      "maximum": 50.0,
      "minimum": 1.0,
      "title": "Limit",
      "default": 15
    },
    "exclude_sessions": {
      "type": "boolean",
      "title": "Exclude Sessions",
      "description": "Leave out the work sessions (memories written with `kind: session`, what a coding assistant's hooks save), for a read that wants what was said and decided. Default false: everything.",
      "default": false
    },
    "min_score": {
      "anyOf": [
        {
          "type": "number",
          "maximum": 1.0,
          "minimum": 0.0
        },
        {
          "type": "null"
        }
      ],
      "title": "Min Score",
      "description": "Leave out the memories whose `score` is below this, 0 to 1 (a cosine similarity, compared as the response shows it). Absent: no floor, every nearest memory comes back. Fewer than `limit` results can come back, none when nothing in the store is that close. A higher floor drops more of the weak matches and, past some value, true ones too: the right value depends on your texts and on the embedding model."
    },
    "types": {
      "items": {
        "type": "string",
        "enum": [
          "memories",
          "facts"
        ]
      },
      "type": "array",
      "maxItems": 2,
      "minItems": 1,
      "title": "Types",
      "description": "What to search, a list of kinds, each once: `memories` (the default, alone) the memories, as before 1.0.13; `facts` the facts true now (those GET /v1/facts lists, the ones written with POST /v1/facts included; one still waiting for its vector is listed there and found once it has it), by the cosine of their own vector. With both, each kind is ranked by its own score and the rankings are merged by rank (reciprocal rank fusion, k = 60: the first memory, the first fact, the second memory...), not by score: how a fact's cosine compares with a memory's was not measured. The order of the list does not matter; at equal rank a memory comes first, so with `limit: 1` the best memory is the answer whenever there is one. When the request names `types`, each result says its `type`. `run_id`, `metadata` and `min_score` narrow the memories only: with `facts` in the list each of them is a 422.",
      "default": [
        "memories"
      ]
    },
    "full_text": {
      "type": "boolean",
      "title": "Full Text",
      "description": "Also return each result's whole text as `content`: a memory's as it is stored, a fact's line (`subject · predicate · object`, its dates). `snippet` stays its first 280 characters. Default false: no `content` in the results. A memory can hold 16,000 characters, so a page of 50 whole memories can be large.",
      "default": false
    }
  },
  "additionalProperties": false,
  "type": "object",
  "required": [
    "query"
  ]
}

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/korely-ai-search-body"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.