Chroma · Schema

Chroma Record

A Chroma record represents a single item stored in a collection, consisting of an embedding vector, optional document text, optional metadata, and an optional URI reference.

Artificial IntelligenceAI-NativeApache 2.0CloudEmbeddingsHybrid SearchJavaScriptLLMMachine-LearningMulti-ModalOpen-SourcePythonRAGRetrievalSDKSearchServerlessTypeScriptVector Database

Properties

Name Type Description
id string A unique identifier for the record within the collection. Must be unique across all records in the collection.
embedding arraynull The vector embedding for this record. Each element is a floating point number representing a dimension of the embedding space.
document stringnull The text document associated with this record. If provided without an embedding, the server will automatically generate an embedding from the document text.
metadata objectnull Key-value metadata associated with the record. Values can be strings, numbers, integers, or booleans. Metadata is searchable using where filters.
uri stringnull An optional URI reference associated with the record, typically pointing to the source content or an external resource.
View JSON Schema on GitHub

JSON Schema

chroma-record-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://trychroma.com/schemas/chroma/record.json",
  "title": "Chroma Record",
  "description": "A Chroma record represents a single item stored in a collection, consisting of an embedding vector, optional document text, optional metadata, and an optional URI reference.",
  "type": "object",
  "required": ["id"],
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "description": "A unique identifier for the record within the collection. Must be unique across all records in the collection."
    },
    "embedding": {
      "type": ["array", "null"],
      "items": {
        "type": "number",
        "format": "float"
      },
      "description": "The vector embedding for this record. Each element is a floating point number representing a dimension of the embedding space."
    },
    "document": {
      "type": ["string", "null"],
      "description": "The text document associated with this record. If provided without an embedding, the server will automatically generate an embedding from the document text."
    },
    "metadata": {
      "type": ["object", "null"],
      "additionalProperties": {
        "oneOf": [
          { "type": "string" },
          { "type": "number" },
          { "type": "integer" },
          { "type": "boolean" }
        ]
      },
      "description": "Key-value metadata associated with the record. Values can be strings, numbers, integers, or booleans. Metadata is searchable using where filters."
    },
    "uri": {
      "type": ["string", "null"],
      "format": "uri",
      "description": "An optional URI reference associated with the record, typically pointing to the source content or an external resource."
    }
  },
  "$defs": {
    "Embedding": {
      "type": "array",
      "items": {
        "type": "number",
        "format": "float"
      },
      "description": "A vector embedding represented as an array of floating point numbers"
    },
    "WhereFilter": {
      "type": "object",
      "description": "A metadata filter expression used to narrow search results based on record metadata values. Supports comparison operators ($eq, $ne, $gt, $gte, $lt, $lte, $in, $nin) and logical operators ($and, $or).",
      "additionalProperties": true
    },
    "WhereDocumentFilter": {
      "type": "object",
      "description": "A document content filter expression used to filter records by their document text. Supports $contains, $not_contains for substring matching and $regex, $not_regex for pattern matching.",
      "additionalProperties": true
    },
    "IncludeField": {
      "type": "string",
      "enum": ["embeddings", "documents", "metadatas", "distances", "uris"],
      "description": "A field that can be included in query and get responses"
    },
    "QueryResult": {
      "type": "object",
      "description": "The result of a vector similarity query, containing matched record IDs and optionally their embeddings, documents, metadatas, distances, and URIs",
      "required": ["ids"],
      "properties": {
        "ids": {
          "type": "array",
          "items": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "description": "Nested arrays of record IDs, one array per query"
        },
        "embeddings": {
          "type": ["array", "null"],
          "items": {
            "type": "array",
            "items": {
              "$ref": "#/$defs/Embedding"
            }
          },
          "description": "Nested arrays of embedding vectors, one array per query"
        },
        "documents": {
          "type": ["array", "null"],
          "items": {
            "type": "array",
            "items": {
              "type": ["string", "null"]
            }
          },
          "description": "Nested arrays of documents, one array per query"
        },
        "metadatas": {
          "type": ["array", "null"],
          "items": {
            "type": "array",
            "items": {
              "type": ["object", "null"],
              "additionalProperties": true
            }
          },
          "description": "Nested arrays of metadata objects, one array per query"
        },
        "distances": {
          "type": ["array", "null"],
          "items": {
            "type": "array",
            "items": {
              "type": "number",
              "format": "float"
            }
          },
          "description": "Nested arrays of distance scores, one array per query"
        },
        "uris": {
          "type": ["array", "null"],
          "items": {
            "type": "array",
            "items": {
              "type": ["string", "null"]
            }
          },
          "description": "Nested arrays of URIs, one array per 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/chroma-record"
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.