{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/vectara/main/json-schema/vectara-corpus-schema.json",
  "title": "Vectara Corpus",
  "description": "A Vectara corpus is a container of indexed documents used for retrieval and grounded generation.",
  "type": "object",
  "required": ["key", "name"],
  "properties": {
    "key": {
      "type": "string",
      "description": "Unique key identifying the corpus."
    },
    "name": {
      "type": "string",
      "description": "Human-readable corpus name."
    },
    "description": {
      "type": "string",
      "description": "Description of the corpus and its intended contents."
    },
    "queries_are_answers": {
      "type": "boolean",
      "description": "Whether stored queries should be treated as answers (question-answer corpora)."
    },
    "documents_are_questions": {
      "type": "boolean",
      "description": "Whether stored documents should be treated as questions."
    },
    "encoder_id": {
      "type": "string",
      "description": "Identifier of the embedding encoder used by the corpus."
    },
    "filter_attributes": {
      "type": "array",
      "items": { "$ref": "#/$defs/FilterAttribute" }
    },
    "custom_dimensions": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": { "type": "string" },
          "description": { "type": "string" }
        }
      }
    },
    "enabled": {
      "type": "boolean",
      "description": "Whether the corpus accepts indexing and queries."
    },
    "created_at": {
      "type": "string",
      "format": "date-time"
    }
  },
  "$defs": {
    "FilterAttribute": {
      "type": "object",
      "properties": {
        "name": { "type": "string" },
        "level": { "type": "string", "enum": ["document", "document_part"] },
        "indexed": { "type": "boolean" },
        "type": { "type": "string", "enum": ["text", "integer", "real", "boolean"] }
      }
    }
  }
}