LlamaIndex Parse Job

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://llamaindex.ai/schemas/llamaindex/parse-job.json",
  "title": "LlamaIndex Parse Job",
  "description": "A parse job in LlamaParse representing the asynchronous processing of a document through AI-powered parsing with configurable tiers for different quality and speed trade-offs.",
  "type": "object",
  "required": ["id", "status", "tier"],
  "properties": {
    "id": {
      "type": "string",
      "description": "Unique identifier of the parse job."
    },
    "status": {
      "type": "string",
      "enum": ["pending", "processing", "completed", "failed"],
      "description": "Current processing status of the parse job."
    },
    "tier": {
      "type": "string",
      "enum": ["fast", "cost_effective", "agentic", "agentic_plus"],
      "description": "Parsing tier that determines quality and speed trade-off. Fast outputs spatial text only. Cost-effective is optimized for text-heavy documents. Agentic handles images and diagrams. Agentic-plus provides maximum fidelity for complex layouts."
    },
    "version": {
      "type": "string",
      "description": "API version used for parsing. Use 'latest' for most recent or a specific date string for production stability.",
      "pattern": "^(latest|\\d{4}-\\d{2}-\\d{2})$"
    },
    "file_id": {
      "type": "string",
      "description": "Identifier of the uploaded file being parsed."
    },
    "source_url": {
      "type": "string",
      "format": "uri",
      "description": "URL of the document fetched for parsing, if provided instead of file_id."
    },
    "file_name": {
      "type": "string",
      "description": "Name of the parsed file."
    },
    "num_pages": {
      "type": "integer",
      "minimum": 0,
      "description": "Total number of pages in the document."
    },
    "target_pages": {
      "type": "string",
      "description": "Page range to parse using 1-based indexing (e.g., '1-5', '3,7,10').",
      "pattern": "^[\\d,\\-\\s]+$"
    },
    "result": {
      "$ref": "#/$defs/ParseResult"
    },
    "created_at": {
      "type": "string",
      "format": "date-time",
      "description": "Timestamp when the parse job was created."
    },
    "completed_at": {
      "type": "string",
      "format": "date-time",
      "description": "Timestamp when the parse job completed."
    }
  },
  "$defs": {
    "ParseResult": {
      "type": "object",
      "description": "The parsed output of a document containing extracted content in various formats.",
      "properties": {
        "text": {
          "type": "string",
          "description": "Plain text representation of the parsed content."
        },
        "markdown": {
          "type": "string",
          "description": "Markdown-formatted representation of the parsed content."
        },
        "json": {
          "type": "object",
          "additionalProperties": true,
          "description": "Structured JSON representation of the parsed content."
        },
        "pages": {
          "type": "array",
          "description": "Per-page parsing results.",
          "items": {
            "$ref": "#/$defs/ParsePage"
          }
        },
        "metadata": {
          "type": "object",
          "additionalProperties": true,
          "description": "Metadata extracted from the document."
        }
      }
    },
    "ParsePage": {
      "type": "object",
      "description": "Parsed content for a single page of a document.",
      "required": ["page_number"],
      "properties": {
        "page_number": {
          "type": "integer",
          "minimum": 1,
          "description": "1-based page number."
        },
        "text": {
          "type": "string",
          "description": "Plain text content of the page."
        },
        "markdown": {
          "type": "string",
          "description": "Markdown-formatted content of the page."
        }
      }
    }
  }
}