Llamaindex · Schema

LlamaIndex Extraction Agent

An extraction agent in LlamaExtract configured with a specific data schema and extraction settings for transforming unstructured documents into structured JSON representations.

AgentsFrameworkLLMOpen SourceRAGLlamaIndex

Properties

Name Type Description
id string Unique identifier of the extraction agent.
name string Human-readable name of the extraction agent.
project_id string Identifier of the project the agent belongs to.
description string Optional description of the extraction agent and its purpose.
data_schema object JSON Schema defining the structure of the data to extract from documents.
prompt string Optional prompt used for automatic schema inference from example documents.
extraction_jobs array Extraction jobs that have been run with this agent.
created_at string Timestamp when the extraction agent was created.
updated_at string Timestamp when the extraction agent was last updated.
View JSON Schema on GitHub

JSON Schema

llamaindex-extraction-agent-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://llamaindex.ai/schemas/llamaindex/extraction-agent.json",
  "title": "LlamaIndex Extraction Agent",
  "description": "An extraction agent in LlamaExtract configured with a specific data schema and extraction settings for transforming unstructured documents into structured JSON representations.",
  "type": "object",
  "required": ["id", "name", "project_id"],
  "properties": {
    "id": {
      "type": "string",
      "description": "Unique identifier of the extraction agent."
    },
    "name": {
      "type": "string",
      "description": "Human-readable name of the extraction agent.",
      "minLength": 1,
      "maxLength": 255
    },
    "project_id": {
      "type": "string",
      "description": "Identifier of the project the agent belongs to."
    },
    "description": {
      "type": "string",
      "description": "Optional description of the extraction agent and its purpose.",
      "maxLength": 1000
    },
    "data_schema": {
      "type": "object",
      "additionalProperties": true,
      "description": "JSON Schema defining the structure of the data to extract from documents."
    },
    "prompt": {
      "type": "string",
      "description": "Optional prompt used for automatic schema inference from example documents."
    },
    "extraction_jobs": {
      "type": "array",
      "description": "Extraction jobs that have been run with this agent.",
      "items": {
        "$ref": "#/$defs/ExtractionJob"
      }
    },
    "created_at": {
      "type": "string",
      "format": "date-time",
      "description": "Timestamp when the extraction agent was created."
    },
    "updated_at": {
      "type": "string",
      "format": "date-time",
      "description": "Timestamp when the extraction agent was last updated."
    }
  },
  "$defs": {
    "ExtractionJob": {
      "type": "object",
      "description": "An asynchronous extraction job that processes documents through an extraction agent.",
      "required": ["id", "extraction_agent_id", "status"],
      "properties": {
        "id": {
          "type": "string",
          "description": "Unique identifier of the extraction job."
        },
        "extraction_agent_id": {
          "type": "string",
          "description": "Identifier of the extraction agent used for this job."
        },
        "status": {
          "type": "string",
          "enum": ["pending", "processing", "completed", "failed"],
          "description": "Current status of the extraction job."
        },
        "file_ids": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Identifiers of the files being processed."
        },
        "results": {
          "type": "array",
          "description": "Extraction results for each processed file.",
          "items": {
            "$ref": "#/$defs/FileExtractionResult"
          }
        },
        "created_at": {
          "type": "string",
          "format": "date-time",
          "description": "Timestamp when the extraction job was created."
        },
        "completed_at": {
          "type": "string",
          "format": "date-time",
          "description": "Timestamp when the extraction job completed."
        }
      }
    },
    "FileExtractionResult": {
      "type": "object",
      "description": "Extraction result for a single processed file.",
      "required": ["file_id", "status"],
      "properties": {
        "file_id": {
          "type": "string",
          "description": "Identifier of the processed file."
        },
        "file_name": {
          "type": "string",
          "description": "Name of the processed file."
        },
        "data": {
          "type": "object",
          "additionalProperties": true,
          "description": "Structured data extracted from the file, conforming to the agent data schema."
        },
        "status": {
          "type": "string",
          "enum": ["success", "error"],
          "description": "Extraction status for this specific file."
        },
        "error": {
          "type": "string",
          "description": "Error message if extraction failed for this file."
        }
      }
    }
  }
}

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/llamaindex-extraction-agent"
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.