DocuPipe · Schema

Analysis

Public-facing representation of DocuPipeAnalysis.

Artificial IntelligenceDocument ExtractionDocument IntelligenceIntelligent Document ProcessingOCRDocument AI

Properties

Name Type Description
analysisId string Unique identifier of the analysis object.
jobId string Unique identifier of the job that created the analysis.
documentIds array List of document IDs that were analyzed.
filename string Name of the file that was analyzed, if there is only a single document.
dataset string Dataset which defines what documents are included in the analysis.
schemaId string Unique identifier of the schema used to fetch standardizations for querying.
numDocs integer Number of documents analyzed.
pages array List of page numbers to analyze. If none, all pages are analyzed. Only applies for single document.
data array List of questions and answers for the analysis, along with confidence and citations.
timestamp string Timestamp of the analysis job.
View JSON Schema on GitHub

JSON Schema

docupanda-analysis-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/docupanda/json-schema/docupanda-analysis-schema.json",
  "title": "Analysis",
  "description": "Public-facing representation of DocuPipeAnalysis.",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/docupanda-analysis-api-openapi.yml#/components/schemas/Analysis",
  "properties": {
    "analysisId": {
      "type": "string",
      "title": "Analysis ID",
      "description": "Unique identifier of the analysis object."
    },
    "jobId": {
      "type": "string",
      "title": "Job ID",
      "description": "Unique identifier of the job that created the analysis."
    },
    "documentIds": {
      "items": {
        "type": "string"
      },
      "type": "array",
      "title": "Document IDs",
      "description": "List of document IDs that were analyzed."
    },
    "filename": {
      "type": "string",
      "title": "Filename",
      "description": "Name of the file that was analyzed, if there is only a single document."
    },
    "dataset": {
      "type": "string",
      "title": "Dataset",
      "description": "Dataset which defines what documents are included in the analysis."
    },
    "schemaId": {
      "type": "string",
      "title": "Schema ID",
      "description": "Unique identifier of the schema used to fetch standardizations for querying."
    },
    "numDocs": {
      "type": "integer",
      "title": "Number of Documents",
      "description": "Number of documents analyzed."
    },
    "pages": {
      "items": {
        "type": "integer"
      },
      "type": "array",
      "title": "Pages",
      "description": "List of page numbers to analyze. If none, all pages are analyzed. Only applies for single document."
    },
    "data": {
      "items": {
        "$ref": "#/$defs/QuestionAnswer"
      },
      "type": "array",
      "title": "Data (Questions and Answers)",
      "description": "List of questions and answers for the analysis, along with confidence and citations."
    },
    "timestamp": {
      "type": "string",
      "title": "Timestamp",
      "description": "Timestamp of the analysis job."
    }
  },
  "type": "object",
  "required": [
    "analysisId",
    "jobId",
    "data"
  ],
  "$defs": {
    "Citation": {
      "properties": {
        "documentId": {
          "type": "string",
          "title": "Document ID",
          "description": "Unique identifier of the document where the citation is found."
        },
        "pages": {
          "items": {
            "type": "integer"
          },
          "type": "array",
          "title": "Pages",
          "description": "List of page numbers where the citation is found (zero-indexed)."
        }
      },
      "type": "object",
      "required": [
        "documentId",
        "pages"
      ],
      "title": "Citation"
    },
    "Confidence": {
      "type": "string",
      "enum": [
        "high",
        "medium",
        "low"
      ],
      "title": "Confidence"
    },
    "QuestionAnswer": {
      "properties": {
        "question": {
          "type": "string",
          "title": "Question",
          "description": "The question to be answered."
        },
        "answer": {
          "type": "string",
          "title": "Answer",
          "description": "The answer to the question."
        },
        "confidence": {
          "$ref": "#/$defs/Confidence",
          "description": "The confidence level of the answer."
        },
        "citations": {
          "items": {
            "$ref": "#/$defs/Citation"
          },
          "type": "array",
          "title": "Citations",
          "description": "List of citations for the answer."
        }
      },
      "type": "object",
      "required": [
        "question"
      ],
      "title": "QuestionAnswer"
    }
  }
}

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/docupanda-analysis"
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. See our Privacy Policy and Terms.

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