{
  "openapi": "3.0.1",
  "info": {
    "title": "Docling Document Converter: PDF & Office to Markdown",
    "description": "Convert PDFs (including scans), Word, PowerPoint, Excel, HTML and images into clean, LLM-ready Markdown or structured Docling JSON with tables, headings, reading order, OCR and optional RAG chunks with page references.",
    "version": "0.1",
    "x-build-id": "mV3OcoPkBpSBNR9TG"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/tallowlanelabs~docling-document-converter/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-tallowlanelabs-docling-document-converter",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/tallowlanelabs~docling-document-converter/runs": {
      "post": {
        "operationId": "runs-sync-tallowlanelabs-docling-document-converter",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/tallowlanelabs~docling-document-converter/run-sync": {
      "post": {
        "operationId": "run-sync-tallowlanelabs-docling-document-converter",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "files": {
            "title": "Upload documents",
            "type": "array",
            "description": "Upload PDF, DOCX, PPTX, XLSX, HTML, Markdown, CSV or image files (PNG, JPG, TIFF). They are stored in a key-value store of your choice and read by the Actor. By default uploaded files are deleted after the run (see 'Delete uploaded files after run').",
            "items": {
              "type": "string"
            }
          },
          "urls": {
            "title": "Document URLs",
            "type": "array",
            "description": "Direct links to documents (PDF, DOCX, PPTX, XLSX, HTML, MD, CSV, images). Each URL is downloaded once, converted, and the downloaded copy is discarded.",
            "items": {
              "type": "object",
              "required": [
                "url"
              ],
              "properties": {
                "url": {
                  "type": "string",
                  "title": "URL of a web page",
                  "format": "uri"
                }
              }
            }
          },
          "outputFormat": {
            "title": "Output format",
            "enum": [
              "markdown",
              "json",
              "both"
            ],
            "type": "string",
            "description": "Markdown is best for LLMs and RAG. Docling JSON is the full lossless document model (layout, provenance, bounding boxes, table cells).",
            "default": "markdown"
          },
          "ocrMode": {
            "title": "OCR",
            "enum": [
              "auto",
              "force",
              "off"
            ],
            "type": "string",
            "description": "Auto: OCR only regions with no text layer (scans, embedded images) – billed as OCR pages only where OCR produced most of the text. Force: OCR every page (use for scans with a bad text layer; every page is billed as an OCR page). Off: text layer only, cheapest and fastest; scanned pages come back empty.",
            "default": "auto"
          },
          "tableMode": {
            "title": "Table structure",
            "enum": [
              "fast",
              "accurate",
              "off"
            ],
            "type": "string",
            "description": "Fast (default): TableFormer fast model, good for most tables; billed at the normal page price ($0.003/page). Accurate (opt-in): TableFormer accurate model for dense tables with merged cells (e.g. financial statements); about 1.5-2x slower and billed $0.007 per PDF/image page instead of $0.003 (OCR pages stay $0.01, no extra). Off: tables come out as plain text. Applies to PDFs and images; Office/HTML tables are read natively and always billed at the normal price.",
            "default": "fast"
          },
          "skipOcrOnFigures": {
            "title": "Skip OCR inside figures",
            "type": "boolean",
            "description": "OCR mode Auto only: on digital pages (pages with a text layer), don't OCR regions detected as pictures/charts. Faster, and figure-internal labels are not part of the Markdown anyway; turn off if you need chart/diagram labels in the JSON output. Scanned pages are always OCR'd in full. No effect on price.",
            "default": true
          },
          "maxPagesPerDocument": {
            "title": "Max pages per document",
            "minimum": 1,
            "maximum": 5000,
            "type": "integer",
            "description": "Only the first N pages of each PDF are converted (and billed). The output marks truncated documents.",
            "default": 200
          },
          "maxFileSizeMb": {
            "title": "Max file size",
            "minimum": 1,
            "maximum": 500,
            "type": "integer",
            "description": "Documents larger than this are skipped (not billed).",
            "default": 100
          },
          "documentTimeoutSecs": {
            "title": "Per-document timeout",
            "minimum": 30,
            "maximum": 3600,
            "type": "integer",
            "description": "Stop converting a document after this many seconds; pages finished so far are returned as a partial result.",
            "default": 600
          },
          "includeImagePlaceholders": {
            "title": "Image placeholders in Markdown",
            "type": "boolean",
            "description": "Insert <!-- image --> where pictures appear, so LLMs know a figure was there.",
            "default": true
          },
          "chunking": {
            "title": "Create RAG chunks",
            "type": "boolean",
            "description": "Split each document into token-sized chunks (Docling HybridChunker: respects headings, tables and lists) with heading path and page numbers. Billed $0.001 per started batch of 100 chunks, counted per document.",
            "default": false
          },
          "chunkMaxTokens": {
            "title": "Max tokens per chunk",
            "minimum": 64,
            "maximum": 8192,
            "type": "integer",
            "description": "Measured with the all-MiniLM-L6-v2 tokenizer (close to most embedding models; leave headroom for OpenAI tokenizers).",
            "default": 512
          },
          "chunksAsDatasetItems": {
            "title": "Output chunks as separate dataset rows",
            "type": "boolean",
            "description": "Also push one dataset item per chunk (recordType = 'chunk') – handy for feeding vector databases directly via integrations.",
            "default": false
          },
          "inlineContentMaxKb": {
            "title": "Max inline content size",
            "minimum": 0,
            "maximum": 8192,
            "type": "integer",
            "description": "Markdown/JSON/chunks up to this size are put directly in the dataset item; bigger outputs are saved to the key-value store and linked (…Url fields).",
            "default": 2048
          },
          "outputKeyValueStoreName": {
            "title": "Key-value store for large outputs",
            "type": "string",
            "description": "Optional named key-value store for outputs too big to inline. Default: the run's own store (subject to your retention settings)."
          },
          "deleteUploadedFilesAfterRun": {
            "title": "Delete uploaded files after run",
            "type": "boolean",
            "description": "When on (default), files you uploaded through 'Upload documents' are deleted from their key-value store after conversion, so your source documents are not kept. URL downloads are never stored.",
            "default": true
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}