{
"openapi": "3.1.0",
"x-stoplight": {
"id": "6g738bjcu8e72"
},
"info": {
"title": "JSON response",
"version": "",
"summary": "",
"description": "",
"contact": {
"name": "Lazarus IT",
"url": "https://lazarus-ai.atlassian.net/servicedesk/customer/portal/8",
"email": "support@lazarusai.com"
},
"license": {
"name": "Get Lazarus",
"url": "https://emvnha23ura.typeform.com/lazarus-rikai?typeform-source=dashboard.lazarusai.com"
},
"termsOfService": "https://www.lazarusai.com/legal"
},
"paths": {
"/ocr": {
"post": {
"summary": "JSON response",
"description": "Make a request to OCR and receive JSON response data.\n\n#### File upload options\nWe support requests with Content-Type `application/json` or `multipart/form-data`. Note that `application/json` requests are preferred as `multipart/form-data` requests do not support all flags and fields.\n- `[application/json]` **inputURL** link to file\n- `[application/json]` **base64** base64 encoded file data\n- `[multipart/form-data]` **file** upload local file from browser\n - [PDF Form Example](https://documentation-resources.s3.amazonaws.com/JR_Form.pdf)\n - [JSON Response for Example](https://docs.google.com/document/d/15fSuTmEWKtidAFbaP3m9uMfX4GziJqZnNP385Sel5rM/edit?usp=sharing)\n<!-- Supports PDF, PNG, TIF, TIFF, JPE, WebP, and TXT. -->",
"operationId": "post_ocr",
"parameters": [
{
"$ref": "#/components/parameters/apiVersion"
},
{
"$ref": "#/components/parameters/orgId"
},
{
"$ref": "#/components/parameters/authKey"
},
{
"$ref": "#/components/parameters/subOrgId"
},
{
"$ref": "#/components/parameters/version"
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"anyOf": [
{
"$ref": "#/components/schemas/URLRequest"
},
{
"$ref": "#/components/schemas/Base64Request"
}
],
"title": "Request Body"
}
},
"multipart/form-data": {
"schema": {
"$ref": "#/components/schemas/FileRequest"
}
}
}
},
"responses": {
"200": {
"description": "Successful Response.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OCRResultsResponseBody"
}
}
}
},
"400": {
"$ref": "#/components/responses/400"
},
"403": {
"$ref": "#/components/responses/403"
},
"404": {
"$ref": "#/components/responses/404"
},
"500": {
"$ref": "#/components/responses/500"
},
"502": {
"$ref": "#/components/responses/502"
}
},
"x-stoplight": {
"id": "qau5bef64kxhm"
}
}
},
"/ocr/zip": {
"post": {
"summary": "ZIP file response",
"description": "Make a request to OCR and receive response data in a ZIP file.\n\n#### File upload options\nWe only support requests with Content-Type `application/json` at this endpoint.\n- `[application/json]` **inputURL** link to file\n- `[application/json]` **base64** base64 encoded file data\n\n#### Response zip file contents\n| File | Description |\n| ----- | ------- |\n| .csv | CSV containing a breakdown of the itemization |\n| .json | JSON file containing the entire JSON response |\n| .txt | TXT file containing the entire JSON response |\n| file | The original uploaded file |\n\nThe default name for the file is an epoch timestamp if `fileId` field is not included in the request.",
"operationId": "post_zip_ocr",
"parameters": [
{
"$ref": "#/components/parameters/apiVersion"
},
{
"$ref": "#/components/parameters/orgId"
},
{
"$ref": "#/components/parameters/authKey"
},
{
"$ref": "#/components/parameters/async"
},
{
"$ref": "#/components/parameters/subOrgId"
},
{
"$ref": "#/components/parameters/version"
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"anyOf": [
{
"$ref": "#/components/schemas/ZipURLRequest"
},
{
"$ref": "#/components/schemas/ZipBase64Request"
}
],
"title": "Request Body"
}
}
}
},
"responses": {
"200": {
"description": "Successful Response.",
"content": {
"application/zip": {
"schema": {}
}
}
},
"400": {
"$ref": "#/components/responses/400"
},
"403": {
"$ref": "#/components/responses/403"
},
"404": {
"$ref": "#/components/responses/404"
},
"500": {
"$ref": "#/components/responses/500"
},
"502": {
"$ref": "#/components/responses/502"
}
},
"x-stoplight": {
"id": "qgl3f7wc95ql2"
}
}
}
},
"components": {
"schemas": {
"Base64Request": {
"type": "object",
"title": "Base64Request",
"description": "/forms/ocr request body with base64 file upload",
"x-stoplight": {
"id": "gr8stvcse2nmi"
},
"required": [
"base64"
],
"properties": {
"base64": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "string"
}
],
"description": "Base64 encoded string for the file to extract data from. If it is an array, the base64 strings will be appended into one PDF then ran through the model.",
"forceRequire": true
},
"fileId": {
"type": "string",
"description": "Custom ID for document. If not present, will default to a random UUID.",
"default": "UUID",
"examples": ["file1.pdf"]
},
"forceBase64": {
"type": "boolean",
"title": "forceBase64",
"description": "Setting this parameter to true converts files to Base64 format before sending them on to the model.",
"default": false
},
"metadata": {
"type": "object",
"description": "Custom JSON to be included in the returned response."
},
"webhook": {
"type": "string",
"description": "Webhook URL to send status updates and JSON response to.\n"
},
"webhookSendFull": {
"type": "boolean",
"description": "Send whole JSON response to webhook URL upon request completion. Set to `false` to only send request status.\n",
"default": true
},
"version": {
"type": "integer",
"description": "OCR model version (1 or 2)",
"default": 2
}
}
},
"ErrorMessage": {
"properties": {
"status": {
"allOf": [
{
"$ref": "#/components/schemas/Status"
}
],
"title": "status",
"description": "Status of the request."
},
"message": {
"type": "string",
"description": "Error message."
}
},
"type": "object",
"required": [
"status"
],
"title": "ErrorMessage",
"description": "Response when an error occurs.",
"x-stoplight": {
"id": "84gjthmpbah9b"
}
},
"FileRequest": {
"type": "object",
"title": "FileRequest",
"description": "/forms/ocr request body with local file upload",
"x-stoplight": {
"id": "0klmw49zwgfl7"
},
"required": [
"file"
],
"properties": {
"file": {
"type": "string",
"format": "binary",
"title": "file",
"description": "File to upload: Must be a PDF, JPEG, PNG, or TIFF.",
"forceRequire": true
},
"fileId": {
"type": "string",
"description": "Custom ID for document. If not present, will default to a random UUID.",
"default": "UUID",
"examples": ["file1.pdf"]
},
"forceBase64": {
"type": "boolean",
"title": "forceBase64",
"description": "Setting this parameter to true converts files to Base64 format before sending them on to the model.",
"default": false
},
"webhook": {
"type": "string",
"description": "Webhook URL to send status updates and JSON response to.\n"
},
"webhookSendFull": {
"type": "boolean",
"description": "Send whole JSON response to webhook URL upon request completion. Set to `false` to only send request status.\n",
"default": true
},
"version": {
"type": "integer",
"description": "OCR model version (1 or 2)",
"default": 2
}
}
},
"LineV2": {
"properties": {
"content": {
"type": "string",
"description": "Content of the field as a string."
},
"polygon": {
"items": {
"type": "number"
},
"type": "array",
"description": "Bounding box coordinates of content."
},
"spans": {
"items": {
"$ref": "#/components/schemas/SpanV2"
},
"type": "array",
"description": "Span where data can be found in the raw text."
}
},
"type": "object",
"title": "LineV2",
"x-stoplight": {
"id": "7oq3ehiqzk3gk"
}
},
"OCRResultsResponseBody": {
"oneOf": [
{
"$ref": "#/components/schemas/OCRResultsResponseBodyV2"
}
],
"title": "OCRResultsResponseBody",
"description": "/ocr response",
"discriminator": {
"propertyName": "ocrVersion",
"mapping": {
"2": "#/components/schemas/OCRResultsResponseBodyV2"
}
},
"x-stoplight": {
"id": "ywe7epsrq2xzm"
}
},
"OCRResultsResponseBodyV2": {
"properties": {
"status": {
"allOf": [
{
"$ref": "#/components/schemas/Status"
}
],
"description": "Status of the request."
},
"documentId": {
"type": "string",
"description": "ID for document request or filename if specified."
},
"modelType": {
"type": "string",
"description": "Type of base/extraction model used, OCR or Forms."
},
"id": {
"type": "string",
"description": "Request ID."
},
"requestDateTime": {
"type": "string",
"description": "Date and time request was made."
},
"startTime": {
"type": "integer",
"description": "Request start time."
},
"endTime": {
"type": "integer",
"description": "Request end time."
},
"pages": {
"type": "integer",
"description": "Number of pages in the document."
},
"ocrResults": {
"allOf": [
{
"$ref": "#/components/schemas/OCRResultsV2"
}
],
"description": "Model results."
},
"resultUrl": {
"type": "string",
"description": "URL to the result of the OCR process."
},
"metadata": {
"type": "object",
"description": "Custom JSON to be included in the returned response.",
"forceType": "object"
}
},
"type": "object",
"required": [
"ocrVersion"
],
"title": "OCRResultsResponseBodyV2",
"x-stoplight": {
"id": "753ptcmntgr2g"
}
},
"OCRResultsV2": {
"properties": {
"version": {
"type": "string",
"description": "OCR model version (1 or 2)"
},
"modelVersion": {
"type": "string",
"description": "OCR model version date."
},
"readResults": {
"items": {
"$ref": "#/components/schemas/ReadResultV2"
},
"type": "array",
"description": "Read results for each page in the document."
},
"readStyles": {
"items": {
"$ref": "#/components/schemas/ReadStyleV2"
},
"type": "array",
"description": "Styled objects found in the document."
},
"rawText": {
"type": "string",
"description": "All the extracted text from the document."
}
},
"type": "object",
"title": "OCRResultsV2",
"x-stoplight": {
"id": "ms96uzb530zli"
}
},
"ReadResultV2": {
"properties": {
"pageNumber": {
"type": "integer",
"description": "Page number."
},
"angle": {
"type": "number",
"description": "Slant of text read."
},
"width": {
"type": "number",
"description": "Document width."
},
"height": {
"type": "number",
"description": "Document height."
},
"unit": {
"type": "string",
"description": "Unit of measurement used for height and width."
},
"lines": {
"items": {
"$ref": "#/components/schemas/LineV2"
},
"type": "array",
"description": "Lines of text on the page."
},
"words": {
"items": {
"$ref": "#/components/schemas/WordV2"
},
"type": "array",
"description": "Words on the page."
},
"spans": {
"items": {
"$ref": "#/components/schemas/SpanV2"
},
"type": "array",
"description": "Span where data can be found in the raw text."
},
"kind": {
"type": "string",
"description": "Type of document."
}
},
"type": "object",
"title": "ReadResultV2",
"x-stoplight": {
"id": "b45c7d6sadgo5"
}
},
"ReadStyleV2": {
"properties": {
"confidence": {
"type": "number",
"description": "Model confidence in detection and accuracy."
},
"spans": {
"items": {
"$ref": "#/components/schemas/SpanV2"
},
"type": "array",
"description": "Span where data can be found in the raw text."
},
"isHandwritten": {
"type": "boolean",
"description": "Whether or not text was handwritten.",
"default": false
}
},
"type": "object",
"title": "ReadStyleV2",
"x-stoplight": {
"id": "t2ze8fr0ydm1x"
}
},
"SpanV2": {
"properties": {
"offset": {
"type": "integer",
"description": "Offset of the data from the edge of the document."
},
"length": {
"type": "integer",
"description": "Length of area of the data."
}
},
"type": "object",
"title": "SpanV2",
"x-stoplight": {
"id": "woxp3w8uu4phc"
}
},
"Status": {
"type": "string",
"enum": [
"SUCCESS",
"RUNNING",
"AUTH_FAILURE",
"FAILURE"
],
"title": "Status",
"x-stoplight": {
"id": "m87wtkj3i4wln"
}
},
"URLRequest": {
"properties": {
"inputUrl": {
"type": "string",
"title": "inputURL",
"description": "URL for the file to extract data from: Must be a PDF, JPEG, PNG, or TIFF.",
"forceRequire": true
},
"fileId": {
"type": "string",
"title": "fileId",
"description": "Custom ID for document. If not present, will default to a random UUID.",
"default": "UUID",
"examples": ["file1.pdf"]
},
"forceBase64": {
"type": "boolean",
"title": "forceBase64",
"description": "Setting this parameter to true converts files to Base64 format before sending them on to the model.",
"default": false
},
"metadata": {
"type": "object",
"title": "metadata",
"description": "Custom JSON to be included in the returned response."
},
"webhook": {
"type": "string",
"description": "Webhook to ping after API runs."
},
"webhookSendFull": {
"type": "boolean",
"description": "Set to true to send all response data to webhook upon request completion, otherwise only send request status.",
"default": true
},
"version": {
"type": "integer",
"description": "OCR model version (1 or 2)",
"default": 2
}
},
"type": "object",
"title": "URLRequest",
"description": "/forms/ocr request body with URL file upload",
"required": [
"inputUrl"
],
"x-stoplight": {
"id": "48uapeo61xnk9"
}
},
"WordV2": {
"properties": {
"content": {
"type": "string",
"description": "Content of the field as a string."
},
"polygon": {
"items": {
"type": "number"
},
"type": "array",
"description": "Bounding box coordinates of content."
},
"confidence": {
"type": "number",
"description": "Model confidence in detection and accuracy."
},
"span": {
"allOf": [
{
"$ref": "#/components/schemas/SpanV2"
}
],
"description": "Span where data can be found in the raw text."
}
},
"type": "object",
"title": "WordV2",
"x-stoplight": {
"id": "onnnafgjoyfge"
}
},
"ZipBase64Request": {
"properties": {
"base64": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "string"
}
],
"description": "Base64 encoded string for the file to extract data from. If it is an array, the base64 strings will be appended into one PDF then ran through the model.",
"forceRequire": true
},
"statusId": {
"type": "string",
"description": "List of document IDs for each file uploaded."
},
"outputURL": {
"type": "string",
"pattern": " https?://(?:www\\\\.)?[a-zA-Z0-9./]+",
"description": "URL where resulting zip file should be sent. Must be open to PUT requests. Required if submitting an async request."
},
"outputURLHeaders": {
"type": "object",
"description": "Request headers to include in the PUT request to the output URL.",
"forceType": "object"
},
"fileId": {
"type": "string",
"description": "Custom ID for document."
},
"forceBase64": {
"type": "boolean",
"description": "Setting this parameter to true converts files to Base64 format before sending them on to the model.",
"default": false
},
"metadata": {
"type": "object",
"description": "Custom JSON to be included in the returned response.",
"forceType": "object"
},
"webhook": {
"type": "string",
"pattern": " https?://(?:www\\\\.)?[a-zA-Z0-9./]+",
"description": "Webhook to ping after API runs."
},
"webhookSendFull": {
"type": "boolean",
"description": "Set to true to send all response data to webhook upon request completion, otherwise only send request status.",
"default": true
},
"version": {
"type": "integer",
"description": "OCR model version (1 or 2)",
"default": 2
}
},
"type": "object",
"title": "ZipBase64Request",
"required": [
"base64",
"webhook"
],
"x-stoplight": {
"id": "oc9su9i22oq6c"
}
},
"ZipURLRequest": {
"properties": {
"inputURL": {
"type": "string",
"pattern": " https?://(?:www\\\\.)?[a-zA-Z0-9./]+",
"description": "URL for the file to extract data from: Must be a PDF, JPEG, PNG, TIFF, or TXT.",
"forceRequire": true
},
"statusId": {
"type": "string",
"description": "List of document IDs for each file uploaded."
},
"outputURL": {
"type": "string",
"pattern": " https?://(?:www\\\\.)?[a-zA-Z0-9./]+",
"description": "URL where resulting zip file should be sent. Must be open to PUT requests. Required if submitting an async request."
},
"outputURLHeaders": {
"type": "object",
"description": "Request headers to include in the PUT request to the output URL.",
"forceType": "object"
},
"fileId": {
"type": "string",
"description": "Custom ID for document."
},
"forceBase64": {
"type": "boolean",
"description": "Setting this parameter to true converts files to Base64 format before sending them on to the model.",
"default": false
},
"metadata": {
"type": "object",
"description": "Custom JSON to be included in the returned response.",
"forceType": "object"
},
"webhook": {
"type": "string",
"pattern": " https?://(?:www\\\\.)?[a-zA-Z0-9./]+",
"description": "Webhook to ping after API runs."
},
"webhookSendFull": {
"type": "boolean",
"description": "Set to true to send all response data to webhook upon request completion, otherwise only send request status.",
"default": true
},
"version": {
"type": "integer",
"description": "OCR model version (1 or 2).",
"default": 2
}
},
"type": "object",
"title": "ZipURLRequest",
"required": [
"inputURL",
"webhook"
],
"x-stoplight": {
"id": "rn1n7chd4gah9"
}
}
},
"parameters": {
"apiVersion": {
"name": "apiVersion",
"in": "header",
"required": true,
"schema": {
"type": "string",
"minLength": 1,
"pattern": "YYYY-MM-DD",
"title": "apiVersion",
"description": "API Version",
"default": "2025-02-27"
},
"description": "API Version"
},
"orgId": {
"name": "orgId",
"in": "header",
"required": true,
"schema": {
"type": "string",
"minLength": 1,
"pattern": "^[a-zA-Z0-9\\-_]+$",
"title": "orgId",
"description": "Organization ID"
},
"description": "Organization ID"
},
"authKey": {
"name": "authKey",
"in": "header",
"required": true,
"schema": {
"type": "string",
"minLength": 1,
"pattern": "^[a-zA-Z0-9\\-_]+$",
"title": "authKey",
"description": "Authentication key"
},
"description": "Authentication key"
},
"subOrgId": {
"name": "subOrgId",
"in": "header",
"required": false,
"schema": {
"type": "string",
"minLength": 1,
"pattern": "^[a-zA-Z0-9\\-_]+$",
"title": "subOrgId",
"description": "Sub-organization ID"
},
"description": "Sub-organization ID"
},
"version": {
"name": "version",
"in": "header",
"required": false,
"schema": {
"type": "integer",
"minLength": 1,
"title": "version",
"description": "API version",
"default": 2
},
"description": "API version"
},
"async": {
"name": "async",
"in": "query",
"required": false,
"schema": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Runs request asynchronously"
},
"description": "Runs request asynchronously"
}
},
"responses": {
"400": {
"description": "Bad request or failure to read. Request was invalid or we could not process your data.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorMessage"
},
"examples": {
"Missing required field": {
"value": {
"status": "FAILURE",
"message": "Request body is missing required field(s): question"
}
}
}
}
}
},
"403": {
"description": "Unauthorized attempt. There was an issue with your credentials, model permissions or billing.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorMessage"
},
"examples": {
"Invalid credentials": {
"value": {
"status": "AUTH_FAILURE",
"message": "Invalid authentication"
}
}
}
}
}
},
"404": {
"description": "Not found error. When a request references an invalid endpoint or resource.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorMessage"
},
"examples": {
"Custom model not found": {
"value": {
"status": "FAILURE",
"message": "Model id 'abc' is not valid."
}
}
}
}
}
},
"500": {
"description": "Model processing failed. Extraction model or LLM could not process your request.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorMessage"
},
"examples": {
"OCR failed": {
"value": {
"status": "FAILURE",
"message": "Error during request to OCR microservice."
}
},
"LLM failed": {
"value": {
"status": "FAILURE",
"message": "We made three attempts to process the model with no success."
}
}
}
}
}
},
"502": {
"description": "Could not connect to model.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorMessage"
},
"examples": {
"Custom model not found": {
"value": {
"status": "FAILURE",
"message": "Request to the model failed."
}
}
}
}
}
}
}
},
"servers": [
{
"url": "https://api.lazarusai.com/api/forms",
"description": ""
}
]
}