The Data Extraction API from Eden AI — 1 operation(s) for data extraction.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.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.curl "https://apis.io/api/v1/apis/eden-ai:eden-ai-data-extraction-api"curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a 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.
openapi: 3.2.0
info:
title: OCR Features Data Extraction API
version: '2.0'
description: Your project description
servers:
- url: https://api.edenai.run/v2
tags:
- name: Data Extraction
paths:
/ocr/data_extraction/:
post:
operationId: ocr_data_extraction_create
description: 'Available Providers
|Provider|Version|Price|Billing unit|
|----|-------|-----|------------|
|**amazon**|`boto3 (v1.15.18)`|0.05 (per 1 page)|1 page
|**base64**|`latest`|0.25 (per 1 page)|1 page'
summary: Data Extraction
tags:
- Data Extraction
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ocrdata_extractionDataExtractionRequest'
examples:
RequestExample:
value:
providers: amazon,base64
file_url: http://edenai-resource-example.png
summary: Request Example
multipart/form-data:
schema:
$ref: '#/components/schemas/ocrdata_extractionDataExtractionRequest'
examples:
RequestExample:
value:
providers: amazon,base64
file: /edenai/edenai/features/ocr/samples/data/invoice.png
summary: Request Example
required: true
security:
- FeatureApiAuth: []
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/ocrdata_extractionResponseModel'
examples:
ResponseExample:
value:
amazon:
fields:
- key: Classification
value: Post
bounding_box:
left: 0.6780509948730469
top: 0.8059332370758057
width: 0.02771328017115593
height: 0.008247338235378265
confidence_score: 1.0
cost: 0.0
base64:
fields:
- key: Company name
value: SC AUCHAN ROMANIA SA
bounding_box:
left: 83.0
top: 90.0
width: 137.0
height: 18.0
confidence_score: 0.99
- key: Company address
value: '1 BUC X 3,60
PATE DE'
bounding_box:
left: 10.0
top: 470.0
width: 164.0
height: 37.0
confidence_score: 1.0
- key: Phone number
value: 021-9141
bounding_box:
left: 193.0
top: 1373.0
width: 56.0
height: 15.0
confidence_score: 0.92
- key: Card number
value: 168,95
bounding_box:
left: 13.0
top: 831.0
width: 271.0
height: 21.0
confidence_score: 0.99
- key: Date
value: '2022-04-02'
bounding_box:
left: 11.0
top: 1087.0
width: 120.0
height: 17.0
confidence_score: 1.0
- key: Time
value: '12:29:23'
bounding_box:
left: 230.0
top: 1083.0
width: 59.0
height: 16.0
confidence_score: 1.0
- key: Receipt no
value: 1081-00024
bounding_box:
left: 15.0
top: 1486.0
width: 278.0
height: 18.0
confidence_score: 0.53
- key: Card type
value: Mastercard
bounding_box:
left: 217.0
top: 1026.0
width: 70.0
height: 14.0
confidence_score: 0.99
- key: Tax
value: '24.52'
bounding_box:
left: 14.0
top: 1297.0
width: 145.0
height: 17.0
confidence_score: 0.99
- key: Total
value: '168.95'
bounding_box:
left: 13.0
top: 784.0
width: 271.0
height: 33.0
confidence_score: 0.99
cost: 0.0
summary: Response Example
description: ''
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/BadRequest'
description: ''
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: ''
'403':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: ''
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/NotFoundResponse'
description: ''
components:
schemas:
BadRequest:
type: object
properties:
error:
$ref: '#/components/schemas/NestedBadRequest'
required:
- error
NestedBadRequest:
type: object
properties:
type:
type: string
message:
$ref: '#/components/schemas/FieldError'
required:
- message
- type
NestedError:
type: object
properties:
type:
type: string
message:
type: string
required:
- message
- type
ocrdata_extractionDataExtractionDataClass:
properties:
fields:
items:
$ref: '#/components/schemas/ItemDataExtraction'
title: Fields
type: array
original_response:
default: null
description: original response sent by the provider, hidden by default, show it by passing the `show_original_response` field to `true` in your request
title: Original Response
status:
allOf:
- $ref: '#/components/schemas/StatusEnum'
title: Status
required:
- status
title: ocrdata_extractionDataExtractionDataClass
type: object
StatusEnum:
enum:
- sucess
- fail
type: string
ItemDataExtraction:
properties:
key:
title: Key
type: string
value:
title: Value
bounding_box:
$ref: '#/components/schemas/BoundingBox'
confidence_score:
maximum: 1
minimum: 0
title: Confidence Score
type: integer
required:
- key
- value
- bounding_box
- confidence_score
title: ItemDataExtraction
type: object
NotFoundResponse:
type: object
properties:
details:
type: string
default: Not Found
FieldError:
type: object
properties:
<parameter_name>:
type: array
items:
type: string
required:
- <parameter_name>
ocrdata_extractionResponseModel:
properties:
base64:
$ref: '#/components/schemas/ocrdata_extractionDataExtractionDataClass'
default: null
amazon:
$ref: '#/components/schemas/ocrdata_extractionDataExtractionDataClass'
default: null
title: ocrdata_extractionResponseModel
type: object
Error:
type: object
properties:
error:
$ref: '#/components/schemas/NestedError'
required:
- error
ocrdata_extractionDataExtractionRequest:
type: object
properties:
settings:
type: string
default: {}
description: "A dictionnary or a json object to specify specific models to use for some providers. <br> It can be in the following format: {\"google\" : \"google_model\", \"ibm\": \"ibm_model\"...}.\n "
providers:
type: array
items:
type: string
minLength: 1
description: 'It can be one (ex: **''amazon''** or **''google''**) or multiple provider(s) (ex: **''amazon,microsoft,google''**) that the data will be redirected to in order to get the processed results.<br> Providers can also be invoked with specific models (ex: providers: **''amazon/model1, amazon/model2, google/model3''**)'
fallback_providers:
type: array
items:
type: string
default: []
description: "Providers in this list will be used as fallback if the call to provider in `providers` parameter fails.\n To use this feature, you must input **only one** provider in the `providers` parameter. but you can put up to 5 fallbacks.\n\nThey will be tried in the same order they are input, and it will stop to the first provider who doesn't fail.\n\n\n*Doesn't work with async subfeatures.*\n "
maxItems: 5
response_as_dict:
type: boolean
default: true
description: "Optional : When set to **true** (default), the response is an object of responses with providers names as keys : <br> \n ``` {\"google\" : { \"status\": \"success\", ... }, } ``` <br>\n When set to **false** the response structure is a list of response objects : <br> \n ``` [{\"status\": \"success\", \"provider\": \"google\" ... }, ] ```. <br>\n "
attributes_as_list:
type: boolean
default: false
description: "Optional : When set to **false** (default) the structure of the extracted items is list of objects having different attributes : <br>\n ```{'items': [{\"attribute_1\": \"x1\",\"attribute_2\": \"y2\"}, ... ]}``` <br>\n When it is set to **true**, the response contains an object with each attribute as a list : <br>\n ```{ \"attribute_1\": [\"x1\",\"x2\", ...], \"attribute_2\": [y1, y2, ...]}``` "
show_base_64:
type: boolean
default: true
show_original_response:
type: boolean
default: false
description: "Optional : Shows the original response of the provider.<br>\n When set to **true**, a new attribute *original_response* will appear in the response object."
file:
type: string
format: binary
description: 'File to analyse in binary format to be used with *content-type*: **multipart/form-data** <br> **Does not work with application/json !**'
file_url:
type:
- string
- 'null'
format: uri
description: 'File **URL** to analyse to be used with with *content-type*: **application/json**.'
file_password:
type:
- string
- 'null'
description: If your PDF file has a password, you can pass it here!
maxLength: 200
convert_to_pdf:
type:
- boolean
- 'null'
default: false
description: Boolean value to specify weather to convert the doc/docx files to pdf format to be accepted by a majority of the providers
required:
- providers
BoundingBox:
description: "Bounding box of a word in the image\n\nAttributes:\n left (float): Left coordinate of the bounding box\n top (float): Top coordinate of the bounding box\n width (float): Width of the bounding box\n height (float): Height of the bounding box\n text (str): Text detected in the bounding box\n\nConstructor:\n from_json (classmethod): Create a new instance of BoundingBox from a JSON object\n from_normalized_vertices (classmethod): Create a new instance of BoundingBox from normalized vertices\n unknown (classmethod): Return a invalid bouding_box with all field filled with `-1`"
properties:
left:
description: Left coordinate of the bounding box
title: Left
type: integer
top:
description: Top coordinate of the bounding box
title: Top
type: integer
width:
description: Width of the bounding box
title: Width
type: integer
height:
description: Height of the bounding box
title: Height
type: integer
required:
- left
- top
- width
- height
title: BoundingBox
type: object
securitySchemes:
FeatureApiAuth:
type: http
scheme: bearer
bearerFormat: JWT