Eden AI Ocr API

openapi: 3.2.0
info:
  title: Eden Ai Ocr API
  version: '2.0'
  description: 'Operations tagged Ocr across 2 of this provider''s published API definitions: eden-ai-ocr-features-openapi.json, eden-ai-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://api.edenai.run/v2
tags:
- name: OCR
paths:
  /ocr/ocr/:
    post:
      operationId: ocr_ocr_create
      description: 'Available Providers


        |Provider|Version|Price|Billing unit|

        |----|-------|-----|------------|

        |**amazon**|`boto3 (v1.15.18)`|1.5 (per 1000 page)|1 page

        |**google**|`v1`|1.5 (per 1000 page)|1 page

        |**microsoft**|`v3.2`|1.0 (per 1000 page)|1 page

        |**sentisight**|`v3.3.1`|0.75 (per 1000 file)|1 file

        |**api4ai**|`v1.0.0`|3.0 (per 1000 request)|1 request

        |**mistral**|`v1`|4.0 (per 1000 page)|1 page


        Supported Languages


        |Name|Value|

        |----|-----|

        |**Abaza**|`abq`|

        |**Adyghe**|`ady`|

        |**Afrikaans**|`af`|

        |**Albanian**|`sq`|

        |**Angika**|`anp`|

        |**Arabic**|`ar`|

        |**Assamese**|`as`|

        |**Asturian**|`ast`|

        |**Avaric**|`av`|

        |**Awadhi**|`awa`|

        |**Azerbaijani**|`az`|

        |**Bagheli**|`bfy`|

        |**Basque**|`eu`|

        |**Belarusian**|`be`|

        |**Bengali**|`bn`|

        |**Bhojpuri**|`bho`|

        |**Bihari languages**|`bh`|

        |**Bislama**|`bi`|

        |**Bodo (India)**|`brx`|

        |**Bosnian**|`bs`|

        |**Braj**|`bra`|

        |**Breton**|`br`|

        |**Bulgarian**|`bg`|

        |**Bundeli**|`bns`|

        |**Buriat**|`bua`|

        |**Camling**|`rab`|

        |**Catalan**|`ca`|

        |**Cebuano**|`ceb`|

        |**Chamorro**|`ch`|

        |**Chechen**|`ce`|

        |**Chhattisgarhi**|`hne`|

        |**Chinese**|`zh`|

        |**Cornish**|`kw`|

        |**Corsican**|`co`|

        |**Crimean Tatar**|`crh`|

        |**Croatian**|`hr`|

        |**Czech**|`cs`|

        |**Danish**|`da`|

        |**Dargwa**|`dar`|

        |**Dari**|`prs`|

        |**Dhimal**|`dhi`|

        |**Dogri (macrolanguage)**|`doi`|

        |**Dutch**|`nl`|

        |**English**|`en`|

        |**Erzya**|`myv`|

        |**Estonian**|`et`|

        |**Faroese**|`fo`|

        |**Fijian**|`fj`|

        |**Filipino**|`fil`|

        |**Finnish**|`fi`|

        |**French**|`fr`|

        |**Friulian**|`fur`|

        |**Gagauz**|`gag`|

        |**Galician**|`gl`|

        |**German**|`de`|

        |**Gilbertese**|`gil`|

        |**Goan Konkani**|`gom`|

        |**Gondi**|`gon`|

        |**Gurung**|`gvr`|

        |**Haitian**|`ht`|

        |**Halbi**|`hlb`|

        |**Hani**|`hni`|

        |**Haryanvi**|`bgc`|

        |**Hawaiian**|`haw`|

        |**Hindi**|`hi`|

        |**Hmong Daw**|`mww`|

        |**Ho**|`hoc`|

        |**Hungarian**|`hu`|

        |**Icelandic**|`is`|

        |**Inari Sami**|`smn`|

        |**Indonesian**|`id`|

        |**Ingush**|`inh`|

        |**Interlingua (International Auxiliary Language Association)**|`ia`|

        |**Inuktitut**|`iu`|

        |**Irish**|`ga`|

        |**Italian**|`it`|

        |**Japanese**|`ja`|

        |**Jaunsari**|`jns`|

        |**Javanese**|`jv`|

        |**K''iche''**|`quc`|

        |**Kabardian**|`kbd`|

        |**Kabuverdianu**|`kea`|

        |**Kachin**|`kac`|

        |**Kalaallisut**|`kl`|

        |**Kangri**|`xnr`|

        |**Kara-Kalpak**|`kaa`|

        |**Karachay-Balkar**|`krc`|

        |**Kashubian**|`csb`|

        |**Kazakh**|`kk`|

        |**Khaling**|`klr`|

        |**Khasi**|`kha`|

        |**Kirghiz**|`ky`|

        |**Korean**|`ko`|

        |**Korku**|`kfq`|

        |**Koryak**|`kpy`|

        |**Kosraean**|`kos`|

        |**Kumarbhag Paharia**|`kmj`|

        |**Kumyk**|`kum`|

        |**Kurdish**|`ku`|

        |**Kurukh**|`kru`|

        |**Kölsch**|`ksh`|

        |**Lak**|`lbe`|

        |**Lakota**|`lkt`|

        |**Latin**|`la`|

        |**Latvian**|`lv`|

        |**Lezghian**|`lez`|

        |**Lithuanian**|`lt`|

        |**Lower Sorbian**|`dsb`|

        |**Lule Sami**|`smj`|

        |**Luxembourgish**|`lb`|

        |**Mahasu Pahari**|`bfz`|

        |**Maithili**|`mai`|

        |**Malay (macrolanguage)**|`ms`|

        |**Maltese**|`mt`|

        |**Manx**|`gv`|

        |**Maori**|`mi`|

        |**Marathi**|`mr`|

        |**Marshallese**|`mh`|

        |**Mongolian**|`mn`|

        |**Montenegrin**|`cnr`|

        |**Neapolitan**|`nap`|

        |**Nepali (macrolanguage)**|`ne`|

        |**Newari**|`new`|

        |**Niuean**|`niu`|

        |**Nogai**|`nog`|

        |**Northern Sami**|`se`|

        |**Norwegian**|`no`|

        |**Occitan (post 1500)**|`oc`|

        |**Old English (ca.'
      summary: OCR
      tags:
      - OCR
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ocrocrOcrRequest'
            examples:
              RequestExample:
                value:
                  providers: google,mistral,sentisight,microsoft,api4ai,amazon
                  language: en
                  file_url: http://edenai-resource-example.png
                summary: Request Example
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/ocrocrOcrRequest'
            examples:
              RequestExample:
                value:
                  providers: google,mistral,sentisight,microsoft,api4ai,amazon
                  file: /edenai/edenai/features/ocr/samples/data/ocr_en.png
                  language: en
                summary: Request Example
        required: true
      security:
      - FeatureApiAuth: []
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ocrocrResponseModel'
              examples:
                ResponseExample:
                  value:
                    google:
                      text: 'I 福州科技馆 福州科技馆空调线路改造项目工程 施工招标公告 招标项目福州科技馆空调线路改造项目工程已批准建设, 招标人为福州科技馆,建设资金来源自筹。项目已具备 招标条件,现对该项目的施工进行公开招标。 1.项目概况与招标范围 建设地点: 福州市仓山区橘园洲桥下公园内 工程招标控 制价: 29135 元;计划工期: 15日历天质量要求:合 按招标范围:详见工程量清单为准, 2. 投标人资格要求 2.1 投标人须具备人员,设备,资金等方面具有相应的设 计经验及施工能力。 2. 2 本次招标不接受联合体投标。 3. 投标报名、开标时间 投标报名截止时间至2018年12月4日12时00分,开标'
                      bounding_boxes:
                      - text: I
                        left: 0.5178571428571429
                        top: -0.004132231404958678
                        width: 0.0
                        height: 0.012396694214876033
                      - text: 福州
                        left: 0.13095238095238096
                        top: 0.13429752066115702
                        width: 0.22321428571428573
                        height: 0.04338842975206612
                      - text: 科技
                        left: 0.46726190476190477
                        top: 0.13429752066115702
                        width: 0.2261904761904762
                        height: 0.04338842975206612
                      - text: 馆
                        left: 0.8065476190476191
                        top: 0.13429752066115702
                        width: 0.05357142857142857
                        height: 0.04338842975206612
                      - text: 福州
                        left: 0.20535714285714285
                        top: 0.25413223140495866
                        width: 0.0744047619047619
                        height: 0.024793388429752067
                      - text: 科技
                        left: 0.28273809523809523
                        top: 0.25413223140495866
                        width: 0.0744047619047619
                        height: 0.024793388429752067
                      - text: 馆
                        left: 0.3601190476190476
                        top: 0.25413223140495866
                        width: 0.03571428571428571
                        height: 0.024793388429752067
                      - text: 空调
                        left: 0.39880952380952384
                        top: 0.25413223140495866
                        width: 0.07142857142857142
                        height: 0.024793388429752067
                      - text: 线路
                        left: 0.47619047619047616
                        top: 0.25413223140495866
                        width: 0.07142857142857142
                        height: 0.024793388429752067
                      - text: 改造
                        left: 0.5535714285714286
                        top: 0.25413223140495866
                        width: 0.07142857142857142
                        height: 0.024793388429752067
                      cost: 0.0
                    mistral:
                      text: "# 福州科技馆空调线路改造项目工程 \n\n## 施工招标公告\n\n招标项日福州科技馆空调线路改造项目工程已批准建设，招标人为：福州科技馆，建设资金来源——互惠。项目已具备招标条件，现对该项目的施工进行公开招标。\n\n## 1. 项目概况与招标范围\n\n建设地点：福州市仓山区横溢洲桥下公园内 工程招标控制价：29135元/ 计划工期：15日历天 质量要求：企络 㫮标范围：涉及工程量请来为准。\n\n## 2. 授标人资格要求\n\n2.1 授标人须具备人员、设备、资金等方面具有相应的设计经验及施工能力。\n2.2 本次招标不接受联合体授标。\n\n## 3. 授标报名、开标时间\n\n授标报名截止时间至2018年12月4日12时00分，开标"
                      bounding_boxes: []
                      usage: null
                      cost: 0.0
                    sentisight:
                      text: '#   M  # # @ 4 {042547.E 14171 UM: 223SIL; ##IM: JLEA 0464 #rMh 12# 00 9.#7'
                      bounding_boxes:
                      - text: '#   M  # # @'
                        left: 0.13095238095238096
                        top: 0.19008264462809918
                        width: 0.761904761904762
                        height: 0.06611570247933884
                      - text: '4'
                        left: 0.6160714285714286
                        top: 0.4731404958677686
                        width: 0.07738095238095233
                        height: 0.028925619834710703
                      - text: '{042547.E'
                        left: 0.1636904761904762
                        top: 0.5475206611570248
                        width: 0.26190476190476186
                        height: 0.02892561983471076
                      - text: '14171'
                        left: 0.7232142857142857
                        top: 0.5929752066115702
                        width: 0.15476190476190477
                        height: 0.03305785123966942
                      - text: 'UM:'
                        left: 0.12202380952380952
                        top: 0.6301652892561983
                        width: 0.0773809523809524
                        height: 0.028925619834710647
                      - text: '223SIL; ##IM:'
                        left: 0.2113095238095238
                        top: 0.6301652892561983
                        width: 0.2678571428571429
                        height: 0.028925619834710647
                      - text: JLEA
                        left: 0.49107142857142855
                        top: 0.6301652892561983
                        width: 0.15476190476190482
                        height: 0.028925619834710647
                      - text: '0464'
                        left: 0.15178571428571427
                        top: 0.8657024793388429
                        width: 0.11904761904761904
                        height: 0.028925619834710647
                      - text: '#rMh'
                        left: 0.28869047619047616
                        top: 0.8657024793388429
                        width: 0.125
                        height: 0.028925619834710647
                      - text: 12# 00 9.#7
                        left: 0.6577380952380952
                        top: 0.9028925619834711
                        width: 0.22023809523809523
                        height: 0.02892561983471076
                      cost: 0.0
                    microsoft:
                      text: 2. 2.2
                      bounding_boxes:
                      - text: '2.'
                        left: 0.12797619047619047
                        top: 0.6838842975206612
                        width: 0.017857142857142856
                        height: 0.01652892561983471
                      - text: '2.2'
                        left: 0.18154761904761904
                        top: 0.8016528925619835
                        width: 0.041666666666666664
                        height: 0.01652892561983471
                      cost: 0.0
                    api4ai:
                      text: 'I

                        福州科技馆

                        福州科技馆空调线路改造项目工程

                        施工招标公告

                        招标项目福州科技馆空调线路改造项目工程已批准建设,

                        招标人为福州科技馆,建设资金来源自筹。项目已具备

                        招标条件,现对该项目的施工进行公开招标。

                        1.项目概况与招标范围

                        建设地点: 福州市仓山区橘园洲桥下公园内 工程招标控

                        制价: 29135 元;计划工期: 15日历天质量要求:合

                        按招标范围:详见工程量清单为准,

                        2. 投标人资格要求

                        2.1 投标人须具备人员,设备,资金等方面具有相应的设

                        计经验及施工能力。

                        2. 2 本次招标不接受联合体投标。

                        3. 投标报名、开标时间

                        投标报名截止时间至2018年12月4日12时00分,开标'
                      bounding_boxes:
                      - text: 'I

                          福州科技馆

                          福州科技馆空调线路改造项目工程

                          施工招标公告

                          招标项目福州科技馆空调线路改造项目工程已批准建设,

                          招标人为福州科技馆,建设资金来源自筹。项目已具备

                          招标条件,现对该项目的施工进行公开招标。

                          1.项目概况与招标范围

                          建设地点: 福州市仓山区橘园洲桥下公园内 工程招标控

                          制价: 29135 元;计划工期: 15日历天质量要求:合

                          按招标范围:详见工程量清单为准,

                          2. 投标人资格要求

                          2.1 投标人须具备人员,设备,资金等方面具有相应的设

                          计经验及施工能力。

                          2. 2 本次招标不接受联合体投标。

                          3. 投标报名、开标时间

                          投标报名截止时间至2018年12月4日12时00分,开标'
                        left: -0.004132231404958678
                        top: 0.12202380952380952
                        width: 0.7440476190476191
                        height: 0.8987603305785123
                      cost: 0.0
                    amazon:
                      text: 'JH # . ****** are ***** . 1. ********* IN## : 29135  #RIM: **** $ # : ######### 2. ####### 2.1 . RE. *********** . 3. **** ######### 2018 *'
                      bounding_boxes:
                      - text: JH
                        left: 0.3082338869571686
                        top: 0.13518710434436798
                        width: 0.04629765450954437
                        height: 0.04273286834359169
                      - text: '#'
                        left: 0.6437202095985413
                        top: 0.13354769349098206
                        width: 0.04994326829910278
                        height: 0.044661857187747955
                      - text: .
                        left: 0.250115305185318
                        top: 0.44582700729370117
                        width: 0.15961581468582153
                        height: 0.023941639810800552
                      - text: '******'
                        left: 0.4236774146556854
                        top: 0.4461418688297272
                        width: 0.16829903423786163
                        height: 0.02276456542313099
                      - text: are
                        left: 0.6215114593505859
                        top: 0.44597354531288147
                        width: 0.05179109424352646
                        height: 0.02195529267191887
                      - text: '*****'
                        left: 0.7265733480453491
                        top: 0.4462999105453491
                        width: 0.14002187550067902
                        height: 0.021753868088126183
                      - text: .
                        left: 0.12542514503002167
                        top: 0.48515304923057556
                        width: 0.12193533033132553
                        height: 0.022544588893651962
                      - text: '1.'
                        left: 0.12524548172950745
                        top: 0.5207677483558655
                        width: 0.022567208856344223
                        height: 0.019478561356663704
                      - text: '*********'
                        left: 0.16472700238227844
                        top: 0.5190067887306213
                        width: 0.2541719079017639
                        height: 0.023697713389992714
                      - text: IN##
                        left: 0.7296434044837952
                        top: 0.5625028610229492
                        width: 0.1382470726966858
                        height: 0.022239895537495613
                      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: ''
    servers:
    - url: https://api.edenai.run/v2
  /ocr/ocr:
    post:
      summary: OCR
      description: Extract text from an image or PDF using selected OCR providers.
      operationId: ocr
      tags:
      - OCR
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - providers
              - file
              properties:
                providers:
                  type: string
                file:
                  type: string
                  format: binary
                language:
                  type: string
      responses:
        '200':
          description: OCR results
      security:
      - bearerAuth: []
    servers:
    - url: https://api.edenai.run/v2
      description: Production
components:
  schemas:
    BadRequest:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/NestedBadRequest'
      required:
      - error
    ocrocrResponseModel:
      properties:
        api4ai:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
        clarifai:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
        amazon:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
        microsoft:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
        mistral:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
        google:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
        sentisight:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
        base64:
          $ref: '#/components/schemas/ocrocrOcrDataClass'
          default: null
      title: ocrocrResponseModel
      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>
    Error:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/NestedError'
      required:
      - error
    ocrocrOcrDataClass:
      properties:
        text:
          title: Text
          type: string
        bounding_boxes:
          items:
            $ref: '#/components/schemas/Bounding_box'
          title: Bounding Boxes
          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:
      - text
      - status
      title: ocrocrOcrDataClass
      type: object
    NestedError:
      type: object
      properties:
        type:
          type: string
        message:
          type: string
      required:
      - message
      - type
    StatusEnum:
      enum:
      - sucess
      - fail
      type: string
    Bounding_box:
      properties:
        text:
          title: Text
          type: string
        left:
          title: Left
          type: integer
        top:
          title: Top
          type: integer
        width:
          title: Width
          type: integer
        height:
          title: Height
          type: integer
      required:
      - text
      - left
      - top
      - width
      - height
      title: Bounding_box
      type: object
    ocrocrOcrRequest:
      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
        language:
          type:
          - string
          - 'null'
          description: 'Language code of the language the document is written in (ex: fr (French), en (English), es (Spanish))'
      required:
      - providers
    NestedBadRequest:
      type: object
      properties:
        type:
          type: string
        message:
          $ref: '#/components/schemas/FieldError'
      required:
      - message
      - type
  securitySchemes:
    FeatureApiAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key
x-refined-from:
- eden-ai-ocr-features-openapi.json
- eden-ai-openapi.yml