API

Every extractaai.api.* operation is listed below with parameter shapes and return types from the plugin Zod schemas.

New to Corsair? See API access, authentication, and error handling.

Classification

create

classification.create Create a document classification (EXTRACTA_AI_CREATE_CLASSIFICATION) Risk: write

await corsair.extractaai.api.classification.create({});

Input

Name	Type	Required	Description
`classificationDetails`	`object`	Yes	—

classificationDetails full type

{
  name: string,
  description?: string,
  documentTypes: {
    name: string,
    description: string,
    uniqueWords: string[],
    extractionId?: string
  }[]
}

Output

Name	Type	Required	Description
`status`	`created`	Yes	—
`createdAt`	`number`	Yes	—
`classificationId`	`string`	Yes	—

delete

classification.delete Delete a document classification (EXTRACTA_AI_DELETE_CLASSIFICATION) [DESTRUCTIVE · IRREVERSIBLE] Risk: destructive · Irreversible

await corsair.extractaai.api.classification.delete({});

Input

Name	Type	Required	Description
`classificationId`	`string`	Yes	—

Output

Name	Type	Required	Description
`status`	`success`	Yes	—
`message`	`string`	No	—

update

classification.update Update a document classification (EXTRACTA_AI_UPDATE_CLASSIFICATION) Risk: write

await corsair.extractaai.api.classification.update({});

Input

Name	Type	Required	Description
`classificationId`	`string`	Yes	—
`classificationDetails`	`object`	Yes	—

classificationDetails full type

{
  name: string,
  description: string,
  documentTypes: {
    name: string,
    description: string,
    uniqueWords: string[],
    extractionId?: string
  }[]
}

Output

Name	Type	Required	Description
`status`	`updated`	Yes	—
`updatedAt`	`number`	Yes	—
`classificationId`	`string`	Yes	—

view

classification.view View a document classification configuration (EXTRACTA_AI_VIEW_CLASSIFICATION) Risk: read

await corsair.extractaai.api.classification.view({});

Input

Name	Type	Required	Description
`classificationId`	`string`	Yes	—

Output

Name	Type	Required	Description
`status`	`success`	Yes	—
`classificationId`	`string`	Yes	—
`classificationDetails`	`object`	Yes	—

classificationDetails full type

{
  createdAt?: number,
  name: string,
  description?: string,
  documentTypes: {
    name: string,
    description: string,
    uniqueWords: string[],
    extractionId?: string
  }[]
}

Credits

get

credits.get Get the account credit balance (EXTRACTA_AI_GET_CREDITS) Risk: read

await corsair.extractaai.api.credits.get({});

Input: empty object Output

Name	Type	Required	Description
`status`	`ok`	Yes	—
`credits`	`number`	Yes	—

Extraction

create

extraction.create Create a document extraction template (EXTRACTA_AI_CREATE_EXTRACTION) Risk: write

await corsair.extractaai.api.extraction.create({});

Input

Name	Type	Required	Description
`extractionDetails`	`object`	Yes	—

extractionDetails full type

{
  name: string,
  description?: string,
  language: string,
  options?: {
    hasTable?: boolean,
    hasVisuals?: boolean,
    handwrittenTextRecognition?: boolean,
    checkboxRecognition?: boolean,
    longDocument?: boolean,
    splitPdfPages?: boolean,
    specificPageProcessing?: boolean,
    specificPageProcessingOptions?: {
      from: number,
      to: number
    }
  },
  fields: {
    key: string,
    description?: string,
    example?: string,
    type?: string | object | array,
    properties?: lazy[],
    items?: {
      type: string | object,
      example?: string,
      properties?: lazy[]
    }
  }[]
}

Output

Name	Type	Required	Description
`status`	`created`	Yes	—
`createdAt`	`number`	Yes	—
`extractionId`	`string`	Yes	—

delete

extraction.delete Delete an extraction, batch, or file (EXTRACTA_AI_DELETE_EXTRACTION) [DESTRUCTIVE · IRREVERSIBLE] Risk: destructive · Irreversible

await corsair.extractaai.api.extraction.delete({});

Input

Name	Type	Required	Description
`extractionId`	`string`	Yes	—
`batchId`	`string`	No	—
`fileId`	`string`	No	—

Output

Name	Type	Required	Description
`status`	`deleted`	Yes	—
`deletedAt`	`number`	Yes	—

getBatchResults

extraction.getBatchResults Get extraction results for a batch (EXTRACTA_AI_GET_BATCH_RESULTS) Risk: read

await corsair.extractaai.api.extraction.getBatchResults({});

Input

Name	Type	Required	Description
`extractionId`	`string`	Yes	—
`batchId`	`string`	Yes	—
`fileId`	`string`	No	—

Output: object

Output full type

{
  status: waiting,
  extractionId?: string,
  batchId?: string,
  fileId?: string
} | {
  extractionId: string,
  batchId: string,
  fileId?: string,
  files: {
    fileId?: string,
    fileName?: string,
    status: string,
    result?: lazy,
    url?: string
  }[]
}

update

extraction.update Update a document extraction configuration (EXTRACTA_AI_UPDATE_EXTRACTION) Risk: write

await corsair.extractaai.api.extraction.update({});

Input

Name	Type	Required	Description
`extractionId`	`string`	Yes	—
`extractionDetails`	`object`	Yes	—

extractionDetails full type

{
  name?: string,
  description?: string,
  language?: string,
  options?: {
    hasTable?: boolean,
    hasVisuals?: boolean,
    handwrittenTextRecognition?: boolean,
    checkboxRecognition?: boolean,
    longDocument?: boolean,
    splitPdfPages?: boolean,
    specificPageProcessing?: boolean,
    specificPageProcessingOptions?: {
      from: number,
      to: number
    }
  },
  fields?: {
    key: string,
    description?: string,
    example?: string,
    type?: string | object | array,
    properties?: lazy[],
    items?: {
      type: string | object,
      example?: string,
      properties?: lazy[]
    }
  }[]
}

Output

Name	Type	Required	Description
`status`	`updated`	Yes	—
`updatedAt`	`number`	Yes	—
`extractionId`	`string`	Yes	—

view

extraction.view View a document extraction configuration (EXTRACTA_AI_VIEW_EXTRACTION) Risk: read

await corsair.extractaai.api.extraction.view({});

Input

Name	Type	Required	Description
`extractionId`	`string`	Yes	—

Output

Name	Type	Required	Description
`extractionId`	`string`	Yes	—
`extractionDetails`	`object`	Yes	—

extractionDetails full type

{
  name: string,
  description?: string,
  language: string,
  options?: {
    hasTable?: boolean,
    hasVisuals?: boolean,
    handwrittenTextRecognition?: boolean,
    checkboxRecognition?: boolean,
    longDocument?: boolean,
    splitPdfPages?: boolean,
    specificPageProcessing?: boolean,
    specificPageProcessingOptions?: {
      from: number,
      to: number
    }
  },
  fields: {
    key: string,
    description?: string,
    example?: string,
    type?: string | object | array,
    properties?: lazy[],
    items?: {
      type: string | object,
      example?: string,
      properties?: lazy[]
    }
  }[],
  status?: string,
  batches?: {
  }
}

Overview

Plugins

Classification

create

delete

update

view

Credits

get

Extraction

create

delete

getBatchResults

update

view

​Classification

​create

​delete

​update

​view

​Credits

​get

​Extraction

​create

​delete

​getBatchResults

​update

​view

Classification

create

delete

update

view

Credits

get

Extraction

create

delete

getBatchResults

update

view