Extract document data (Async)

post

Authorizations

ApiKeyAuth

X-Api-KeystringRequired

Body

application/json

agentInstructionsstring · max: 4000 · nullableOptional

Additional system-level instructions injected into the LLM system prompt

Default: null

analysisDepthstring · enum · nullableOptional

Depth of document analysis: 'quick' (skip classification if type provided) or 'standard' (full analysis)

Default: standardPossible values:

chartOfAccountsany of · nullableOptional

Chart of accounts mapping. Flat array for standard: [{accountId, accountName}]. Structured dict for BusinessFinancialStatement: {BalanceSheet: [...], ProfitAndLossStatement: [...]}.

Default: null

or

chartOfAccountsUrlstring · nullableOptional

URL to download chart of accounts JSON. Only used when chartOfAccounts is not provided directly.

Default: null

contentstring · nullableOptional

Base64-encoded file content

Default: null

custom_document_typesstring[] · nullableOptional

Custom document type names to use for V2 classification instead of the built-in list

Default: null

documentTypestring · nullableOptional

Document type. Mutually exclusive with documentTypes; one is required.

Default: null

enableCachingboolean · nullableOptional

If true, store extraction result in cache for future requests

Default: false

enableDocumentAnalysisboolean · nullableOptional

Run AI document analysis to categorize content before extraction (V2 only)

Default: true

enableJudgeboolean · nullableOptional

Enable LLM-as-Judge evaluation: a second LLM reviews extraction quality post-hoc

Default: false

enablePageContentboolean · nullableOptional

Include page-wise OCR content and AI-generated summaries per page

Default: false

enablePageSummariesboolean · nullableOptional

Deprecated — use enablePageContent instead

Default: false

enableRawSectionsboolean · nullableOptional

Include raw OCR text sections with bounding boxes in the result (V2 only)

Default: false

extractionPromptstring · nullableOptional

Custom natural language prompt to guide LLM extraction behavior beyond the extractionFormat schema.

Default: null

file_urlstring · nullableOptional

Public URL to file

Default: null

form8825Addressstring · nullableOptional

Single property address (backward-compatible alias for form8825Addresses with one entry)

Default: null

form8825Addressesstring[] · nullableOptional

Property addresses for Form 8825 direct deep extraction. Skips property identification and runs a native-PDF extraction per address.

Default: null

formTypesstring[] · nullableOptional

Form types (for tax documents)

Default: null

galleryIdsstring[] · nullableOptional

Knowledge Search gallery IDs to tag the document into after extraction

Default: null

includeLayoutboolean · nullableOptional

Include document layout structure (tables, paragraphs, headings) in result

Default: false

industrystring · nullableOptional

Industry name to load default chart of accounts from database for supported document types

Default: null

modelstring · enum · nullableOptional

LLM model for extraction

Default: gemini-3Example: gemini-3Possible values:

overrideCacheboolean · nullableOptional

If true, bypass cached extraction results and re-extract from scratch

Default: false

querystring · nullableOptional

Natural language question to answer after extraction completes. Enables async Q&A on the result.

Default: null

quickExtractboolean · nullableOptional

Use Gemini native PDF extraction (bypasses Azure OCR). Faster but may have lower accuracy for complex layouts.

Default: false

rawExtractionOnlyboolean · nullableOptional

Skip LLM extraction entirely; return only OCR/layout data without structured extraction

Default: false

subtypestring · nullableOptional

Document subtype

Default: null

tagInstructionsstring · nullableOptional

Tag classification instructions (only used when documentType is OtherWithMetadata)

Default: null

Responses

200

OK

application/json

messagestring · nullableOptional

Status message

Default: null

statusstring · enumOptionalDefault: successPossible values:

202

Accepted — returned instead of 200 when the request uses documentTypes for a multi-extraction. The success code varies with the request, not just the endpoint.

400

Bad Request

application/json

401

Authentication required — the X-Api-Key header is missing or invalid.

500

Returned instead of 400 when the request body is missing or invalid. Known defect — see the API Reference.

post/extract

HTTPcURLJavaScriptPython

POST /extract HTTP/1.1
Host: api-docai-uat.uptiq.ai
X-Api-Key: YOUR_API_KEY
Content-Type: application/json
Accept: */*
Content-Length: 1015

{
  "additionalParams": {
    "extractImages": false,
    "imageInstructions": "text",
    "returnFieldConfidences": false
  },
  "agentInstructions": "text",
  "analysisDepth": "standard",
  "chartOfAccounts": {
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "chartOfAccountsUrl": "text",
  "content": "text",
  "custom_document_types": [
    "text"
  ],
  "documentType": "text",
  "documentTypes": [
    {
      "documentType": "text",
      "entity": "text",
      "entityId": "text",
      "pageNumbers": [
        1
      ],
      "sheetNames": [
        "text"
      ]
    }
  ],
  "enableCaching": false,
  "enableDocumentAnalysis": true,
  "enableJudge": false,
  "enablePageContent": false,
  "enablePageSummaries": false,
  "enableRawSections": false,
  "extractionFormat": {
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "extractionPrompt": "text",
  "file_url": "text",
  "form8825Address": "text",
  "form8825Addresses": [
    "text"
  ],
  "formTypes": [
    "text"
  ],
  "galleryIds": [
    "text"
  ],
  "includeLayout": false,
  "industry": "text",
  "metadata": {
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "model": "gemini-3",
  "overrideCache": false,
  "query": "text",
  "quickExtract": false,
  "rawExtractionOnly": false,
  "subtype": "text",
  "tagInstructions": "text"
}

{
  "data": {
    "_id": "text",
    "documentStatus": "Pending",
    "documentType": "text",
    "requestId": "text",
    "subtype": "text"
  },
  "message": "text",
  "status": "success"
}