Chabad Library Text Processing API
  1. Extraction
Chabad Library Text Processing API
  • System
    • Health Check
      GET
  • Search
    • Search Chabad Library
      GET
  • Texts
    • List All Texts
      GET
    • Get Text by Slug
      GET
  • Extraction
    • Test Chabad Library API
      GET
    • Extract Text from Document
      POST
  • Processing
    • Generate Document Outline
      POST
    • Process Complete Document
      POST
    • Translate Document Segment
      POST
  • Schemas
    • HealthResponse
    • ErrorResponse
    • SourceMetadata
    • OutlineSegment
    • DocumentOutline
    • TranslationData
    • Footnote
    • TranslatedSegment
    • EnrichedSegment
    • ProcessedDocument
    • SearchResult
    • SearchResultsResponse
    • WorkByIdResponse
    • NavSearchResult
    • TextListItem
    • NavSearchResultsResponse
    • PaginationInfo
    • PaginatedTextsResponse
  1. Extraction

Extract Text from Document

POST
/api/extract
Extract text content from a PDF or image file using Google Gemini. Supports streaming (not yet fully implemented) and multiple output formats (JSON or Markdown).

Request

Query Params

Body Params multipart/form-dataRequired

Responses

🟢200Success
application/json
Extracted text content
Body

🟠400400
🔴500500
🔴501501
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST '/api/extract?stream&format' \
--form 'file=@""'
Response Response Example
200 - Example 1
{
    "text": "string"
}
Modified at 2025-12-03 11:51:17
Previous
Test Chabad Library API
Next
Generate Document Outline
Built with