Complete API reference for @edwinfom/resume-intel — parseResume, options, return types, and exported schemas.

API Reference

parseResume(input, options)

The main function. Accepts a PDF buffer and returns structured resume data.

Parameters

input — Buffer | ArrayBuffer | Uint8Array

The PDF file content. All three buffer types are accepted.

options — ResumeIntelOptions

Option Type Default Description
model LanguageModel required Any Vercel AI SDK compatible model
maxRetries number 3 Max self-correction attempts per section on validation failure
layoutStrategy 'spatial' | 'linear' 'spatial' PDF text extraction strategy
useTaskDecomposition boolean true Run parallel per-section extractions
systemPromptPrefix string '' Custom instructions injected before extraction prompts
abortSignal AbortSignal — Standard abort signal for cancellation

Return value

Promise<ResumeIntelResult>

interface ResumeIntelResult {
  data: JsonResume      // JSON Resume v1 compatible object
  meta: ExtractionMeta
}
 
interface ExtractionMeta {
  durationMs: number              // total processing time in ms
  retryCount: number              // retries in single-shot mode
  ocrFallback: boolean            // true if Tesseract OCR was used
  layoutStrategy: 'spatial' | 'linear'
  pageCount: number               // number of PDF pages
  tokenUsage?: {
    promptTokens: number
    completionTokens: number
    totalTokens: number
  }
  sectionResults?: Array<{        // task decomposition mode only
    section: string               // 'basics' | 'work' | 'education' | ...
    success: boolean
    retryCount: number
    error: string | null
  }>
}

JsonResumeSchema

The Zod schema for the JSON Resume v1 specification. Use it to validate your own data.

import { JsonResumeSchema } from '@edwinfom/resume-intel'
 
const result = JsonResumeSchema.safeParse(myData)

SectionSchemas

Individual Zod schemas for each JSON Resume section.

import { SectionSchemas } from '@edwinfom/resume-intel'
 
const workResult = SectionSchemas.work.safeParse(myWorkData)

Available keys: basics, work, education, skills, languages, projects, awards, certificates, publications, volunteer, interests, references

Error classes

ResumeExtractionError

Thrown when the LLM fails to produce valid data after all retry attempts.

import { ResumeExtractionError } from '@edwinfom/resume-intel'
 
try {
  const result = await parseResume(pdfBuffer, { model })
} catch (error) {
  if (error instanceof ResumeExtractionError) {
    console.error(error.message)  // "Failed to extract valid resume data after 4 attempts..."
    console.error(error.cause)    // the underlying Zod or API error
  }
}

OcrNotEnabledError

Thrown when a scanned PDF is detected but OCR processing fails (e.g., tesseract.js issue).

import { OcrNotEnabledError } from '@edwinfom/resume-intel'
 
try {
  const result = await parseResume(pdfBuffer, { model })
} catch (error) {
  if (error instanceof OcrNotEnabledError) {
    console.error('OCR failed:', error.message)
  }
}

TypeScript types

All types are exported from the main entry point:

import type {
  ResumeIntelOptions,
  ResumeIntelResult,
  ExtractionMeta,
  SectionExtractionResult,
  TokenUsage,
  JsonResume,
  ResumeSectionKey,
  TextBlock,
  SpatialDocument,
  SpatialPage,
} from '@edwinfom/resume-intel'