GitHub - cernis-intelligence/docuglean-ocr: Intelligent document processing. Extract structured data like JSON, Markdown and HTML from documents using AI.

Intelligent document processing using State of the Art AI models.

If you find Docuglean helpful, please ⭐ this repository to show your support!

npm install docuglean-ocr

import { ocr, extract } from 'docuglean-ocr';

// Extract raw text from documents (supports URLs and local files)
const ocrResult = await ocr({
  filePath: 'https://arxiv.org/pdf/2302.12854',
  provider: 'openai',
  model: 'gpt-4o-mini',
  apiKey: 'your-api-key'
});

import { z } from 'zod';

// Define schema for structured extraction
const ReceiptSchema = z.object({
  date: z.string(),
  total: z.number(),
  items: z.array(z.object({
    name: z.string(),
    price: z.number()
  }))
});

// Extract structured data from documents
const extractResult = await extract({
  filePath: './receipt.pdf',
  provider: 'mistral',
  model: 'mistral-small-latest',
  apiKey: 'your-api-key',
  responseFormat: ReceiptSchema,
  prompt: 'Extract receipt details including date, total, and items'
});
// Summarization via extract
const SummarySchema = z.object({
  title: z.string().optional(),
  summary: z.string().min(50),
  keyPoints: z.array(z.string()).min(3).max(7),
});
const summary = await extract({
  filePath: './long-report.pdf',
  provider: 'openai',
  apiKey: 'your-api-key',
  responseFormat: SummarySchema,
  prompt: 'Provide a concise 3-sentence summary of this document and 3–7 key points.'
});
console.log('Summary:', summary.summary);

from docuglean import ocr, extract

# Extract raw text from documents (supports URLs and local files)
ocr_result = await ocr(
    file_path="./test/data/testocr.png",
    provider="gemini",
    model="gemini-2.5-flash",
    api_key="your-api-key"
)

from pydantic import BaseModel
from typing import List

# Define schema for structured extraction
class Item(BaseModel):
    name: str
    price: float

class Receipt(BaseModel):
    date: str
    total: float
    items: List[Item]

# Extract structured data from documents
extract_result = await extract(
    file_path="./receipt.pdf",
    provider="mistral",
    model="mistral-small-latest",
    api_key="your-api-key",
    response_format=Receipt,
    prompt="Extract receipt details including date, total, and items"
)

# Summarization via extract
class Summary(BaseModel):
    title: str | None = None
    summary: str
    keyPoints: List[str]

summary = await extract(
    file_path="./long-report.pdf",
    provider="openai",
    api_key="your-api-key",
    response_format=Summary,
    prompt="Provide a concise 3-sentence summary of this document and 3–7 key points."
)
print("Summary:", summary.summary)

from docuglean import classify, CategoryDescription

# Classify a patient medical record
result = await classify(
    file_path="./patient-record.pdf",
    categories=[
        CategoryDescription(
            name="Patient Intake Forms",
            description="Pages with patient registration, insurance information, and consent forms"
        ),
        CategoryDescription(
            name="Medical History",
            description="Pages containing past medical history, medications, allergies, and family history"
        ),
        CategoryDescription(
            name="Lab Results",
            description="Pages with laboratory test results, blood work, and diagnostic reports"
        ),
        CategoryDescription(
            name="Treatment Notes",
            description="Pages with doctor's notes, treatment plans, and prescriptions"
        )
    ],
    api_key="your-api-key",
    provider="mistral"
)

# Access the results
for split in result.splits:
    print(f"{split.name}: Pages {split.pages} (confidence: {split.conf})")

from docuglean import batch_ocr, batch_extract
from docuglean.types import OCRConfig, ExtractConfig

# Batch OCR
results = await batch_ocr([
    OCRConfig(file_path="./invoice1.pdf", provider="openai", api_key="your-api-key"),
    OCRConfig(file_path="./invoice2.pdf", provider="mistral", api_key="your-api-key"),
    OCRConfig(file_path="./receipt.png", provider="local", api_key="not-needed")
])

# Handle results - errors don't stop processing
for i, result in enumerate(results):
    if result["success"]:
        print(f"File {i + 1} processed successfully")
    else:
        print(f"File {i + 1} failed:", result["error"])

from docuglean import parse_docx, parse_pptx, parse_spreadsheet, parse_pdf, parse_csv

# Parse DOCX files (returns HTML, Markdown, and raw text)
result = await parse_docx("./document.docx")
print(result["markdown"])

# Parse PPTX, XLSX, PDF, CSV files
pptx_result = await parse_pptx("./presentation.pptx")
xlsx_result = await parse_spreadsheet("./data.xlsx")
pdf_result = await parse_pdf("./document.pdf")
csv_result = await parse_csv("./data.csv")

cd node-ocr
npm install
npm run build
npm test

cd python-ocr
uv sync
uv run pytest