A fast, helpful, and open-source document parser
ocr/
Example OCR server implementations that conform to the LiteParse OCR API specification.
These servers allow you to use alternative OCR engines instead of the built-in Tesseract.js.
Why Use an External OCR Server?
| Feature | Tesseract.js (built-in) | EasyOCR | PaddleOCR | Surya | Indra | MiniCPM-OCR |
|---|---|---|---|---|---|---|
| Setup | Zero (included) | uv | uv | uv | uv | uv + inference server |
| Speed | Moderate | Moderate | Fast (2-3x) | Moderate (GPU recommended) | Fast (CPU only) | ~1.2 pages/s (GPU) |
| Accuracy (Latin) | Good | Good | Good | Excellent | Very good | Excellent |
| Accuracy (CJK) | Fair | Good | Excellent | Excellent | Good (Chinese only) | Excellent |
| Languages | 100+ | 80+ | 80+ | 91 | ~55 (Latin, Cyrillic, Greek, Devanagari, Bengali, Chinese) | zh, en |
| Memory | In-process | Separate | Separate | Separate | Separate | Separate (layout in-process) |
Recommendations:
- Quick start: Use built-in Tesseract (no setup)
- Asian languages: Use PaddleOCR (best CJK support)
- Multilingual / broad scripts: Use Surya (strong multilingual accuracy)
- General use: EasyOCR (good balance)
- Fast CPU OCR / scans: Use Indra (no GPU; check the model-weights license)
- Document parsing (tables, formulas, seals): Use MiniCPM-OCR (Chinese and English)
Available Servers
easyocr/
Flask server wrapping EasyOCR library.
- Port: 8828
- Good general-purpose OCR
- 80+ languages
paddleocr/
Flask server wrapping PaddleOCR library.
- Port: 8829
- Excellent for Chinese, Japanese, Korean
- 2-3x faster than EasyOCR
suryaocr/
FastAPI server wrapping Surya OCR 2.
- Port: 8830
- Multilingual foundation model (90+ languages)
- Block-level output; GPU recommended
indraocr/
FastAPI server wrapping Indra OCR.
- Port: 8831
- Small CPU-only model (ONNX Runtime, no GPU)
- Line-level output; straightens skewed and sideways pages
- Model weights are under a modified OpenRAIL-M license (see its README)
minicpmocr/
FastAPI server wrapping MiniCPM-OCR 1.0.
- Port: 8832
- Chinese and English document parsing, including tables and formulas
- Runs the PP-DocLayout layout detector in-process and needs a MiniCPM-OCR
inference server (vLLM, SGLang, llama.cpp, or Ollama) via
MINICPM_OCR_BASE_URL
Quick Start
# Start EasyOCR server
cd ocr/easyocr
uv run server.py
# OR start PaddleOCR server
cd ocr/paddleocr
uv run server.py
# OR start Surya OCR server
cd ocr/suryaocr
uv run server.py
# OR start Indra OCR server
cd ocr/indraocr
uv run server.py
# OR start MiniCPM-OCR server (needs a MiniCPM-OCR inference server)
cd ocr/minicpmocr
MINICPM_OCR_BASE_URL=http://localhost:18499 uv run server.py
Then use with LiteParse:
# CLI
lit parse document.pdf --ocr-server-url http://localhost:8828/ocr
# Code
const parser = new LiteParse({
ocrServerUrl: 'http://localhost:8828/ocr',
ocrLanguage: 'en',
});
API Specification
All servers implement the same API (defined in OCR_API_SPEC.md):
Endpoint: POST /ocr
Request:
- Content-Type:
multipart/form-data - Fields:
file- Image filelanguage- Language code (e.g., 'en', 'zh', 'ja')
Response:
{
"results": [
{
"text": "recognized text",
"bbox": [x1, y1, x2, y2],
"confidence": 0.95
}
]
}
Creating a Custom OCR Server
To implement your own OCR server:
Create a Flask/FastAPI/Express server
Accept
POST /ocrwith multipart form dataReturn JSON with
resultsarray containing:text- Recognized text stringbbox- Bounding box as[x1, y1, x2, y2]confidence- Confidence score (0-1)
(Optional) Implement
GET /healthendpoint
See the existing servers as reference implementations.
Language Codes
Most servers accept ISO 639-1 codes (e.g., 'en', 'zh', 'ja') and map them internally:
| ISO Code | Language | Notes |
|---|---|---|
| en | English | |
| zh | Chinese (Simplified) | |
| zh-tw | Chinese (Traditional) | |
| ja | Japanese | |
| ko | Korean | |
| fr | French | |
| de | German | |
| es | Spanish | |
| ar | Arabic | |
| hi | Hindi |