read-pdf2llm
Version:
High-performance PDF text extractor (with OCR fallback) for Node.js, optimized for LLM pipelines. Uses PDFium, Tesseract, and C++ addon.
43 lines (42 loc) • 901 B
JSON
{
"name": "read-pdf2llm",
"version": "1.0.33",
"description": "High-performance PDF text extractor (with OCR fallback) for Node.js, optimized for LLM pipelines. Uses PDFium, Tesseract, and C++ addon.",
"main": "index.js",
"keywords": [
"pdf",
"ocr",
"nodejs",
"native-addon",
"tesseract",
"pdfium",
"llm",
"text-extraction"
],
"author": "Vitor Ricardo <vitorricardo@outlook.com>",
"license": "MIT",
"type": "commonjs",
"scripts": {
"build": "node-gyp configure build",
"prebuild": "prebuild --napi --strip"
},
"dependencies": {
"node-addon-api": "^7.0.0",
"node-gyp-build": "^4.8.0"
},
"devDependencies": {
"node-gyp": "^10.3.1",
"prebuild": "^13.0.1"
},
"overrides": {
"prebuild": {
"node-gyp": "^10.2.0"
}
},
"files": [
"index.js",
"prebuilds/**",
"README.md",
"LICENSE"
]
}