Files
anything-llm/collector/package.json
Timothy Carambat 719521c307 Document Processor v2 (#442)
* wip: init refactor of document processor to JS

* add NodeJs PDF support

* wip: partity with python processor
feat: add pptx support

* fix: forgot files

* Remove python scripts totally

* wip:update docker to boot new collector

* add package.json support

* update dockerfile for new build

* update gitignore and linting

* add more protections on file lookup

* update package.json

* test build

* update docker commands to use cap-add=SYS_ADMIN so web scraper can run
update all scripts to reflect this
remove docker build for branch
2023-12-14 15:14:56 -08:00

42 lines
1.1 KiB
JSON

{
"name": "anything-llm-document-collector",
"version": "0.2.0",
"description": "Document collector server endpoints",
"main": "index.js",
"author": "Timothy Carambat (Mintplex Labs)",
"license": "MIT",
"private": false,
"engines": {
"node": ">=18.12.1"
},
"scripts": {
"dev": "NODE_ENV=development nodemon --trace-warnings index.js",
"start": "NODE_ENV=production node index.js",
"lint": "yarn prettier --write ./processSingleFile ./processLink ./utils index.js"
},
"dependencies": {
"@googleapis/youtube": "^9.0.0",
"bcrypt": "^5.1.0",
"body-parser": "^1.20.2",
"cors": "^2.8.5",
"dotenv": "^16.0.3",
"express": "^4.18.2",
"extract-zip": "^2.0.1",
"js-tiktoken": "^1.0.8",
"langchain": "0.0.201",
"mammoth": "^1.6.0",
"mbox-parser": "^1.0.1",
"mime": "^3.0.0",
"moment": "^2.29.4",
"multer": "^1.4.5-lts.1",
"officeparser": "^4.0.5",
"pdf-parse": "^1.1.1",
"puppeteer": "^21.6.1",
"slugify": "^1.6.6",
"uuid": "^9.0.0"
},
"devDependencies": {
"nodemon": "^2.0.22",
"prettier": "^2.4.1"
}
}