Initial commit

.babelrc

@@ -0,0 +1,6 @@
+{
+  "presets": [
+    "@babel/preset-env",
+    "@babel/preset-typescript"
+  ]
+}

.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

.gitignore

@@ -0,0 +1,138 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
+
+
+build
+
+.DS_Store
+
+storage
+dist

README.md

@@ -0,0 +1,17 @@
+# Data Connectors for LLM
+
+This repository contains a collection of data connectors built by Mendable AI. These connectors are designed to output data in a specific format suitable for LLMs.
+
+## Connectors
+
+The following connectors are currently available:
+
+- Google Drive
+- Web Scraper
+- Zendesk
+- Text
+- Confluence (In progress)
+
+## Usage
+
+To use these connectors, you need to create a data connector with the provider of your choice. Here is an example:

babel.config.js

@@ -0,0 +1,3 @@
+module.exports = {
+  presets: [['@babel/preset-env', {targets: {node: 'current'}}]],
+};

example.env

@@ -0,0 +1,6 @@
+GOOGLE_DRIVE_CLIENT_ID=<>
+GOOGLE_DRIVE_CLIENT_SECRET=<>
+GOOGLE_DRIVE_REDIRECT_URI=<>
+NANGO_SECRET_KEY=<>
+SCRAPING_BEE_API_KEY=<>
+NANGO_CONNECTION_ID_TEST=<>

jest.config.js

@@ -0,0 +1,6 @@
+module.exports = {
+  transform: {
+    '^.+\\.tsx?$': 'babel-jest',
+  },
+  moduleFileExtensions: ['ts', 'tsx', 'js', 'jsx', 'json', 'node'],
+};