Giter VIP home page Giter VIP logo

ai's Introduction

AI-Playbook

Production URL

The latest non-dev version of this app is running at Live AI Playground.

Releasing to Production

Releasing to a Heroku app/account requires the appropriate setup, including environment variables (see below).

Running Locally

Make sure you have Node.js and the Heroku Toolbelt installed.

Environment variables

The following environment variables are required (they also have to be setup in the Heroku app's environment when running it there). These environment variables are obtained from the service provider's respective developer consoles after signing up for their services:

# Recaptcha
RECAPTCHA_SITE_KEY=<recaptcha site key>
RECAPTCHA_SECRET_KEY=<recaptcha secret key>

# Microsoft
MS_AZURE_COGNITIVE_SERVICES_API_KEY=<MS Azure Cognitive Services API Key>
MS_AZURE_COG_SERVICES_ENTITY_LINKING_API_KEY=<MS Azure Entity Linking API Key>
MS_AZURE_COMPUTER_VISION_KEY=<key>

# IBM Watson/Alchemy/etc (note that different IBM services have different auth requirements)
IBM_WATSON_TONE_USERNAME=<IBM Tone API Username>
IBM_WATSON_TONE_PASSWORD=<IBM Tone API Password>
IBM_ALCHEMY_API_KEY=<IBM Alchemy API Key>

# Google NLP
GCLOUD_PROJECT=<Google Cloud Platform Project ID>
GOOGLE_NLP_API_KEY=<API KEY>
GOOGLE_CLOUD_PRIVATE_KEY="<key>"
GOOGLE_CLOUD_EMAIL="[email protected]"

# Clarifai
CLARIFAI_CLIENT_ID=<token>
CLARIFAI_CLIENT_SECRET=<secret>

# Recast.ai
RECAST_AI_TOKEN=<token>

# API.ai
API_AI_TOKEN=<token>

# Baidu
BAIDU_TRANSLATION_APP_ID=<token>
BAIDU_TRANSLATION_KEY=<token>

# this is enabled for rate limiting on our production environment
REDIS_URL=redis://<Redis location>
RATE_LIMITING_ENABLED=true
RATE_LIMITING_INTERVAL=<interval>
RATE_LIMITING_REQUESTS=<limit>

These variables must be added as Config Vars to the Heroku app. We recommend including all the variables in a .env file to be placed in the root directory of the repository and then set in heroku via heroku config:set VARNAME=value. Alternatively, the variables can be configured directly on the shell via export VARNAME=value.

Packages used by the app are described in package.json and can be installed by running npm install on the local root directory of the repository.

$ npm install
$ npm start

For config values you can add them directly to the app as follows:

heroku config:add GOOGLE_CLOUD_PRIVATE_KEY="$GOOGLE_CLOUD_PRIVATE_KEY" --app YOURAPPNAME

when variables require quotes, or

heroku config:add GOOGLE_CLOUD_PRIVATE_KEY=<KEY> --app YOURAPPNAME

The app should now be running on localhost:5000.

Deployment

$ heroku create
$ git push heroku master
$ heroku open

or

Deploy to Heroku

Libraries Used

Recaptcha

https://www.google.com/recaptcha/admin

najax

Simple jQuery-like calls in Node.js https://github.com/najaxjs/najax

sentiment.js

https://github.com/thisandagain/sentiment

Sentimental

https://github.com/thinkroth/Sentimental

Recast AI

https://github.com/RecastAI/SDK-NodeJS

API.ai

https://github.com/api-ai/api-ai-node-js

IBM Watson Dev Cloud/Alchemy API

https://www.npmjs.com/package/watson-developer-cloud

Microsoft Azure Cognitive Services

https://portal.azure.com/ https://westus.dev.cognitive.microsoft.com/docs/services/

(Unofficial) Node.js API for Microsoft Azure Cognitive Services

https://github.com/joshbalfour/node-cognitive-services

Amazon Rekognition API

https://aws.amazon.com/rekognition/

Baidu Translation

http://api.fanyi.baidu.com/api/trans/product/index

Documentation

Other Software Used

ai's People

Contributors

diegodoval avatar efexen avatar ellm avatar kyh avatar leppert avatar mwee avatar pmn avatar roskoff avatar simon-hibbs avatar startakovsky avatar tomazberisa avatar trampolinerocket avatar withfries2 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

ai's Issues

Swift stdlib tool Error

Getting this error "Swift stdlib tool Error"
Task failed with exit 1 signal 0

I've tried resetting my keychain and account, and still getting the issue.

The build is successful if I run in on an iPhone simulator, but the build fails when I try to use my phone. (iPhone 7 Plus iOS 11.1)

I'm wondering if it's because I just signed up for my developer account. Will wait and see if it's working in the next day.

No Vision Examples

Following through the reading linearly, there are examples linked off in the NLP page (for the sentiment analysis API, language analysis API, and entity analysis API's). But on the computer vision page there are no such comparison examples which would be useful.

The page following computer vision is the 'Building your own model' page which begins with "If you've played with the examples from the previous sections on NLP and vision recognition, you've seen the power of APIs. Send in a picture, get a list of objects in that picture; send in a sentence, and get the emotional tilt of that sentence, or get the sentence back in another language. Magic.". But actually following along we haven't seen that - we haven't sent any pictures anywhere.

Request: some usable examples of image recognition APIs.

Link to playbook in README

The README has a link to localhost and a TODO note that says to update it. I think that URL is intended to be http://aiplaybook.a16z.com/ but since I'm on mobile not my computer right now and also because I'm not 100% sure it's the right link I submit this as an issue rather than editing and submitting a PR

Typo in section 'What Can You Do with AI?'

Specifically in the section headed 'Applying AI to your Business':

'Here are a a few was you can brainstorm how AI can help:'

should be->

'Here are a few ways you can brainstorm how AI can help:'

Failing NLP API's

Hello!

Some apis in the Natural Language Processing section.

Google Cloud API in some calls shows "Limit exceeded" and in others show some weird metadata (i think the endpoint you're calling is no longer available).

Also IBM Alchemy Language API seems down, always return error after some time.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.