This is not an official Google product
This repo includes 4 demos from my Google Next talk and Google I/O talk on the Cloud ML APIs. To run the demos, follow the instructions below.
cd
into vision-api-firebase
firebase login
via the CLI and then firebase init functions
to initialize the Firebase SDK for Cloud Functions. When prompted, don't overwrite functions/package.json
or functions/index.js
.functions/
directory in a file called keyfile.json
:functions/index.js
replace both instances of your-firebase-project-id
with the ID of your Firebase projectfirebase deploy --only functions
firebase serve
from the vision-api-firebase/
directory of this project. Navigate to localhost:5000
to try uploading a photo. After uploading a photo check your Functions logs and then your Firebase Database to confirm the function executed correctly.firebase deploy --only hosting
. For future deploys you can run firebase deploy
to deploy Functions and Hosting simultaneously.cd
into speech/
brew install sox --with-flac
request.sh
bash request.sh
cd
into natural-language/
Generate Twitter Streaming API credentials and copy them to local.json
Create a Google Cloud project, generate a JSON keyfile, and add the filepath to local.json
Create a BigQuery dataset and table with the below schema, add them to local.json
Generate an API key and add it to local.json
Change line 37 to filter tweets on whichver terms you'd like
Install node modules: npm install
Run the script: node twitter.js
cd
into nl-firebase-twitter/
cd
into the frontend/
directory and run firebase login
and firebase init
to associate this with the Firebase project you just created. When prompted, don't overwrite existing files. Create a database and hosting project (no Functions).cd
into the backend/
directory and run npm install
to install dependenciesbackend/
directory as keyfile.json
backend/local.json
YOUR-API-KEY
in backend/local.json
with this key.searchTerms
in backend/index.js
with the search terms you'd like to filter tweets onFIREBASE-PROJECT-ID
in backend/local.json
with the id of your Firebase projectid:STRING,text:STRING,user:STRING,user_time_zone:STRING,user_followers_count:INTEGER,hashtags:STRING,tokens:STRING,score:STRING,magnitude:STRING,entities:STRING
backend/local.json
.backend/
directory run node index.js
. You should see tweet data being written to your Firebase databasefrontend/
directory run firebase serve
frontend/
directory run firebase deploy
cd
into vision-speech-nl-translate
python textify.py