Switch branches/tags
Nothing to show
Clone or download
ramhiser git-ignoring Google app credentials
Got the idea from @ebahsini in #4 (before he deleted it)
Latest commit 50267da Nov 27, 2016

Serverless API around Google Cloud Vision

This project is a serverless API wrapper around Google Cloud Vision using AWS API Gateway + AWS Lambda. Deployment is performed with the Serverless Framework.


The API Gateway endpoint accepts an image URL and triggers a Lambda function, which ingests the image from a URL and sends the image to Google Cloud Vision for standard image recognition tasks (e.g., facial detection, OCR, etc.).

For instance, the following curl command sends an image URL to the API Gateway.

curl -H "Content-Type: application/json" -X POST \
-d '{"image_url": ""}' \

The response JSON includes a variety of metadata to describe the faces detected:

  "responses": [
      "faceAnnotations": [
          "angerLikelihood": "VERY_UNLIKELY",
          "blurredLikelihood": "VERY_UNLIKELY",
          "boundingPoly": {
            "vertices": [
                "x": 512,
                "y": 249
                "x": 637,
                "y": 249
                "x": 637,
                "y": 395
                "x": 512,
                "y": 395
          "detectionConfidence": 0.98645973,

In the examples folder, we provide a script that produces a new image with bounding boxes around the faces detected:

highlighted faces

Beyond facial detection, Google Cloud Vision supports the following image recognition tasks:


Google Cloud Vision Credentials

In order to access the Cloud Vision API, you will need to create Google Application Credentials by following the instructions here for the Service Account Key. Then, download the JSON file with your application credentials and rename the file as cloudvision/google-application-credentials.json.


Make sure you have Node.js 4.0+ installed. Then, install the Serverless Framework.

npm install serverless -g

Install any Python dependencies to the cloudvision/vendored folder.

pip install -t cloudvision/vendored/ -r requirements.txt

NOTE: Homebrew + Mac OS users who encounter the DistutilsOptionError error should see this SO post for a fix.

After installing Python requirements to the vendored folder, type the following at the commandline to deploy the wrapper API:

serverless deploy

This command does the following:

  • Create IAM roles on AWS for Lambda and API Gateway
  • Zips Python code and uploads to S3
  • Creates AWS Lambda function
  • Creates API Gateway endpoint that triggers AWS Lambda function


Example Python scripts are available in the examples folder. These examples require that the API (described above) be successfully deployed. As mentioned by Chris Cooper, the Python dependencies must be installed locally in order to run the examples. To do this, type the following locally:

pip install -r requirements.txt