Deploying a REST API

Beam apps can be deployed using the RestAPI trigger.

Input and output fields are serialized and validated by the Beam.Types module.

Here’s an example of what this might look like:

	inputs={"x": beam.Types.Float(), "y": beam.Types.Float()},
	outputs={"sum": beam.Types.Float()},
inputsdictA dictionary specifying the interface for the API
outputsdictA dictionary specifying the outputs returned from the API
handlerstringThe function that will be run when the API is invoked

Calling the API

After deploying the API, you’ll be able to copy a cURL request to hit the API. In your app dashboard, click Call API.

Call API

Example Request

curl -X POST --compressed "" \
   -H 'Accept: */*' \
   -H 'Accept-Encoding: gzip, deflate' \
   -H 'Authorization: Basic dW5kZWZpbmVkOnVuZGVmaW5lZA==' \
   -H 'Connection: keep-alive' \
   -H 'Content-Type: application/json' \
   -d '{"prompt": "Here's my example prompt"}'

Example Response

  "result": {
    "prediction": "{'POSITIVE': 0.9988627433776855, 'NEGATIVE': 0.0011372779263183475}"
  "msg": "",
  "error_msg": ""

Beam Types

The beam library includes several basic data types that can be used to validate your inputs against.

beam.types.Json()A JSON object
beam.types.String(max_length=None)A string field, with an optional max_length parameter
beam.types.Float()Standard floating point value
beam.types.Boolean()Standard boolean value
beam.types.Tensor(shape=None, dtype=None)A torch tensor object, with optional shape and dtype parameters
beam.types.Dataframe()A pandas dataframe object
beam.types.NumpyArray(shape=None, dtype=None)A numpy array, with optional shape and dtype parameters
beam.types.Binary()A binary object, for example a video file or anything that doesn’t fit into the other types listed
beam.types.Image(raw=False)A generic image, automatically serialized into a PIL object for use in the handler

Types can be labeled optional by passing in required=false