REST API - Slai

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:

app.Trigger.RestAPI(
	inputs={"x": beam.Types.Float(), "y": beam.Types.Float()},
	outputs={"sum": beam.Types.Float()},
	handler="test.py:add_numbers",
)

Name	Type	Description
`inputs`	dict	A dictionary specifying the interface for the API
`outputs`	dict	A dictionary specifying the outputs returned from the API
`handler`	string	The 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 "https://beam.slai.io/ahg0v" \
   -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.

Type	Description
`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=falsebeam.types.Boolean(required=false)beam.types.Dataframe(required=false)