Custom Endpoints

You can add your own applications or models to DeepFellow as long as they expose a Web API. Custom models from Docker images can be called using /custom/{path} endpoint.

Supported HTTP methods are: GET, POST, PUT, DELETE, PATCH, HEAD, and OPTIONS.

Example

First, install your custom service or model using Docker images – learn how to do it with Custom Models guide. After installation, if your service provides Web API with /nlp endpoint, you can call one of its routes on /custom/nlp. For example:

curl -X 'POST' \
  'https://deepfellow-server-host/custom/nlp/sentiment' \
  -H 'Authorization: Bearer DEEPFELLOW-PROJECT-API-KEY' \
  -H 'Content-Type: application/json' \
  -d '{"text": "My dog is smiling at me."}'

  import requests

  response = requests.post(
      "https://deepfellow-server-host/custom/nlp/sentiment",
      json={
          "text": "My dog is smiling at me."
      },
      headers={
          "Content-Type": "application/json",
          "Authorization": "Bearer DEEPFELLOW-PROJECT-API-KEY"
      }
  )

  data = response.json()
  print(data)

const response = await fetch('https://deepfellow-server-host/custom/nlp/sentiment', {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json',
        Authorization: 'Bearer DEEPFELLOW-PROJECT-API-KEY'
    },
    body: JSON.stringify({
        text: 'My dog is smiling at me.'
    })
});

const data = await response.json();
console.log(data);

Response:

{ "label": "positive" }

Example

On this page