README.md

node-red-contrib-vectorize

A Node-RED node to vectorize text using TensorFlow.js and Universal Sentence Encoder.

Installation

To install this node, run the following command in your Node-RED user directory (typically ~/.node-red):

npm install node-red-contrib-vectorize
Usage
This node uses TensorFlow.js and the Universal Sentence Encoder to convert text into a vector representation.

Input
msg.payload: A string of text that you want to vectorize.
Output
msg.payload: A vector representation of the input text.
Example Flow
Here is an example flow that demonstrates how to use the vectorize node:

<JSON>
[
    {
        "id": "1",
        "type": "inject",
        "z": "1",
        "name": "",
        "props": [
            {
                "p": "payload"
            }
        ],
        "repeat": "",
        "crontab": "",
        "once": false,
        "onceDelay": 0.1,
        "topic": "",
        "payload": "Hello, world!",
        "payloadType": "str",
        "x": 150,
        "y": 100,
        "wires": [
            [
                "2"
            ]
        ]
    },
    {
        "id": "2",
        "type": "vectorize",
        "z": "1",
        "name": "",
        "x": 350,
        "y": 100,
        "wires": [
            [
                "3"
            ]
        ]
    },
    {
        "id": "3",
        "type": "debug",
        "z": "1",
        "name": "",
        "active": true,
        "tosidebar": true,
        "console": false,
        "tostatus": false,
        "complete": "payload",
        "targetType": "msg",
        "x": 550,
        "y": 100,
        "wires": []
    }
]
Node Properties
Name: Optional name for the node.
License
This project is licensed under the ISC License.