node-redisai-js


RedisAI bindings for node_redis node-redis


This package allows node-redis (2.8+) to interface with the RedisAI module.

To use this module, you will need Redis 4.0 or higher and the RedisAI module installed.

Usage

The RedisAI commands will be mapped to javascript-friendly names (ai.tensorset becomes client.ai_tensorset).

``js
var
redis = require('redis'),
redisai = require('node-redisai-js');

redisai(redis);
`

Example

Running Models


Once a RedisAI Model key has been set with AI.MODELSET it can be run with any Tensor keys from the database as its input. The model's output, after it was executed, is stored in RedisAI Tensors as well.
Here is a quick example!

The inputs for the example are the tensors stored under the 'tA' and 'tB' keys. Once the model's run had finished, a new RedisAI Tensor key called 'tC' is created and stores the model's output.

`javascript
var redis = require('redis');
var redisai = require('node-redisai-js');
var fs = require('fs')
redisai(redis);

var client = redis.createClient();
var model_blob = fs.readFileSync('./examples/graph.pb');

client.ai_modelset(["mymodel", "TF", "CPU", "INPUTS", "a", "b", "OUTPUTS", "c", "BLOB", model_blob]);
client.ai_tensorset(["tA", "FLOAT", 2, "VALUES", 2, 3]);
client.ai_tensorset(["tB", "FLOAT", 2, "VALUES", 3, 5]);
client.ai_modelrun(["mymodel", "INPUTS", 'tA', 'tB', "OUTPUTS", 'tC']);
client.ai_tensorget(["tC", "VALUES"], function (err, res) {
console.log(res)
});

// Output should be
// [ '6', '15' ]
client.quit();
``