Basic

Easily Generate Text with AI in your app using 🌊 Floom.

Learning time 🕙: 2 minutes

Create Pipeline

Create a YAML file named 'text-generation.yaml' using your favorite editor.

kind: floom/pipeline/1.2

pipeline:
  name: text-generation

prompt:  
  template: 
    package: floom/prompt/template/default
    system: "Be polite and concise"

Deploy

Deploy the AI Pipeline with Floom CLI to ☁️ Floom Cloud or local 🐳 Floom Docker.

☁️ Floom Cloud

floom deploy text-generation.yaml

🐳 Docker

floom deploy -endpoint=<YOUR-FLOOM-ADDRESS> -f text-generation.yaml

Copy the deployed pipeline URI:

Deploying pipeline 'text-generation'...
Deployed to text-generation-28g4fj82.pl.floom.ai

Run

Run the pipeline from your app using Floom SDK.

Python

from floom import FloomClient

floom_client = FloomClient()

floom_client.run(
  pipeline="text-generation-28g4fj82.pl.floom.ai", 
  prompt="Your query here"
)

Node

import { FloomClient } from '../FloomClient';

const floomClient = new FloomClient();

const response = await floomClient.run(
  "text-generation-28g4fj82.pl.floom.ai",
  "Your query here",
);

.NET

var floomClient = new FloomClient();

var response = await floomClient.Run(
      pipeline: "text-generation-28g4fj82.pl.floom.ai",
      prompt: "Your query here"
);

Java

import ai.floom.FloomClient;

FloomClient floomClient = new FloomClient();

FloomResponse response = floomClient.run(
      "text-generation-28g4fj82.pl.floom.ai",
      "Your query here"
);

Golang

import (
    "fmt"
    "github.com/FloomAI/FloomSDK-Go"
)

floomClient := floom.NewFloomClient()

response, err := floomClient.Run(
    "text-generation-28g4fj82.pl.floom.ai", 
    "Your query here"
)

Rust

extern crate floom;

use floom::FloomClient;

let mut floom_client = FloomClient::new();

let response = floom_client.run(
    "text-generation-28g4fj82.pl.floom.ai",
    "Your query here",
);

Production Improvements

including Plugins: Caching, Cost Management, Prompt Validation and Response Validation executed on OpenAI GPT-3.5.