Cannabis Strain Generator

Enter the flavors of the strain and the AI will generate a name and a description.

No time to walk through the tutorial? Test this application here.

Use Case

Cannabis strains are named after their medicinal or recreational effects, history, genetics, flavor profiles, or cohesive branding. This tutorial will explore how to build an AI text application that takes flavors of Cannabis strains as input and generates a strain name and description as output based on the above listed properties. The name and description produced by the AI can be used just for fun or as an assistant to help come up with new ideas.

This application comprises two prompts chained together as an Intelet, which is a workflow that takes the output from one prompt and feeds it into the input of the next prompt. The first prompt generates the name of the strain from the flavors, and the second prompt takes the flavors and strain name to create a description.

If you don’t have an account, create an account on the Mantium Platform to get started.

Prompt A

When you are ready to create your prompt, click AI Manager > Prompts > Add New Prompt, and fill out the following:

  • Name of Prompt: Cannabis Name Generator I
  • Description: Generates Name and Description

Tags and Intelets can be left blank.

For deploying your prompt publicly at the end of this tutorial, you can add a default security policy configured by Mantium. Click Add Security Policies under Security Policies and drag Default Policies from All Policies to Selected Policies. Click Done to save. You will know the policy has been applied when its name is visible under Security Policies.

Provider Settings

  • Provider: OpenAI
  • Endpoint: Completion
  • Engine: Davinci

Prompt Body

We have prepared a text sample (see below) for you to paste into the Prompt Text field. In addition, the Prompt contains examples of flavors and corresponding strain names.

Be sure to add a space after the : on the last line, as the model begins the completion after the space. Language models are sensitive to all characters, including spaces.

Flavors: vanilla, pepper, sweet.
Name: Wedding Cake
###
Flavors: mint, pungent, nutty.
Name: Gorilla Cookies
###
Flavors: cherry, berry, sweet.
Name: Cherry Punch
###
Flavors: ammonia, menthol, earthy.
Name: Sour Power OG
###
Flavors: lemon, pine, chemical
Name: Lemon OG
###
Flavors: 

Prompt Settings

  • Response Length: 30
  • Temperature: 0.9
  • Top P: 0.8
  • Stop Sequences: ###

Notes on Prompt Settings

Response Length controls the length of an output response. The response length is set to 25 tokens because the response is the strain's name, short and not lengthy.

Temperature controls “creativity” - higher temperatures will produce more creative outputs but are less likely to adhere to structure. A lower temperature is advised for a prompt that requires a well-defined response, as the model will choose words with a higher probability of occurrence.

Top P is another way to control "creativity" using a different probability method.

Stop sequences are another method of controlling output - they allow you to define any text sequences that force the model to stop. If you don't have a stop sequence, the model might generate a stream of the requested response length, or stop in the middle of a sentence.

We set the rest of the Advanced Settings to the default values

Test Prompt Text

With the example flavors below, you can test the output of the prompt (see image below). We suggest clicking Test Run multiple times and tweaking the Temperature and Top P values to test output consistency as needed. Once you are satisfied with the results, click Save.

tropical, pineapple, pear.

Prompt B

Following the same steps as above, we will create the second prompt. The information for the second prompt is as shown below.

  • Name of Prompt: Cannabis Name Generator II
  • Description: Generates Name and Description

Provider Settings

  • Provider: OpenAI
  • Endpoint: Completion
  • Engine: Davinci

Prompt Body

The prompt body contains the flavors, corresponding strain names, and description.

Flavors: Flowery, Pepper, Pungent.
Name: Dosidos
Text: Indica-dominant hybrid strain with qualities similar to OGKB. Aroma is pungent, sweet, and earthy with slight floral funkiness. Lean towards the sedative side.
###
Flavors: Vanilla, Butter, Sweet.
Name: Ice Cream Cake
Text: Indica strain - offers sedating effects that leave your mind and body completely relaxed. Features a creamy flavor profile with sweet hunts of vanilla and sugary dough.
###
Flavors: Sweet, Berry, Tree Fruit.
Name: Runtz.
Text: Is loved for its incredibly fruity flavor profile that smells just like a bag of the sugary candy we all know and love.
###
Flavors:

Prompt Settings

  • Response Length: 60
  • Temperature: 0.7
  • Top P: 1
  • Stop Sequences: ###

Add an Intelet

After creating Prompt A and Prompt B, we will build an Intelet. Click AI Manager > Intelets > Add an Intelet

Provide the identifying information below

  • Intelet Name: Cannabis Name Generator
  • Description: To generate names and description

Drag and Drop

To build out an Intelet, you will drag the prompts from the All Prompts section to the Selected Prompts area. Be sure to arrange the prompts in the proper order with Prompt A on top of Prompt B as shown in the image below.

One-Click Deploy

Mantium enables sharing your Prompts and Intelets using the One-Click Deploy feature. From the current interface(image above), we can deploy the Intelet by simply clicking on the Deploy button.

Deploy Intelet

  • Name: Cannabis Name Generator
  • Description: Enter the flavors of the strain and the AI will generate a name and a description.
  • Author Name: Your Name
  • ✅ Add Input Field
  • Public
  • Input Placeholder Text: flavors:
  • Note that you can add examples

Another way to deploy an intelet is to navigate to the Intelet drawer view. From your list of Intelets, click on the Cannabis Name Generator Intelet, and then click Deploy .

After deploying your prompt, you will have a unique URL that you can share so that others can interact with it. To interact with the Intelet, input the flavor of your choice, and the AI will generate a Name and Description. (See a test example below)

Similar Use Cases

Another example of a concept generator use case is Game Concept Generator. You can find the tutorial here to learn how to build this text application.


Did this page help you?