Create Your First Prompt With Co:here

For an explanation of terms, check out the glossary.

Getting Started

If you do not already have an account, register on the Mantium platform.
In order to create prompts with Co:here as a provider, you must add your Co:here API Key into the Mantium platform. If you don’t have an Co:here API key, click here to learn how to obtain one.
Once you are logged into your Mantium account, Navigate to Integrations > AI Providers, then paste your API key into the Co:here form.

Use Case

To demonstrate the summarization capabilities of a large language model, we will be building a prompt that summarizes a complex paragraph about Jupiter into a simpler, plain-language explanation.

Prompt Creation

When you are ready to create your prompt, click AI Manager > Prompts > Add New Prompt.

Then, fill out the following:

Name of Prompt: Summarize a Paragraph
Description: Summarize a complex paragraph using Co:here Compose-Generate.

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: Co:here
Endpoint: Completion

Model Settings

Model: Large

Prompt Body

Prompt Line

Jupiter is the fifth planet from the Sun and the largest in the Solar System. It is a gas giant with a mass one-thousandth that of the Sun, but two-and-a-half times that of all the other planets in the Solar System combined. Jupiter is one of the brightest objects visible to the naked eye in the night sky, and has been known to ancient civilizations since before recorded history. It is named after the Roman god Jupiter. When viewed from Earth, Jupiter can be bright enough for its reflected light to cast visible shadows, and is on average the third-brightest natural object in the night sky after the Moon and Venus.

In summary,

Prompt Settings

Basic Settings

Max Tokens: 55
Temperature: 0
Return Likelihoods: None
P: 1

All other settings can be left blank for now.

Test Prompt

After completing the above, click Test Run to see the response in the Results field! Feel free to click Test Run multiple times - due to the stochastic nature of natural language models, it is possible that you may receive a different result the next time you run the prompt. Do note that each time, however, the model will be summarizing the same text from the prompt body.

Click Save when you are ready to save your prompt.

One-Click Deploy

Mantium enables sharing your prompt using the One-Click Deploy feature, located in each prompt's drawer view. From your list of prompts, click on the Simplify and Summarize prompt, then click Deploy.

Then, add the following configuration settings:

Name: Summarize a Paragraph
Description: Summarize a complex paragraph about Jupiter using Co:here Compose-Generate.
Author: Your Name
Add Input Field - leave unchecked
Public
Live
✅ I have followed my provider's go live requirements

Deploying a prompt will create a single-page application with a unique URL that can be shared if the prompt is deployed as Public.

To interact with this prompt, simply click Execute in the deployed prompt - each time, the model will create a summarized explanation of the prompt text from above. Creating an interactive Completion prompt requires creating a pattern of text for the model to follow - learn how in the Game Concept Generator tutorial!

To test out a pre-configured version of this prompt, click here!