Getting Started with Ask Sage

In this section, we will guide users through the User Interface and the Prompt Settings of the Ask Sage Platform. Understanding these two sections is crucial to getting started with the platform and generating the best results for use case.

Table of contents
  1. User Interface (UI)
    1. Prompt Settings - A
    2. Prompt Window - B
      1. Prompt Templates
    3. Inference Window - C
    4. Chat History - D
    5. Dropdown Menu - E
  2. Prompt Hyperparameters
    1. Model
    2. Personality
    3. Temperature
    4. Live
    5. Datasets
  3. Account Settings
    1. Customization
    2. Tokens
  4. Summary

User Interface (UI)

The Ask Sage platform is designed to be user-friendly for organizations and its users to interact with GenAI models. The UI is divided into five main sections: Prompt Settings, Prompt Window, Inference Window, Chat History, and Dropdown Menu.

Prompt Settings - A

Here users can set the various hyperparameters/features for a prompt. This includes setting the model, persona, temperature, live feature, and datasets they want to reference for the prompt. Additionally, Ask Sage offers a set of Prompt Templates and Plugins that users.

Prompt Window - B

This is where users can enter a prompt, which is like a question or set of instructions they want the model to follow in order to generate a response.

The prompt window also has the ability to utilize the Attachment button which allows users to upload files (e.g., images, documents, etc.) to the platform. This is useful when users want to generate text based on the content of the file (This does not mean the attachment is being saved or stored on a Ask Sage Dataset).

Additionally, there is the Microphone button which allows users to generate text based on voice input. This is useful when users want to generate text based on voice input.

Prompt Templates

Ask Sage provides a set of Prompt Templates that users can utilize to generate text. These templates are designed to help users get started with the platform and generate text based on a specific use case.

There is a filter option that allows users to search for a group of prompt templates based on a specific persona.

Custom Prompt Templates

Additionally, users can also create their own prompt templates by selecting the Add Prompt Template option. This allows users to define unique prompt templates that are relevant to their organization/operations.

If you’re new, start with the prompt templates to understand the platform and generate text. Then, create your own custom templates based on these examples.

Inference Window - C

<img src="../../assets/images/inference-window.png" alt="" width="80%"style="border: 2px solid blue; border-radius: 15px;"/>

This is where the model-generated text will be displayed. You can also interact with the text by highlighting, copying, and pasting it into other applications.

Chat History - D

This is where you can view your various chat sessions and responses generated by the model.

Users can rename a chat session, share it with members from the same organization (given they have the proper need to know for the information) and delete it if they no longer need it

This is where you can access additional information on a user account, billing, and other settings (e.g., dark mode, help, and logout).


Prompt Hyperparameters

To optimize the results for your specific use case, we will begin by exploring the different hyperparameters available to users on Ask Sage. These hyperparameters can be adjusted for each prompt, allowing you to adjust the model and generate the best possible outcomes.



Model

Select the model you want to use for the prompt (i.e., GPT-4o, Claude 3 O., etc.). Because the Ask Sage Platform is agnostic you will have access to the latest models available today. By default, we have a GPT Auto mode which automatically selects the best model for the prompt you are utilizing.

Having the ability to choose the model you want to use for your use case is a powerful feature Ask Sage provides. If you don’t see the model you want to use or have a custom model, you can always reach out to the Ask Sage team to have it added.

Enterprises/Users can request more models to be added, but additional charges may apply. Contact the Ask Sage team for more information at support@asksage.ai.

Any model with a * next to it is name is ‘CUI’ compliant and can be used with CUI information. Also, Ask Sage UI will automatically display at the bottom of the prompt window if the model is CUI compliant as well.


Personality

Select the persona you want to use for the prompt via the personality option. By default, the persona is set to Ask Sage.

A persona is a set of characteristics that define the behavior and specific knowledge you want the model to focus on. It’s like choosing a character for the model to play. Thankfully Ask Sage provides an array of personas (~37 personas) to choose from and you can select the one that best fits your requirements.


Custom Persona

Users can also create their own custom persona by selecting the `Create a New Persona (advanced mode)` option. This allows users to define the characteristics and knowledge they want the GenAI model to focus on.

Fill in the required fields and click on the Submit button to create a custom persona.

Now you can select the custom persona you created from the list of personas available and utilize it within the platform.

Please make sure to follow our term and conditions when creating a custom persona. If a violation is detected, your account will be suspended.


Temperature

The temperature parameter is available via the advanced settings.

Adjust the temperature of the model. By default, the temperature is set to 0.0.

The temperature parameter controls the randomness of the model. Lower temperatures make the model more deterministic and higher temperatures make the model more random. Which means that the higher the temperature, the more creative the model will be, however, it may also produce less coherent results.

It is recommended to often just leave the temperature at the default value of 0.0, but of course, you can adjust it to your liking.


Live

Our live feature is also available in our advanced settings and has three options off, Live, and Live+. By default, the live feature is set to off.

The live feature is a powerful feature that allows users to generate a real-time web search and return up-to-date information in the inferences generated by the model.
  • Live: Will pull 10 results from Bing
  • Live+: Will pull the 10 results from Bing and also pull the top 2 web pages summaries using our Web crawler.

The live feature is a powerful feature that allows users to generate text based on the most up-to-date information available on the web. This is important since GenAI models are trained on data that is locked in time and may not have the most up-to-date information.


Datasets

Lastly, our dataset management is also available in our advanced settings. Select one, multiple or all the datasets you want the prompt to reference and generate text from.

The dataset feature is a powerful feature that allows users to generate text from a specific dataset. This is important since GenAI models are trained on data that is locked in time and may not have the most up-to-date information. By selecting a dataset, you can ensure that the model generates text based on the most up-to-date information you want to reference.

Users can also create their own datasets to use within the platform, but uniquely Ask Sage allows users to use their datasets with any model they choose to use thus not locking users into a specific model.

We recommend you only select the dataset(s) you need for the prompt to reference to reduce the time it takes to generate a response or just select the none option if you don’t need to reference any dataset.


Account Settings

Users can modify their account settings to either customize settings and also view their Token information.

Customization

Under the Customization tab, users can modify the following settings:

  • General: Users can select a theme for the platform and choose to display follow-up prompts for all inference responses or just the most recent one (boolean).
  • Chat Model: Users can select the view of the platform regarding 'modern chat' and 'advanced chat fields' in the user interface.
  • Prompt Settings: Users can define the default dataset, persona, and model to be set when they open the platform.
  • Security: Configure Multi-Factor Authentication, register a CAC Card, or manage API Keys.

Tokens

Under the Tokens tab, users can view their token information and manage their tokens.

  • Subscription: Users can see the subscription they are on.
  • Inference Tokens: Users can see the number of inference tokens they have used and have left.
  • Training Tokens: Users can see the number of training tokens they have used and have left.

Summary

Now that you have a better understanding of the User Interface and the Prompt Settings of the Ask Sage Platform, you are ready to start utilizing the platform and leveraging the power of GenAI!

Proceed to the next sections to learn more about Ask Sage! 🚀


Back to top

Copyright © 2024 Ask Sage Inc. All Rights Reserved.