Chat Settings
Explanation of chat settings available in Impresiv AI
Chat Settings in Impresiv AI
In Impresiv AI, you can adjust various settings to manage how the bot interacts with users. Here’s an explanation of some important chat settings:
Max Token
This setting determines the maximum number of tokens (words or smaller units) that defines the maximum token count for the bot's response.
Example: If you set the max token to 100, the bot will only produce up to 100 tokens in one response. This helps control the length of the responses and overall token usage.
Max Conversations
This option limits the maximum number of conversations that can take place while interacting with the user.
Example: By setting max conversations to 10, the bot will understand the context of the previous 10 conversations. This helps maintain performance and prevents confusion in long conversations.
Temperature
This setting controls the variation or creativity in the bot's generated responses. The temperature value typically ranges from 0 to 1.
Example:
- A low value (e.g., 0.2) will generate more consistent and structured responses.
- A high value (e.g., 0.8) will generate more creative and varied responses. This is useful if you want the bot to respond in a more natural or free-flowing style.
Top P
Also known as nucleus sampling, this setting determines the percentage of probability used to select the response.
Example: If top_p is set to 0.9, the bot will consider the top 90% of possible outcomes to generate a response. This provides a balance between variation and relevance in the answers.
Input Image
This option allows the bot to receive images as input from users.
Example: Users can send an image for analysis or editing, and the bot can process the image based on the instructions provided.
Input Video
This feature allows the bot to receive videos as input.
Example: Users can send a video they want analyzed, and the bot can provide a response or information based on the video content.
Input Audio
This option allows the bot to receive audio inputs from users.
Example: Users can send a voice recording for processing, and the bot can respond with text or relevant information based on the received audio.
With these settings, you can control how the bot interacts and processes information from users. Adjust the settings as needed to improve the user experience.