Image Upload — Unique AI Documentation

Image Upload

1 min read

Functionality

This module makes use of the capabilities of some LLM to answer questions from an uploaded image. This module utilizes the entirety of the conversation history (up to the model’s token limit). It also supports using a summary history instead if the correct tool definition is provided and the functionality is enabled from config.

Input

An image with a valid extension + user query. It’s helpful to trigger this module when specifying in the user query that you need to get information from the uploaded image.
Example: ”Please describe the content of the uploaded image.”

Output

Answer to the question based on the image and conversation history.

Reference in Code in AI Module Template

ImageUpload

Configuration settings

Default Configuration

{
    "languageModel": "AZURE_GPT_4o_2024_1120",
    "chatHistory": {
        "enabled": true,
        "maxMessages": 10,
        "useModelTokenLimit": true,
        "defaultTokenLimit": 4096,
        "percentOfMaxTokens": 0.5
    },
    "supportedExtensions": [
        ".jpg",
        ".jpe",
        ".jpeg",
        ".png",
        ".gif",
        ".bmp"
    ]
}

General parameters

| Parameter | Description | Type | Default | | languageMod | Used GPT model | string | AZURE_GPT_4o_2024_1120 | | chatHistory | Defines which part of history should be included in LLM call | object | See here | | supportedExtensions | List of supported image extensions. | list[string] | `[\