Diaflow Vision
Diaflow Vision allows you to analyse image at your leisure.
Last updated
Was this helpful?
Diaflow Vision allows you to analyse image at your leisure.
Last updated
Was this helpful?
What it does: The Diaflow Vision component analyzes images based on a prompt. This prompt guides the model to describe the image according to your specifications.
The Diaflow Vision component has the identifier of diaflow-vision-X, where X represents the instance number of the Diaflow Vision component.
When to use it? Use Diaflow Vision when you need to process images or documents that contain important data. For instance, if you have a scanned document (like a receipt or contract) and you want to extract the text or numbers from it, this node will help you do that quickly and efficiently.
Prompt
Describes how you want the model to respond. For example, you can specify the role, manner and rules that the model should adhere to. Also mention the component ID to connect the components.
Image source
Add an image to your prompt by identifying a trigger file in this configuration. Only support image formats such as .jpg, .png **If your file is PDF, please convert it to an image using the "PDF to image tool"
Max token
Refers to the maximum number of tokens (which can be words or pieces of words, depending on the tokenization method) that the model can process in a single input sequence.
Enable caching
This option determines whether the results of the component are cached. This means that on the next run of the Flow, Diaflow will utilize the previous computed component output, as long as the inputs have not changed.
Caching time
Only applicable if the "Enable Caching" option has been enabled. This parameter controls how long Diaflow will wait before automatically clearing the cache.
Here is a simple use case of the Diaflow Vision component, where the Diaflow Vision component is being used to generate a description of an image.
