Vision
The Vision tool allows Notis to understand and interpret images that you share. Powered by advanced LLM models, Vision can analyze visual content and extract meaningful information from your images.
What is Vision?
Vision is Notis's image understanding capability that enables our AI to "see" and analyze the content of images you share. When you upload an image, the Vision tool processes it and can describe, analyze, or extract information from the visual content.
Key Features
Image Understanding
Vision can understand and describe the content of images, including:
- People, objects, and scenes
- Text visible in images
- Charts, graphs, and diagrams
- Screenshots
Information Extraction
Vision can extract structured information from images such as:
- Business cards (contact information)
- Receipts (date, vendor, items, amounts)
- Product labels
- Handwritten notes
Visual Analysis
Vision can analyze and provide insights on:
- Data visualizations
- Design elements
- Visual concepts
How to Use Vision
Simply send your images to Notis and instruct what to do with them.
Examples
“Extract information from this restaurant receipt, including the restaurant name, date, time, items purchased, and payment details."
“Digitize this business card information including name, title, company, contact details, and website.”
“Analyze this quarterly sales chart and provide a detailed breakdown of the numbers along with growth percentages between quarters.”
“What is this plant and how much should it be watered every week?”
In practice you don’t have to be specific - this is just to illlustrate the capabilities of Notis in term of data extraction.
Limitations
While Vision is a powerful tool, it does have some limitations:
No PDF support
Vision does not support PDF documents - Vision can only process image files (JPG, PNG, etc.). For PDF analysis, you would need to convert relevant pages to images first or use a different tool.