Vision Language Models (VLMs) Are Now Available
We're excited to introduce Vision Language Model (VLM) support to our platform, bringing a new level of intelligence to your AI workflows.
What's the difference between an LLM and a VLM?
- Large Language Models (LLMs) are designed to understand, reason about, and generate text. They're ideal for tasks like answering questions, summarizing documents, writing content, and analyzing textual information.
- Vision Language Models (VLMs) build on those capabilities by understanding both images and text. They can interpret visual content, extract insights from diagrams, screenshots, charts, scanned documents, and photos, then combine that understanding with natural language reasoning.
What this means for you
With VLM technology now integrated into our platform, you can:
- Analyze images and documents alongside text
- Understand charts, diagrams, and visual reports
- Together with Bring Your Own Model feature build multimodal AI workflows using a single platform
- Deliver more accurate and context-aware AI experiences
This enhancement enables your applications to move beyond text-only interactions, unlocking new possibilities for document processing, visual analysis, and intelligent automation.
Need Help?
Have questions or need advice or assistance with configuration? Our support team is here to help.
New Page: Range Verifier
The Page Range Verifier validates whether a prediction originates from an allowed page range within a document.
If the predicted value is extracted from a page outside the configured range, the prediction is rejected.
