Models Overview
Lazarus offers various LLMs. To gain access to our models please reach out to the sales team at Lazarus AI.
RikAI
RikAI2 combines LLM and extractive AI technologies to understand and contextualize documents. Users can upload documents or images and RikAI2 will analyze them and respond to natural language prompts regarding their contents.
We also have variations of the RikAI2 API available.
- RikAI2-Extract extracts data from a document according to a specific structure defined by the user.
- RikY2 is a lightweight, flexible version of RikAI2, which has document understanding and sequential prompting capabilities.
Forms
Forms provides the ability to quickly and accurately extract key-value pairs from any document without targeted training. Specialized variations excel for specific data such as:
OCR
Optical Character Recognition (OCR) refers to the process of converting an image or PDF of a text document into a string of text. Lazarus can perform OCR across a wide range of languages, handle handwritten text, and return a text string that maintains the ‘read order’ of the original document.
OCR can be used by our LLMs to answer questions about the contents of documents.
VKG
Lazarus' Vector Knowledge Graph, used for accessing and storing data, is combined with RikY-Citation to allow natural language conversations about the information.
VKGs deeply embed knowledge into AI, making it readily usable in automated processes. They outperform alternatives like retrieval-augmented generation (RAG) while remaining easy to expand and update over time.