This paper is devoted to the automation of ophthalmologic image analysis obtained through optical coherence tomography angiography (OCT-A). The research of the retinal and choroidal vascular beds in vivo is widely used by the medical community to diagnose vascular and nonvascular pathologies. Examination of the retinal vasculature can reveal a wide range of conditions such as hypertension, diabetes mellitus, atherosclerosis, cardiovascular disease, and stroke. The paper describes a new tool for automating ophthalmological image analysis—an algorithmic and software package that allows for highly-accurate, autonomous differential diagnostics to separate normal and pathological vascular conditions based on OCT-A images, version 2.0. The new interface of this algorithmic and software complex is also considered in detail. The main tasks set and solved were: 1) redesigning the interface and visual elements of the entire complex using the Solara framework for Python; 2) setting up support for images obtained from various microscopes; and 3) a cloud-based architecture for the software complex. The paper provides examples of image analysis results demonstrating the potential of the system and directions for further research: it is planned to expand the range of supported image types, add new image analysis functionality, and exploring new features for more accurate diagnostics.