This Deep Learning Package (DLPK) integrates advanced vision-language models from OpenAI and Llama into ArcGIS Pro, enabling powerful visual analysis directly within your geospatial workflows. These models are known for their capabilities in natural language processing and visual understanding, supporting tasks such as image classification, captioning, visual question answering, and image reasoning.

By leveraging this DLPK, users can apply OpenAI’s and Llama’s large vision-language models to analyze both images and raster data within ArcGIS Pro. The package offers flexibility for performing tasks like visual question answering and image captioning, enhancing the interpretation of spatial data. This makes it a valuable tool for professionals in environmental science, urban planning, remote sensing, and other fields that rely on extracting insights from imagery.

Note: An internet connection is required when using OpenAI’s vision-language models, and data—including imagery—will be shared with OpenAI during processing. In contrast, the Llama Vision model runs entirely on your local machine, ensuring that your data remains private and never leaves your system. This model is currently not supported in ArcGIS Online.