New Open Encoder Model Adds Multilingual Image-Text Search to RAG Pipelines
This story is from 2026-09-07. It is preserved in the archive; the latest stories are on the live feed.
H Company published NeoMME, an open-weight encoder model described as multimodal-native and multilingual, hosted on Hugging Face. The model is built to embed text and images jointly, and to handle multiple languages within a single encoder rather than requiring separate models per language or modal…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-09-07 22:41 · DEV Community — AI
New Open Encoder Model Adds Multilingual Image-Text Search to RAG Pipelines