AnythingLLM

release-v160

1 min read

Multimodal Support

  • Requires a multimodal model (e.g., local model, cloud-hosted like GPT-4o, or the built-in LLaVA-Llama3).
  • Drag-and-drop images directly into the chat UI for single-session use.
  • Drag-and-drop document files into the chat UI to upload and embed them permanently into the workspace.

Fixes & Updates

  • Updated model lists for Perplexity and TogetherAI.

Graph View