AnythingLLM v1.16.0

v1.16.0Desktop

AnythingLLM v1.16.0

Added 13
  • Generate images via /img when a supported provider is set up
  • Support image attachments for edits, followups, or combination prompts in image generation
  • Drag entire folders into the file picker with hierarchy preserved in the upload panel
  • Drag and drop files into existing folders directly in the file picker
  • Toggle tools on and off during agentic chats without reloading or starting a new session
  • Add support for openai-compatible whisper API
Changed 5
  • Increase the username character limit to 64
  • File picker no longer requires typing https in the URL fetcher and assumes https when left out
  • Lazy-load folders for improved performance with thousands of documents in a folder
  • Update default fallback models for OpenAI and Anthropic
  • Give Downloaded Models its own optgroup in Workspace Model Selector
Fixed 3
  • Aborting a response now fully kills the inference to prevent ghost inference continuing mid-stream
  • Disable temperature for claude-sonnet-5 model
  • Stream Anthropic non-streaming chat completions for REST API workspace chat
Removed 1
  • Remove workspace profile picture feature
Notable Changes
Image Generation

Now you can generate images via /img when a supported provider is set up.

This flow also allows image attachments for edits, followups, or combination prompts if your provider supports image editing.

Ability for an agent-tool to generate images is coming next update.

Better File Picker UX

Now in the file picker you can drag entire folders and their hierarchy will be preserved in the upload panel. This will only import the top level files in the folder — it will be deep and recursive in a later update.

You can also now drag and drop a file into an existing folder directly without needing to move it.

Lastly, you no longer need to type https in the URL fetcher - it will just assume https when left out.

We also made some large performance improvements, like lazy-loading of folders, for those with thousands of documents in a folder.

Tool Toggle Mid-Session

Now, during agentic chats you can freely toggle tools on/off at will without needing to reload or start a new session. Only tools that have been configured (if configuration is required) are available.

Stop Generation

A large improvement is now that aborting a response actually fully kills the inference as well so that ghost inference does not continue when no longer wanted mid-stream.

All Changes
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.15.0...v1.16.0

View original

Upgraded? How did it go?

Discussion