Skip to content

9.7.0

Choose a tag to compare

View all tags
@github-actions github-actions released this 05 Jul 17:42
· 51 commits to main since this release
9.7.0
155f947
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

9.7 Update settings to Obsidian v1.13

  • Add settings search compatibility for Obsidian v1.13+ users. Plugin settings are now indexed and searchable in Obsidian's global settings search. The existing settings tab UI is preserved for users on older versions. (Issue #595.)
  • Display summary values (model name, provider status, shard info) and warning indicators on settings page entries for Obsidian v1.13.1+, making it easier to see current configuration at a glance. (Issue #595)
  • Add configurable "Token estimation ratio" setting (Advanced > Performance) so users with non-English (CJK) or code-heavy vaults can fine-tune character-to-token budgeting. Previously hardcoded at 4 chars/token. (Issue #386.)
  • Note that you may need to rebuild the index after upgrade. You can find the button for this at the bottom of the Explorer tab in the plugin settings.
  • Fix unnecessary re-embedding of indexed notes on every plugin restart.

Recent improvements

9.6 Upgrade to v4 Transformers.js for better GPU support

We now better support local GPU for embeddings via Transformers.js. On my development system I achieve 50--60% GPU utilization. This also reduces the plugin size, shrinking main.js by over 12%.

9.5 Support Voyage AI and Gemini 2 embedding models

This release includes support for Voyage AI as an embedding provider. This is a key step towards supporting Claude and others who do not bundle an embedding model with their main reasoning models. We now support:

  • Local embeddings, via Transformers.js and Ollama.
  • Cloud embeddings, via Gemini, Voyage AI, and Ollama.

9.3 Ollama custom headers

This release focuses on enhancing connectivity for local AI environments and modernising our core development foundations. We've introduced custom headers for Ollama, giving users greater control over their private infrastructure.

9.2 Vault Hygiene and Stability

This release focuses on vault organisation and system stability. As your knowledge base grows, it naturally accumulates duplicate ideas and abandoned notes. We have expanded the Gardener to detect and resolve these issues automatically. Alongside these new capabilities, we have fixed memory leaks and implemented important security updates to the Model Context Protocol (MCP) clients.

9.1 The Gardener's Evolution

Vault Intelligence is a different AI plugin for Obsidian. It transforms your vault into a dynamic, self-maintaining knowledge system. It goes beyond simple Q&A by introducing agents that maintain your vault's structure, retrieve information based on your explicit connections, and ground your knowledge in the real world.

With 9.1, we are doubling down on our core differentiator: The Gardener.

This release introduces significant optimizations for vault hygiene, respects how you physically organise your data, and deepens our native external search grounding.

9.0 The Local AI & Extensibility Update

We've introduced full, production-ready support for local AI via Ollama, allowing you to keep your data entirely on your machine. We've also integrated the Model Context Protocol (MCP), so the agent can safely interact with external databases, APIs, and local services. Finally, we've rebuilt the chat interface for speed and stability.

mascot-8

Assets 5
Loading