Smart Connections
An Obsidian community plugin that uses local embedding models to provide vault-wide semantic search and note relationship discovery, with support for integration with local LLM tools such as Ollama.
Timeline (last 90 days)
The Smart Connections plugin uses local embeddings (for example nomic-embed-text or mxbai-embed-large via Ollama) to achieve vault-level semantic search.
Smart Connections chunks the notes in the vault, computes and caches embeddings, converts the user's question into a vector when they ask, and uses cosine similarity to find the most relevant fragments to feed to the LLM.
Switching embedding models invalidates existing caches and requires reindexing.
Obsidian AI plugins such as Smart Connections and Copilot provide features including automatic summarization, semantic search, and tag recommendations.
All Facts (4)
The Smart Connections plugin uses local embeddings (for example nomic-embed-text or mxbai-embed-large via Ollama) to achieve vault-level semantic search.
50%UnverifiedSmart Connections chunks the notes in the vault, computes and caches embeddings, converts the user's question into a vector when they ask, and uses cosine similarity to find the most relevant fragments to feed to the LLM.
50%UnverifiedSwitching embedding models invalidates existing caches and requires reindexing.
50%UnverifiedObsidian AI plugins such as Smart Connections and Copilot provide features including automatic summarization, semantic search, and tag recommendations.
50%