0.2.0
This release includes Vector Embeddings! embeddingModels can now be configured in SETTINGS. Assuming it is configured and indexEmbeddings
is enabled, then embeddings will automatically be generated and indexed whenever a page changes.
These vector embeddings are used for similarity/semantic search by the new "AI: Search" command. They are also be used to provide additional RAG context to chats.
Please see https://ai.silverbullet.md/Configuration/Embedding%20Models/ for examples and configuration.
What's Changed
- Vector search and embeddings generation by @justyns in #37
- Enrich chat messages with RAG by searching our local embeddings by @justyns in #38
- Refactor: Re-organize providers, interfaces, and types by @justyns in #39
- Add try/catch to tests by @justyns in #40
- Fix bug causing silverbullet to break when aiSettings isn't configured at all by @justyns in #42
- Add option to generate summaries of each note and index them. by @justyns in #43
- Disable indexing on clients, index only on server by @justyns in #44
- Set index and search events to server only by @justyns in #45
Full Changelog: 0.1.0...0.2.0