- main.ts: process files sequentially (not Promise.all) to avoid concurrent
embedding requests hammering Ollama; batch size reduced to 1
- vectorization.ts: shorten embedding prompts from 1000 to 500 chars,
limit headings to 5, remove frontmatter from prompt to stay well within
embedding model context window
- Update vectorization and indexing-pipeline tests for new prompt format
This commit adds semantic caching functionality to speed up repeated queries and implements a complete indexing pipeline
for processing vault files. The changes include:
- Added semantic cache service using ChromaDB for storing and retrieving cached responses
- Implemented indexing pipeline with extraction, normalization, and vectorization steps
- Added cache configuration settings to the plugin
- Updated Ollama client to support cache integration
- Added tests for all new indexing components
- Extended vault indexer with indexing pipeline support
fegger