Overview
The Corpus is Akita’s semantic search layer, backed by Qdrant (vector database, port 6333). It indexes content from multiple sources — books, RSS feeds, research dossiers, chapter summaries — and provides semantic search across all of them.
Search Tools
| Tool | Purpose |
|---|---|
corpus__search | Semantic search across the entire indexed corpus |
corpus__search_in_book | Search within a specific book title |
corpus__search_by_author | Filter search results by author |
corpus__search_by_tags | Filter by Calibre book tags (match any or all) |
corpus__search_book_summaries | Search within AI-generated chapter summaries |
Content Access
| Tool | Purpose |
|---|---|
corpus__get_chunk_context | Return a chunk with surrounding context (configurable window) |
corpus__get_file_chunks | List all chunks from a specific file path |
corpus__get_chapter_summary | Raw summary text for a chapter |
corpus__get_chapter_text | Chapter plaintext (from summary path or direct path) |
Indexing
corpus__reindex— re-index all or specific sourcescorpus__corpus_stats— collection counts, index health
Data Sources
Content flows into the corpus from:
- Calibre books — chapter text extracted from EPUBs
- Chapter summaries — AI-generated summaries of book chapters
- RSS feeds — fetched periodically, reports available via
get_rss_reports - Research dossiers — output of deep research (see Tracks)
MCP Tools
See MCP Tools Reference for the full list of corpus__* tools.