030103 lancedb fulltext
Multi-domain agent skills collection for AI coding agents (Claude, Cursor, Copilot, OpenCode, and more). Covers programming, biology, cooking, and future domains. Installable via npx skills add.
npx -y skills add natuleadan/skills --skill 030103-lancedb-fulltextAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
LanceDB full-text search — BM25 indexing, FTS querying, fuzzy search, phrase queries, field boosting, and boolean search.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.2 KB, as published. Nobody here has run it
Full-Text Search
Overview
Full-text search with LanceDB using BM25 indexing. Covers FTS index creation, query patterns, fuzzy search, and advanced filtering.
Quick Reference
FTS Index
table.create_fts_index("text_column", replace=True)
Basic Query
const results = await table.search("search terms", queryType="fts").toArray()
FTS Features
| Feature | API | Description |
|---|---|---|
| Phrase | "exact phrase" | Exact phrase matching |
| Fuzzy | term~1 | Levenshtein distance |
| Field boost | field:term^2 | Weighted field scoring |
| Boolean | Must/Should | AND/OR term combinations |
| Filtering | .filter(sql) | Metadata pre-filtering |
References
- FTS Index — Index creation, BM25 configuration, tokenization
- FTS Querying — Query patterns, phrase search, index usage
- FTS Advanced — Fuzzy, boosting, boolean, array fields, filtering