v0.6.0
Home GitHub

First Search

Register a database, start the daemon, drop a file into the inbox, and query it over the read-only HTTP API.

Register a database

kura add my_docs

This command:

  1. Collapses whitespace in the name into underscores.
  2. Creates ~/.config/kuradb/my_docs/inbox/.
  3. Creates ~/Kura_my_docs as a symlink to the inbox.
  4. Registers my_docs in ~/.config/kuradb/db.json.

The command fails when the name is already registered or ~/.config/kuradb/my_docs already exists. A database added while the daemon is running is not hot-loaded; restart KuraDB before querying it.

Start the daemon

kura

The foreground launcher starts a detached --daemon process and waits up to 10 seconds for the endpoint file. When ready, it prints a URL such as:

http://localhost:43127

The daemon loads registered databases, restores caches from SQLite, starts a watcher and an embedding loop for each loaded database, and binds the read-only HTTP API to 127.0.0.1. If the endpoint file does not appear in time, the launcher exits with an error that points at ~/.config/kuradb/daemon.log.

Index a file

cp document.md ~/Kura_my_docs/

The watcher polls every 10 seconds. Changed files are parsed and written to SQLite; the embedding scheduler polls every 5 seconds and processes at most 64 pending chunks per batch. Keyword search sees a chunk once it is written; semantic search sees it after it is embedded.

Read the selected endpoint and query both strategies:

BASE="$(cat ~/.config/kuradb/endpoint)"
curl "$BASE/api/search?db=my_docs&q=what+is+RAG&limit=5"

Use target=keyword or target=semantic to run only one strategy:

curl "$BASE/api/search?db=my_docs&q=vector+cache&target=semantic"

See Search API for every parameter and the response shape.

中文