Best Practices
Practical guidance for production Wolbarg usage.
Scope memories
Use stable agent ids and meaningful metadata keys (topic, source, collection).
Prefer metadata filters
Narrow recall with meta.* before increasing topK. Combine with hybrid search for exact token matches.
Peers on demand
Do not install pg / pdf-parse / mammoth / tesseract.js unless you need them. If you ingest those formats, peers are required.
Lifecycle
- Call
ready()at process start to fail fast - Always
close()on shutdown - One
Wolbarginstance per process / org is enough