Limitations (v0.2)

Honest boundaries of Wolbarg 0.2 — peers, PDF quality, SQLite, and Postgres.

Maturity

Core remember / recall (semantic + hybrid + metadata filters) on SQLite and PostgreSQL is the most battle-tested path. Document ingest, OCR/vision, and LLM compression are supported but depend on optional packages and external APIs.

Ingest dependencies (required)

npm install pdf-parse@1.1.4   # PDF
npm install mammoth           # DOCX
npm install tesseract.js      # OCR
npm install pg                # PostgreSQL

.txt / .md / .csv / .json — built-in
.pdf — pdf-parse required; text-layer only unless OCR/vision on images
.docx — mammoth required
images — configure ocr and/or vision

PDF extraction

Scan / camera PDFs with no text layer yield empty extract
Prefer simple text PDFs or pin pdf-parse@1.1.4

SQLite

Uses Node node:sqlite (experimental) — Node 22.5+
Hybrid BM25 uses FTS5 when available

PostgreSQL

Requires pg
pgvector optional; otherwise BYTEA + in-process cosine

Optional providers

compress() needs llm
hybrid: true without keywordSearch falls back to semantic-only
rerank: true without a reranker skips gracefully

Not in v0.2

No hosted cloud control plane
No built-in agent framework / chat UI
No Atlas Search / dedicated vector DB product integration

What's New in 0.2

Highlights of the Wolbarg 0.2 modular provider rewrite and 0.2.1 production hardening.

Best Practices

Practical guidance for production Wolbarg usage.

On this page

Maturity Ingest dependencies (required)PDF extraction SQLite PostgreSQL Optional providers Not in v0.2 Related pages