Semantic document search

Find related passages in PDF or text by meaning.

Related tools
On-device sentence model

English semantic matching · all-MiniLM-L6-v2 · no account or document upload.

Setup includes the local model and PDF text engine. Checking download size… Embeddings stay in memory. Documents remain ephemeral unless you explicitly save a session.

Model and runtime licenses

Source document

Find a passage

Search up to 64,000 characters / 128 passages. Results are ranked by meaning; check the cited source text.

The English model reads at most 256 tokens per passage. Scores measure semantic closeness and are not confidence probabilities.

Checking local AI tools.

Model limits and browser support
  • English sentence embeddings, not a generative answer or factual-verification model. The model reads at most 256 tokens per passage.
  • Up to 128 source passages / 64,000 characters and an 800-character query, or two 800-character passages. Similarity scores are not confidence probabilities.
  • PDF search supports text-layer PDFs up to 25 pages / 8 MiB, requires the PDF packs and worker canvas support; scanned pages need OCR. TXT/Markdown require UTF-8.
  • Physical phones and real Safari remain unverified. Desktop WASM uses one thread. Offline reload requires service-worker support; Windows WebKit offline remains unverified.

No generated answers or summaries are produced by this model. Document chat and summary have separate quality gates.