Semantic Search in Your Files

This semantic search tool lets you ask questions of your own documents privately. Drop a folder of PDFs, Word files, notes, HTML or CSV, and search by meaning — “how many holidays do I get” finds “20 days of paid annual leave” — using a small embedding model that runs in your browser. Keyword search works instantly with no download. Results show the file, the passage and its score, and export as CSV.

Keyword vs meaning search

QueryKeyword findsMeaning also finds
holidays“holidays”“annual leave”
refund“refund”“money back”, “reimbursed”
password rules“password”“14 characters”, “two-factor”

When to use it

  1. Search policy and HR documents.
  2. Find clauses across contracts.
  3. Search research notes and papers.
  4. Search exported chats and emails.
  5. Find answers in course material.

How to Use

  1. Choose keyword or meaning search.
  2. Drop documents or a folder.
  3. Type a question.
  4. Read and export results.

Features

  1. Meaning search
  2. BM25 keyword search
  3. PDF, Word, text, HTML
  4. Multilingual model option
  5. CSV export
  6. Clear downloaded models

FAQs

What is semantic search?

Search that matches meaning rather than exact words, using vectors that place related phrases close together.

Which files can I search?

PDF, Word (.docx), text, Markdown, HTML, CSV, JSON, logs and subtitles.

Is my data stored?

No, the index lives in this browser tab and disappears when you close it.

Is anything uploaded?

No. Files and text are processed in your browser. Only the model itself is downloaded, once, when you ask for it.

Can I delete the downloaded model?

Yes. The Downloaded models panel lists what this tool stored and deletes it after a warning; you'd need to download it again to use it.

Technical Details

Files are read locally (PDF.js for PDFs, mammoth for Word, DOM parsing for HTML, plain text otherwise) and split into overlapping passages of about 600 characters. Keyword mode ranks passages with BM25 (k1 = 1.2, b = 0.75) over lower-cased, accent-stripped, lightly stemmed tokens. Meaning mode embeds every passage and the query with a sentence-transformer (all-MiniLM-L6-v2, or a multilingual MiniLM) through Transformers.js with mean pooling and normalisation, then ranks by cosine similarity blended 80/20 with the keyword score. The index exists only in the open tab.

Productivity Tools

Productivity Tools

  • Stopwatch
  • Pomodoro Timer
  • ATS CV Generator
  • Checklist & To-Do Maker
  • Countdown Timer
  • Mind Map Maker
  • Bank Statement to CSV
  • Invoice Generator