Every document, instantly searchable.
Mia Documents is the search layer over our whole document archive — contracts, invoices, statements, letters and scans across every entity. Drop a file on the machine and it's automatically read, summarised, structured and indexed. Then you just… search.
Drop a file in. Find it forever.
There's nothing to upload by hand and no folders to organise. The pipeline does the filing for you, and the web interface gives everyone one place to look.
1. Drop files on the machine
Copy scans, PDFs and exported documents into the intake folder on the data PC. No naming rules, no manual tagging — just drop them in.
2. Parsed & structured
Each file is read end-to-end: the full text is extracted, then a summary, document type, date, counterparty, amounts, people and tags are pulled out automatically.
3. Loaded into the database
The extracted text and structured fields are written to a secure Azure SQL database and added to a full-text index — ready to be searched the moment it lands.
4. Search from anywhere
Sign in to this site and search by keyword or plain English, then narrow by entity, document type, date range, counterparty or amount. Results come back ranked in milliseconds.
Search that understands your documents.
Full-text, ranked
Every word of every document is indexed. Matches are ranked by relevance across the body, summary, filename, counterparty and tags.
Keyword or natural language
Type precise terms, or ask in plain English. A natural-language mode finds documents even when you don't know the exact words used.
Structured filters
Combine free-text search with filters on entity, document type, date range, counterparty and amount to zero in on exactly what you need.
Private by default
The archive is only visible to signed-in members of the team, using the same accounts as the rest of the Mia platform.