Library
Organise documents in collections, share them with colleagues and control access with roles.
Local intelligence for your documents.
formadata reads, organises and answers your documents with AI. Everything runs on your own hardware, in your own building. Without your approval, your data never leaves it.
Contracts, manuals, expert reports, minutes: your documents hold your company's knowledge. AI finds and condenses it in seconds. Many companies still do without, because the well-known services send every page to data centres outside the EU.
Personal data stays under your control. Nothing is transferred to third countries. A cloud provider only processes data if you allow an external model from the EU.
Quotes, engineering documents and contracts are processed and stored on your servers. No provider trains models on your content.
You know where every file lives and which model has read it. That makes approval by the works council, data protection and IT easier.
Four steps from a pile of documents to an answer with sources. Every step runs on your hardware.
PDF documents go into the library, organised in collections.
Your serverDocling recognises text, tables and figures, on a Mac using its own GPU.
Your hardwareTable of contents, sections and summaries are built automatically. Passages are stored as vectors in Postgres.
Your databaseYou ask in your own words and get answers with sources. Tables appear exactly as in the original.
Your modelOrganise documents in collections, share them with colleagues and control access with roles.
Table of contents, sections and summaries for every document, long manuals included.
Ask across whole collections. The matching passages are retrieved, reranked and turned into an answer with sources.
Tables and figures from the sources appear unchanged next to the answer, so you can check the numbers directly.
Chain processing steps as blocks. Every result is versioned and shows which data and which model produced it.
A conversation with your documents that keeps its history and shows the sources for every answer.
formadata names the place in the document that each statement comes from and highlights the passage in the original.
How often does the HX-200's air filter need changing?
Every 2,000 operating hours, and at least once a year 1. In dusty environments, the interval is halved 2.
| Part | Interval | At the latest |
|---|---|---|
| Air filter | 2,000 h | yearly |
| Oil filter | 4,000 h | every 2 years |
| V-belt | 8,000 h | visual check yearly |
The air filter protects the compressor and bearings from particles. Replace the filter every 2,000 operating hours, and no later than after twelve months. Use original filters only (part number 4471-02).
A collection and a pipeline become an app with its own page: an assistant for the maintenance manuals, one for the contracts, one for the standards. Colleagues open the app and ask. The machinery behind it stays out of sight.
“Which oil goes into the compressor?”
“What notice period applies to supplier Berger?”
“Which IP rating does the outdoor housing need?”
The pipeline decides what an app may set: the collection, the number of passages, the answer depth. Everything else stays as it was built. An improvement to the pipeline reaches every app.
Every question runs as an ordinary run on your hardware. Histories belong to the person asking and are shared with the workspace only on request.
An app shows only what the person asking may see in the library. Whoever sets up an app needs edit rights on its collections.
Contracts name sites, surveys name parcels, minutes name construction sites. formadata finds the places mentioned in your documents, gives them coordinates and shows them on a map. Every point leads back to the passage.
The language model finds places, addresses and facilities in the text, even when they only appear in passing.
Coordinates come from a gazetteer on your server. No address leaves the building, not even for geocoding.
Map tiles are stored locally too. A click on a point opens the documents that mention the place, with the passage highlighted.
formadata runs on a Mac in the office or on a Linux server in your data centre. All models are open and run locally, the language models through Ollama.
Installed natively. Docling reads on the GPU, about 5 pages per second on an M1 Pro.
With Docker Compose, optionally with NVIDIA GPUs for larger models.
| Task | Model | Origin and license |
|---|---|---|
| Reading documents | Docling | IBM Research, MIT |
| Writing answers | Qwen3 or Mistral Small, depending on hardware | Alibaba or Mistral AI, both Apache 2.0 |
| Understanding page images | Qwen2.5-VL | Alibaba, Apache 2.0 |
| Embedding passages | bge-m3 | BAAI, MIT |
| Reranking results | bge-reranker-v2-m3 | BAAI, Apache 2.0 |
All weights live on your server. A local model downloads nothing and sends nothing, wherever it was developed. External models stay switched off. A workspace admin can allow a model from Mistral in the EU for that workspace.
Tell us which documents you have and what you would like to ask them. We will show you how formadata would run at your company.