AI assistants on your documents (RAG)
A RAG assistant answers your team’s questions using only your documents and shows where each answer comes from. It finds in seconds what used to take hours.
How your assistant works
Document indexing
PDFs, Word files, emails, procedures and archives are analysed and made searchable.
Answers with sources
Each answer links to the document and passage used, so you can check in one click.
Access rights respected
People only see the documents they can already open.
Hosting of your choice
On your servers, with a European host or in your cloud.
How a RAG assistant works
Prepare the documents
Your files are converted to text, cleaned and split into coherent passages.
Index the meaning
Each passage becomes a vector representing its meaning, stored in a dedicated database.
Retrieve the right passages
For each question, the system finds the closest passages and checks access rights.
Answer with sources
The model writes the answer from those passages only and shows the references.
RAG or fine-tuning: side by side
| Criterion | RAG assistant | Fine-tuning |
|---|---|---|
| Up-to-date knowledge | Yes, as soon as a document changes | No, retraining needed |
| Cites sources | Yes | No |
| Enforced style and format | Partly | Yes |
| Time to deploy | A few weeks | Longer: dataset and training |
| Best for | Procedures, contracts, archives | Specialised writing, classification |
Real-world examples
- A law firm that queries its case files in plain language.
- A manufacturer that finds a quality procedure with one question.
- An HR team that answers staff questions from the company handbook.
Frequently asked questions
What does RAG mean?
RAG stands for Retrieval-Augmented Generation: the AI first retrieves the relevant passages from your documents, then writes its answer from them.
Can the assistant make things up?
The risk is much lower, because it answers from your documents and cites them. When it finds nothing, it says so.
Further reading
Articles to read
RAG or fine-tuning: how to specialise AI for your business
RAG gives AI access to your documents; fine-tuning changes the model itself.
AI and the GDPR: using artificial intelligence without exposing your data
As soon as an AI tool processes personal data, the GDPR applies.
Choosing an AI tool without risking your data: a checklist
AI tools are multiplying and many teams adopt them without approval.
Official sources and references
Related services
AI app development
We build business software that uses AI to read, sort, summarise or draft for you.
AI agents and automation
An AI agent chains several actions for you: it reads an email, updates the CRM, prepares an invoice and schedules a follow-up.
Model fine-tuning
Fine-tuning specialises an open-source model in your field: your vocabulary, your style, your tasks.
Dataset creation
A model is only as good as its data.
Let’s talk about your project
A free first conversation, with no commitment, to see what would really help your business.