Skip to content

How it works

Three steps. That's it.

No engineering needed. No configuration required.

1
Drop your documents

Drag and drop your PDFs, Word files, presentations. DEPOSIUM® reads, analyzes and structures them automatically. Even scanned documents (built-in OCR).

2
Ask your questions

In English, in French, like you'd talk to a colleague. "What's the maintenance procedure for the compressor?" — DEPOSIUM® searches across all your documents and answers with sources.

3
Discover the connections

DEPOSIUM® doesn't just search: it maps the links between your documents. Cross-references, contradictions, recurring themes — your knowledge takes shape.

From your files to your answers

YOUR DOCUMENTS
PDF, Word, MD
API/MCP connectors
DEPOSIUM®
Smart extraction
File storage
Workspaces
YOUR RESULTS
Sourced chat answers
MCP (Claude, OpenAI, Cursor…)

From ETL to ET(K)L

1
Extract

Your documents, regardless of the source (PDF, DOCX, databases, APIs)

2
Transform

Text extraction, OCR, intelligent chunking, cleaning

3
Knowledge

Enrichment at ingestion: knowledge graph, contextual ontology, structural analysis, temporality

4
Load

Indexing into a hybrid engine (BM25 + vector + graph) ready to be queried

Because we enrich at ingestion, every query is more precise. No costly post-processing, no hallucination from lack of context.

Under the hood: hybrid 5-signal search

Vector search alone loses precision as volume grows. DEPOSIUM® combines 5 independent mechanisms to maintain quality at scale.

Why standard RAG systems hallucinate — even with few documents

The problem isn't volume. Even with 10 documents, a standard RAG system can fabricate answers. The AI retrieves passages that are "close" to your question, but not necessarily the right ones — and generates a fluent answer regardless. The worst part: you can't tell the difference.

1
Vector search

Meaning-based semantic search (not just keywords) on a quantized vector index — compact (~8× lighter) and high-recall, even at scale.

2
BM25 text search

Exact keyword search. Finds precise references (part numbers, proper names, acronyms) that vector search may miss.

3
Knowledge graph

Traverses entity relationships to find indirectly related documents. Vector search never makes these connections.

4
RRF fusion

Evaluation via Reciprocal Rank Fusion, false positives neutralized.

5
Neural reranking

The final judge actually re-reads the question and each candidate document.

Hallucination rate by document volume

↓ Lower is better

30% 25% 20% 10% 5% 0% 1 10 100 1K 10K 100K 1M Documents Standard RAG * DEPOSIUM®
Error source Standard RAG * DEPOSIUM®
Wrong document retrieved 1 to 15% < 1% (5 signals + reranker)
Answer fabricated by the LLM 3 to 10% 0% measured (mandatory source citation)
Incomplete context (info spread across docs) 5 to 15% < 2% (knowledge graph)
Estimated overall hallucination rate 10 to 30% 0% measured on 800+ pages

* Standard RAG estimates based on industry benchmarks (RAGAS, faithfulness). DEPOSIUM®: measured on internal 800+ page benchmark.

Measured performance, not promises

Benchmark over 10,000 queries on the knowledge graph engine *, local and cloud versions.

2.15 ms
Response time
Local version — 76× faster than Neo4j
< 150 MB
Memory used
Local and cloud — 28× less than Neo4j
Stable
Same perf under load
No degradation, even at 10,000 queries
DEPOSIUM® Local 2.15 ms DEPOSIUM® Cloud 3.27 ms FalkorDB 12.8 ms Neo4j 164 ms Response time — ↓ Lower is better
DEPOSIUM® Local DEPOSIUM® Cloud FalkorDB Neo4j
Response time 2.15 ms 3.27 ms 12.8 ms 164 ms
Memory used 147 MB 136 MB 850 MB 4,200 MB
Throughput (req/s) 1,480 545 15,000 2,800

* The knowledge graph engine is one of DEPOSIUM®'s 5 hybrid search signals (BM25, semantic, graph, RRF fusion, reranking). These signals are combined to produce every chat answer. Benchmark on Intel i5-10310U, 16 GB RAM, Linux.

Tech stack

Compliant by design.

Layer What we use Why
Interface Modern web application Fast, works on any device
Analysis Knowledge graph Understands relationships between your documents
AI Models Open-source, from 250 MB to 120B Precise, auditable, lightweight
Security Role-based access control Fine-grained permissions for your team
Storage S3-compatible or local Your files stay where you decide
Integrations MCP server, REST API, CLI Plugs into your existing tools
Deployment Docker / Kubernetes European cloud, on-premise, or hybrid

Ready to unlock what your documents know?

Free trial, no credit card. Your first results in minutes.