SovereignSearch parses, chunks, embeds, and indexes every enterprise document format — PDF, DOCX, PPTX, XLSX, HTML, Markdown, CSV, TXT — entirely on hardware you own. Zero API calls, zero telemetry, zero cloud dependency.
Six production-tested capabilities that power the pipeline — pulled straight from the service layer, not marketing copy.
Docling's trained layout models preserve reading order, multi-column text, and table structure — no more out-of-order fragments from naive PDF parsers.
parser_service.pyHybridChunker splits on the embedding model's own tokenizer. No chunk silently exceeds the 256-token window and gets truncated on its way into Qdrant.
chunker.pyTable chunks serialize as genuine pipe-delimited markdown — not flattened row/column triplets. The frontend renders actual tables from structural metadata.
chunker.pyEvery file is MD5-hashed before parsing. Unchanged files are skipped outright; changed files have stale vectors deleted before new ones are upserted.
vector_service.pyScanned pages fall back to the system Tesseract binary — no torch-based OCR weights to cache separately, no engine that assumes internet access.
parser_service.pyEvery stage catches and logs its own exceptions. One corrupted file in a 50,000-file corpus is recorded and skipped — it does not abort the run.
main.pyThe desktop client can only ask the API what it already indexed. The API is the only thing that touches Qdrant or the model weights. That's the entire security model.
Compiled desktop shell. Debounced search, IPC over Rust, ~5MB bundle. Zero direct access to data.
/health · /ingest · /query — parses, chunks, embeds, queries. API-key authenticated.
Cosine-similarity vector index. gRPC for bulk upsert, REST for health. Persisted in named Docker volumes.
This is a faithful recreation of the shipped desktop client — same layout, same result cards, same table rendering. No mockup, no smoke and mirrors.
| Segment | Q3 Guidance | YoY |
|---|---|---|
| Core Platform | $1.4B | +6.2% |
| Cloud Services | $0.7B | +11.8% |
| Enterprise Solutions | $0.4B | +9.4% |
From defense contractors to regulated financial institutions — SovereignSearch is designed for deployment in air-gapped, classified, and compliance-heavy environments.
The pipeline enforces a hard zero-egress policy. After model weights are cached, no network calls are made — not for telemetry, not for licensing checks, not for updates.
Build and cache on a networked machine once, then carry three things across the gap: the Docker images, the model cache, and your documents. Zero internet required.
Every ingestion is logged. Every query is recorded. File access is read-only by design. Audit trails are generated automatically for SOC 2, ISO 27001, and FedRAMP alignment.
Batch ingestion handles 50,000+ file corpora with hash-based change detection. Sub-50ms query latency even with millions of vectors. Resilient to corruption.
Docker Compose-based deployment with persistent volumes. Works on any Linux host, on-prem server, or edge device. No orchestration required.
All service endpoints require X-API-Key authentication. The API key is set via environment variable. No external identity provider needed — works fully offline.
No per-seat fees. No per-document pricing. No cloud egress charges — because there is no cloud. You buy a license, you own the software, you run it on your infrastructure.
Annual license. Volume discounts available for 50+ seat deployments. All plans include software updates during the license term.
Deploy on your hardware, under your network. No trials, no SaaS, no hidden fees — just software that respects your sovereignty. Purchase a license and own it forever.