SovrGPT Docs

Knowledge base (RAG)

RAG knowledge base in SovrGPT: upload your own documents and get answers with sources, strictly separated per organisation.

The knowledge base is your organisation's searchable document collection. Technically it is RAG (retrieval-augmented generation): before answering, SovrGPT searches your documents, hands matching passages to the model and cites them as sources. That keeps it verifiable where a statement comes from, for example in public administration, legal and compliance. No organisation sees another's knowledge.

Choosing knowledge sources per chat

You choose the source in the input area with the RAG: button:

ModeBehaviour
OffNo knowledge base, a normal chat.
Knowledge baseEnrich answers with your knowledge base.
Knowledge base onlyAnswer exclusively from the knowledge base, without world knowledge.
WebWeb search only, without the knowledge base.
Knowledge base + webCombine the knowledge base and web search.

The organisation sets a default mode, and every chat can change it. The web modes use Brave Search, a provider based in the USA. If such a mode is the default, web search is on in every chat without its own setting.

Managing documents

Under Einstellungen → Wissen (RAG) (settings → knowledge) you upload files (PDF, Word, Excel, text, Markdown), see the document list, delete individual documents and keep an eye on the quota. On upload, SovrGPT extracts the text, splits it into sections and stores them as vectors in our database in Frankfurt.

How the search works

  1. Hybrid search: keyword search (Postgres full text) and semantic search (pgvector) are merged.
  2. Reranking: a cross-encoder (bge-reranker-base) sorts the hits by relevance.
  3. Citing: the top passages go to the model, and the answer names where they came from.

If the search cannot run for technical reasons, SovrGPT says so openly and does not claim that your documents contain nothing relevant. In Knowledge base only mode you then get a request to try again rather than an answer from world knowledge. In the other modes the answer states that it was written without your sources. If only reranking fails, the hits arrive in the order of the hybrid search.

Embedding and reranking run on self-hosted models on rented GPU servers in EU data centres (and additionally in Iceland or Norway, EEA).

Separation between organisations

Every row carries the org_id of its organisation. Row-level security lets only members read; writing happens exclusively on the server, never directly from the browser.

Availability (plans)

FeaturePlan
Knowledge basePro and above (up to 200 documents, 500 MB); enterprise by agreement
Web search as a sourceall plans

Knowledge base vs. file attachment

The knowledge base is permanent and searchable in all of the organisation's chats. A file attachment applies only to that one conversation.

Related topics: Marketplace · Connecting your own systems · GDPR & compliance.

Knowledge base (RAG)