caveauAI

caveauAI is Blue Note Logic's flagship document intelligence platform. It transforms unstructured document collections into queryable knowledge bases using large language models reached through our model gateway.

Documents, retrieval and embeddings run on servers Blue Note Logic operates, with EU or regional hosting available; answer generation goes through our model gateway, which routes to external model providers. The platform indexes documents into 768-dimension semantic embeddings, retrieves the most relevant passages, and generates answers with precise citations back to source material.

How CorpusAI Works

The platform follows a three-stage pipeline: ingest, embed, query. Documents are parsed and chunked into semantically meaningful segments. Each chunk is embedded into a 768-dimension vector space using models optimised for retrieval. When a user asks a question, the system retrieves the most relevant chunks, sends them to a language model through our model gateway, and returns an answer with page-level citations.

Architecture

• Embedding Pipeline: 768-dimension semantic vectors stored in Qdrant on servers Blue Note Logic operates
• Inference: routed through our model gateway (LiteLLM) to external model providers
• Networking: servers linked over a private network, with TLS on public endpoints
• Isolation: Per-tenant corpus isolation — every query is filtered by tenant, to its own documents and the shared corpora it subscribes to
• Storage: Documents stay on servers Blue Note Logic operates, with EU or regional hosting available

Use Cases

CorpusAI is deployed across legal research, regulatory compliance, healthcare documentation, financial analysis, and construction project management. Any organisation with thousands of documents and questions that need answers — not summaries, not chat, but verified, cited answers — is a CorpusAI customer.