Skip to content
All Work
AI Infrastructure

Private RAG Knowledge System

On-premise retrieval-augmented generation system for a professional services firm handling sensitive client documents.

OllamaLangChainPostgreSQL + pgvectorDockerReact

The Challenge

A legal-adjacent services firm needed internal AI search across a large body of client documents but couldn't use cloud AI tools due to data sensitivity and compliance constraints.

The Approach

Assessed infrastructure constraints. Designed a private architecture using local models and vector storage. Chose Ollama for model serving and pgvector for embeddings storage.

The Solution

Deployed a private RAG stack: Ollama running Mistral 7B, LangChain for document chunking and retrieval, PostgreSQL with pgvector for embeddings, and a clean React UI for staff queries. All running on their existing server infrastructure.

Architecture

A retrieval pipeline designed so documents, index, and model serving all stay inside the organization's own infrastructure.
Private infrastructure
Every stage below runs inside the client's own deployment boundary.
  1. Private Documents
    Internal client files
  2. Document Processing
    Chunking and ingestion via LangChain
  3. Embedding & Indexing
    Vector embeddings generated locally
  4. Vector Storage
    PostgreSQL + pgvector
  5. Retrieval
    Relevant passages selected for the query
  6. Local Model Serving
    Ollama
  7. Grounded Response
    Answer assembled from retrieved passages
  8. Staff Interface
    React query UI

Designed for private infrastructure: the retrieval and generation path does not depend on an external model provider.

Ready to build something
that matters?

Bring me one business problem. I typically respond within 24 hours.