Skip to content
VDAI with VD

Service

RAG Applications

Retrieval systems with hybrid search, reranking and traceable answers.

Talk to me about this

What I build

Question-answering and research systems over your documents, tickets, contracts or regulations. Retrieval is hybrid and reranked, answers carry citations, and a verification layer checks that each claim is supported before the user sees it.

How I work

I measure retrieval before generation. A small gold set of questions with known source passages tells us whether chunking and search are working. Only then do I tune prompts. Every answer keeps a trace of what was retrieved and why.

When to call me

Your users ask questions that your search box cannot answer, or a first RAG prototype is confidently wrong too often to trust.

What you get

  • Ingestion pipeline with chunking, metadata and change detection
  • Hybrid retrieval (keyword plus vector) with reranking
  • Answer generation with citations and a verification gate
  • Evaluation set for retrieval quality and answer faithfulness

Selected work

Case studies for this service

Compliance-focused accounting technology startup (under NDA)

TargetTarget Reference Architecture

AI Research Platform for a Regulated Accounting Profession

End-to-end MVP architecture for cited, verified tax research answers: LangGraph agent, hybrid RAG, a claim verification gate and region-locked multi-tenant infrastructure.

Design targets

The 95% accuracy target, P50/P95 latency objectives, seven-day freshness target and eight-skill count are design objectives and reference-concept counts, not observed results.

95%

Accuracy target the architecture is built to

Zero

Target tolerance for fabricated citations in the proposed hard-fail gate

Read case study

Premium family connection platform (under NDA)

Production

Agentic Question Generation for a Family Connection App

A LangGraph agent with agentic RAG generates personalised daily storytelling prompts as strict JSON, served to a live mobile app through FastAPI on AWS.

Production outcomes

Production status reflects the live mobile integration and operational tracing; no numerical engagement lift is claimed.

Daily

Personalised prompts per member, fully automated

Stable JSON

Typed contract the mobile team integrated without friction

Read case study

Related work

Related projects

Adaptive RAG

Toggle-Driven Hybrid Retrieval With Skills

Self-Built ProjectDemonstrated

A self-hosted LangGraph and FastAPI RAG service for a regulated finance and legal practice. Vector search always runs; allowlisted web search is added only when the request toggles it on, never by an LLM router. Four self-reflection gates with hard-capped retry loops decide whether an answer ships. Slash-invocable skills run as isolated sub-agents over the same graph, and opt-in Langfuse tracing plus async DeepEval scoring observe every run without adding latency.

LangGraphFastAPIMilvus

Questions I get asked

Why not just use a bigger context window?

Cost, latency and precision. Retrieval puts the right few passages in front of the model; a huge context puts everything there and hopes. For regulated domains, citations also need to point at a specific source.

Which vector database do you recommend?

It depends on scale and hosting. I have shipped Weaviate with hybrid search and multi-tenant namespaces, and pgvector inside PostgreSQL when the data already lives there.

How do you stop hallucinated citations?

A verification step extracts each claim, checks it against the retrieved source with a small local model, and fails the answer if a citation does not hold.

Have a problem that looks like this?

Tell me about it. I reply within one working day with a first take and no sales pitch.

Book a callSend a message