VERMYN
All work
AI / MLDemo project

Internal Knowledge Retrieval

Question answering over an organisation's own documents, built so every answer cites the source it came from.

Sector
Professional services
Discipline
AI / ML
Technology
Python, OpenAI APIs, PostgreSQL, FastAPI, Docker

The problem

Internal knowledge is spread across documents, wikis and shared drives. Search returns filenames rather than answers, and a language model asked the question directly will answer fluently and sometimes wrongly, with nothing to check it against.

What we built

We built retrieval-augmented question answering over an organisation's own content. Documents are chunked with their structure preserved, retrieved by hybrid search, and answered only from retrieved context. Every answer carries citations, and the system declines rather than guesses when retrieval returns nothing relevant.

Architecture

How the system fits together.

  1. 01

    Ingest

    Documents parsed with headings and hierarchy preserved, then chunked so each passage keeps its context.

  2. 02

    Index

    Embeddings alongside keyword indexing, enabling hybrid retrieval over both meaning and exact terms.

  3. 03

    Retrieve

    Hybrid search with reranking and an explicit relevance floor below which nothing is returned.

  4. 04

    Answer

    Answers generated strictly from retrieved passages, with citations, and refusal when context is insufficient.

  5. 05

    Evaluate

    A fixed question set scored on retrieval quality and answer groundedness, re-run whenever the system changes.

Outcome

What the system delivers.

Capability delivered, stated plainly. We do not attach business metrics to this work that we are not in a position to verify.

  • Answers grounded in retrieved passages, each one cited back to its source document
  • An explicit refusal path when retrieval finds nothing relevant
  • A repeatable evaluation set, so changes can be measured rather than eyeballed
  • Access controls carried through retrieval, so results respect existing document permissions
  • Python
  • OpenAI APIs
  • PostgreSQL
  • FastAPI
  • Docker

More work

View all
  • Technical case study

    Data Engineering · Industrial / manufacturing

    Industrial Data Intelligence

    Machine telemetry arriving continuously from industrial equipment, turned into a consistent time-series store that engineers can query and chart.

    • Python
    • ETL
    • InfluxDB
    • Grafana
    View Case Study
  • Demo project

    AI / ML · Industrial / manufacturing

    Equipment Condition Modelling

    A worked baseline for condition monitoring: feature engineering over sensor history, an evaluated model, and a serving path.

    • Python
    • scikit-learn
    • MLflow
    • FastAPI
    View Case Study

Have a problem worth solving?

Tell us what you're trying to build, automate or improve. Let's explore what technology can do.