LA
All projects
AI / MLResearch2026

No Transformer

Retrieval engine without transformer models

Role / Solo — research

No Transformer — Retrieval engine without transformer models
transformer models
0
pytest suite
Tested
local knowledge base
Offline

The problem

Transformer-based RAG is expensive to run and hard to debug. For narrow domains, classical retrieval can be cheaper and fully explainable.

Approach

  • Built modular retrieval engines with a shared interface so strategies can be swapped.
  • Kept a local knowledge base and scored answers without embedding models.
  • Covered the pipeline with pytest and kept the whole thing runnable offline.

Result

  • Working retrieval pipeline that runs without GPU or API cost.
  • Every answer step can be traced back to a document and a scoring rule.

Stack

  • Python
  • FastAPI
  • pytest
  • Custom engines