Real-world RAG project shows quality work and cloud costs

Permit IQ is a RAG system built with messy, inconsistent real data instead of clean test datasets. The goal was to learn how retrieval finds useful material and how a uses that material to answer questions.

The system is now hosted on . Even as a hobby project, it has already cost about $200, showing that running a production-style RAG system can become expensive quickly.

The next areas to improve are answer quality, evaluation methods, retrieval strategy, reranking, and chunking. Cost reduction is also a focus, including the option of models instead of relying only on cloud-hosted .

Key points

  • Permit IQ uses messy real data rather than clean benchmark data.
  • The system currently runs on .
  • The hobby project has already cost about $200.
  • Quality work is focused on evaluation, retrieval strategy, reranking, and chunking.
  • Cost work may include models instead of using only cloud-.
Read original