RAG failures are rarely solved by a larger model alone. The pipeline must be stable end to end.
A minimum viable RAG pipeline
- Raw sources → cleaning and structural chunking
- Embeddings → indexing
- Retrieval → candidate evidence
- Reranking → relevance convergence
- Generation → citation constraints
- Evaluation → traceable quality signals
If only one improvement can be funded, start with reranking plus evaluation. Better ranking reduces irrelevant evidence; evaluation tells you whether the change helped the actual task.
Evidence state: engineering synthesis. A reproducible comparison will be added in a later lab.