/2 min
Why I don't use LangChain in production RAG
Frameworks are great for a demo. In production, the abstraction you can't see into costs more than it saves.
Tag
#llm
6 posts.
/3 min
When NOT to use RAG (RAG vs fine-tuning vs prompting)
RAG became the default reflex for every LLM problem. Often it's the wrong tool. A straight decision framework for RAG vs fine-tuning vs just prompting.
/4 min/reference
Self-RAG vs Corrective RAG (CRAG): Which Self-Correcting Pattern Should You Use?
CRAG fixes retrieval quality before generation; Self-RAG uses fine-tuned reflection tokens to critique its own output. Here's when to use each.
/4 min/reference
How to Get Reliable JSON From LLMs: JSON Mode vs Structured Outputs vs Constrained Decoding
Structured Outputs with grammar-constrained decoding is the most reliable way to get valid JSON from an LLM. Here's how the three mechanisms compare.
/3 min/reference
Prompt Caching Explained: How to Cut LLM Cost by up to 90% Without Losing Quality
Prompt caching reuses precomputed KV state for identical prompt prefixes, cutting cost up to 90% and latency up to 85% with no quality change.
/4 min/reference
LLM Fallback Strategies: Building Multi-Model Routing That Survives Outages and Rate Limits
Build a production LLM fallback strategy: a cost-ordered chain of models with health checks, backoff, and cross-provider routing.