Servers by @mukundakatta

Structured-output enforcer: extract and validate JSON from messy LLM text.

Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.

Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.

Token-aware message truncation: fit a chat history into your model's context budget.

Inject, parse, and strip [N] citation markers in RAG outputs.

RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.