llm-tool-schema-design verified

Design tool/function schemas LLMs actually call correctly — naming, descriptions, JSON-Schema params, enums, and error surfaces.

onnx-runtime-inference verified

Optimize local model inference with ONNX Runtime — execution providers, graph optimization, quantization, IO binding, and session reuse.

vllm-model-serving verified

Serve open-weight LLMs in production with vLLM — continuous batching, PagedAttention, memory/KV-cache tuning, and OpenAI-compatible API.

embedding-model-selection verified

Choose the right embedding model for RAG — MTEB scores, dimensions vs cost/size, max context, and self-host vs API tradeoffs.

function-calling-best-practices verified

Design robust LLM function/tool calling — schemas, constrained outputs, retry, and validation so agents call tools correctly the first time.

python-context-managers verified

Write correct context managers in Python — __enter__/__exit__, contextlib, and the resource-safety pitfalls that leak file handles and locks.

prompt-injection-defense verified

Defend LLM applications against prompt injection — input/output filtering, sandboxing tools, and separation of instructions from data.

sql-query-performance verified

Diagnose and fix slow SQL — EXPLAIN plans, index design, query rewrites, and the pitfalls of premature optimization.

structured-output-json-schema verified

Get valid, schema-conformant JSON out of LLMs — JSON schema prompting, constrained decoding, repair, and validation loops.

token-cost-optimization verified

Cut LLM API costs — prompt compression, caching, model routing, batching, and streaming without hurting quality.