Calling LLM APIs
Call language model APIs with structured prompts, timeouts, retries, and safe error handling.
Prompt Templates and Structured Output
Build prompt workflows that return parseable JSON, tool calls, or validated results.
RAG and Vector Search
Build retrieval-augmented generation workflows with chunking, embeddings, and source attribution.
Tool Calling Patterns
Design LLM tool calls with clear schemas, validation, and safe execution boundaries.
LLM Error Handling
Handle timeouts, malformed responses, refusals, and partial AI failures.