Llm Application Design

An LLM application combines a language model with product logic, data, tools, prompts, and user experience to solve a specific workflow.

RAG retrieves relevant external documents and adds them to model context so answers can use fresh or private knowledge.

Grounding ties model output to provided sources, records, or tool results, reducing hallucinations and making answers easier to verify.

Prompt injection is an attack where untrusted content tries to override instructions, reveal secrets, or force unintended actions.

Tool calling lets an LLM request structured actions such as database queries, web searches, calculations, or file edits instead of only producing text.

Narrow permissions limit damage from mistakes or prompt injection by exposing only the actions and data needed for the task.

An evaluation set is a collection of representative prompts, expected behavior, and scoring rules used to test an LLM app.

Context window management decides what history, documents, tool results, and instructions fit into the model's limited input space.

Chunking splits documents into smaller passages that can be indexed and retrieved effectively without losing too much meaning.

Embedding search converts text into vectors and finds semantically similar passages even when exact keywords differ.

Reranking reorders retrieved passages using a stronger relevance model so the most useful context appears first.

Structured output asks the model to return data in a predictable format such as JSON, making it easier to validate and consume.