LLM application
An LLM application is software whose functionality incorporates a large language model to perform tasks, process inputs, or produce outputs.
Machine Learning Platform Engineering
An LLM application is a software system whose functionality uses a large language model to process inputs and produce outputs.
- How it is used
- Extends MLOps infrastructure with retrieval, prompt, evaluation, observability, cost, and safety capabilities for production generative workloads.
- How deep it goes
- Explains architecture, metadata, RAG flow, testing, monitoring, and governance, stopping short of implementation code in the supplied evidence.
- Examples
- Uses DakkaBot, company documentation, document ingestion, vector embeddings, semantic retrieval, prompt augmentation, and generated answers.
- What you can do after
- Build it from scratch as an observable RAG service with managed prompts, semantic tests, cost tracking, and multilayered safety controls.
Read how Machine Learning Platform Engineering explains LLM application →
AI Agents and Applications
An LLM application is software that provides a use-case-specific interface or workflow around a large language model.
- How it is used
- Defines bounded, use-case-specific workflows that turn requests and supporting context into LLM outputs for users or other systems.
- How deep it goes
- Explains application structure through summarization and two-phase Q&A workflows, then identifies prompts and chains as implementation components.
- Examples
- Uses REST-accessible summarization, document-based Q&A, web research summarization, and semantic SQL search as concrete applications.
- What you can do after
- Build it from scratch as a bounded research summarization workflow, then integrate its search and summarization steps with LCEL chains.
Read how AI Agents and Applications explains LLM application →
Related concepts
- promptuses · An input, typically containing instructions or context, supplied to an artificial-intelligence model to guide or elicit its output.
- language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- retrieval-augmented generationused by · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- monitoringuses · Monitoring is the ongoing observation and measurement of a system’s behavior, state, or operational signals to assess its condition and detect changes or problems.
- vector databaseuses · A vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.