One search. Connected ideas.

RAG stands for retrieval-augmented generation. It retrieves relevant external information and provides that information to a model before asking for an answer. It connects language generation to a changing knowledge source without retraining the model.

Priority key

A vector database stores vectors and supports similarity queries with metadata. Vector search is the numerical operation; semantic search is the application goal of finding meaningfully related content. Existing databases can also add vector indexes, so you…

An AI agent is software that uses a model to choose actions toward a goal, observes results, and decides what to do next within application limits. A chatbot describes a conversational interface; it may or may not contain an agent. A workflow defines the…

LangChain is a framework ecosystem for assembling model-driven applications. Model wrappers, prompt templates, and composable operations make integration easier. A chain is a sequence of transformations or calls; it can be fixed and does not automatically…

A deterministic workflow follows explicitly coded transitions for given inputs and recorded external outcomes. It can call nondeterministic services, but its orchestration rules remain controlled. It is the natural extension of validation, transactions, and…

Artificial intelligence, or AI, is the broad field of making software perform tasks such as recognizing speech, finding patterns, or understanding language. Machine learning, or ML, learns patterns from examples instead of requiring a rule for every case.…

A large language model, or LLM, is a model trained on large amounts of data to process and generate language. It learns patterns in how text is arranged and can use those patterns for summarization, extraction, explanation, and tool selection. It does not…

Python is a dynamically typed language widely used by AI libraries. A list is an ordered collection, a dictionary maps keys to values, and a set stores unique hashable values. Python uses indentation to define code blocks rather than braces.

An embedding is a list of numbers representing useful features of content, often its meaning. That list is a vector; its number of entries is its dimension. Semantic similarity means closeness in meaning, such as “car accident” and “vehicle collision,” even…

RAG evaluation measures retrieval quality and answer quality independently and together. Fine-tuning changes model behavior through training; long context supplies a large body of content directly; traditional search returns evidence without generating an…

An agent loop alternates decision, action, and observation. ReAct is a pattern that combines deciding what information/action is needed with executing tools and observing results. “Reasoning” here means useful task planning and decision-making, not a…

RAG stands for retrieval-augmented generation. It retrieves relevant external information and provides that information to a model before asking for an answer. It connects language generation to a changing knowledge source without retraining the model.

Priority key

A vector database stores vectors and supports similarity queries with metadata. Vector search is the numerical operation; semantic search is the application goal of finding meaningfully related content. Existing databases can also add vector indexes, so you…

An AI agent is software that uses a model to choose actions toward a goal, observes results, and decides what to do next within application limits. A chatbot describes a conversational interface; it may or may not contain an agent. A workflow defines the…

LangChain is a framework ecosystem for assembling model-driven applications. Model wrappers, prompt templates, and composable operations make integration easier. A chain is a sequence of transformations or calls; it can be fixed and does not automatically…

A deterministic workflow follows explicitly coded transitions for given inputs and recorded external outcomes. It can call nondeterministic services, but its orchestration rules remain controlled. It is the natural extension of validation, transactions, and…

I remove any path that asks it to know account facts. An authorized tool returns canonical status; a template or model explains that result. I test missing claims, denied access, backend failure, and unsupported extra statements.

Artificial intelligence, or AI, is the broad field of making software perform tasks such as recognizing speech, finding patterns, or understanding language. Machine learning, or ML, learns patterns from examples instead of requiring a rule for every case.…

A large language model, or LLM, is a model trained on large amounts of data to process and generate language. It learns patterns in how text is arranged and can use those patterns for summarization, extraction, explanation, and tool selection. It does not…

Python is a dynamically typed language widely used by AI libraries. A list is an ordered collection, a dictionary maps keys to values, and a set stores unique hashable values. Python uses indentation to define code blocks rather than braces.

An embedding is a list of numbers representing useful features of content, often its meaning. That list is a vector; its number of entries is its dimension. Semantic similarity means closeness in meaning, such as “car accident” and “vehicle collision,” even…

RAG evaluation measures retrieval quality and answer quality independently and together. Fine-tuning changes model behavior through training; long context supplies a large body of content directly; traditional search returns evidence without generating an…

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module