Transformer architecture

As explained in AI-Powered Search

A transformer is a neural-network architecture that models relationships among sequence elements using attention and can encode and decode representations.

A transformer is a deep neural-network architecture used to represent meaning in context. In search, its encoder can turn queries and documents into dense numerical vectors called embeddings. Comparing those vectors makes it possible to retrieve related content even when the words differ. section 13.3.1 section 13.4

The meaning of a word depends on its surroundings. A transformer uses attention to interpret each token in relation to other tokens in the input and relationships learned during training. It can encode that contextual meaning as vectors; a decoder can turn vector representations back into text. Search need not use both parts: an encoder alone can supply embeddings for retrieval. section 2.5.2 section 13.3.1

Context changes the query

“What is the difference between a capital and capitol?” calls for a different interpretation of capital than “What is the difference between a capital and lowercase word?” A context-sensitive model can distinguish the questions rather than treating capital as a fixed synonym or meaning. section 1.3.4 section 2.5.2

A transformer-based autocomplete or semantic-search pipeline can follow these steps:

• Pass corpus text through a transformer encoder and index the resulting embeddings. section 13.4
• Encode an incoming query with the transformer, then retrieve the k-nearest indexed vectors using a similarity measure. section 13.4
• Use the retrieved content to recommend related autocomplete terms or rank matching documents. section 13.4

Figure 13.5 A conceptual architecture for end-to-end search using Transformer-encoded vectors

The end-to-end architecture diagram connects the content source, transformer-generated vectors, nearest-neighbor index, and query-time search. section 13.4

Training a transformer from scratch demands substantial computing power, time, and potentially large amounts of GPU memory. Pretrained models offer a practical starting point. Contextual embeddings also do not replace every search signal: when a query remains unclear, keyword search and domain understanding can provide useful fallbacks. section 13.3.2 section 2.5.2

How AI-Powered Search covers it

How deep it goes

Explains attention, encoding, decoding, and a query-to-index retrieval pipeline without specifying model training internals.

Examples

Uses contrasting capital queries, English–Armenian greetings, and a transformer-encoded autocomplete pipeline.

What it assumes

Assumes some Python knowledge for practical model use while explaining embeddings and the encoder–decoder distinction.

What you can do after

Apply it via a pretrained transformer to encode content and queries for nearest-neighbor search.

How it connects

Connects attention and embeddings to dense vector search, nearest-neighbor retrieval, autocomplete, and question answering.

liveBookmanning.com

Read AI-Powered Search on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Learn Generative AI with PyTorchThe internal design and structural organization of a Transformer model built around decoder blocks or self-attention components.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA transformer is a neural network architecture that uses attention mechanisms to process sequences and model relationships among their elements.
• 

  liveBookmanning.com
  Sutskever's ListA Transformer is a neural network architecture based primarily on attention mechanisms for modeling relationships among sequence elements.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA neural-network architecture based on attention mechanisms, used here as the core architecture for large language models.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)A transformer architecture is a neural-network architecture that uses attention mechanisms to process relationships among elements in a sequence or other structured input.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA Transformer is a neural-network architecture designed to process sets or sequences using attention-based contextual representations.
• 

  liveBookmanning.com
  How Large Language Models WorkA transformer is a neural-network architecture that uses attention mechanisms to process relationships among elements in a sequence.
• 

  liveBookmanning.com
  Transformers in ActionA transformer is a neural network architecture that processes sequential and other structured data using attention mechanisms.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA neural network architecture for sequence modeling and content understanding based on attention rather than recurrence or convolution.
• 

  liveBookmanning.com
  LLMs in ProductionA transformer architecture is a neural-network architecture that models sequence relationships primarily through attention rather than recurrence or convolution.
• 

  liveBookmanning.com
  Grokking AI ApplicationsA transformer is a neural-network architecture for sequential data that uses attention to relate elements of an input sequence.
• 

  liveBookmanning.com
  The AI Pocket BookA neural network architecture that contextualizes each token using surrounding tokens rather than compressing the whole prompt into one summary vector.
• 

  liveBookmanning.com
  Time Series Forecasting Using Foundation ModelsA neural-network architecture built from stacked attention and feed-forward processing components, typically organized into encoder and decoder parts.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthA transformer model is a neural network architecture that uses attention-based mechanisms to model contextual relationships in structured sequences or other data.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA sequence model built from positional encoding and multiheaded attention, used here as the standard original design for NLP and other tasks.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionThe Transformer is a neural-network architecture based primarily on attention mechanisms for processing sequences and modeling context.
• 

  liveBookmanning.com
  Hugging Face in ActionThe Transformer architecture is a neural-network architecture based on attention mechanisms for processing sequences and other structured inputs.
• 

  liveBookmanning.com
  Domain-Specific Small Language ModelsA neural network architecture for sequence modeling built around self-attention and parallel processing, underlying both large and small language models.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionA transformer is a neural-network architecture for sequence modeling that uses attention, especially self-attention, rather than recurrence.
• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsA transformer model is a neural-network architecture that uses attention mechanisms to model contextual relationships in sequence data.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)a neural network architecture based on self-attention mechanisms that enables processing of sequential data and underpins many large language models.
• 

  liveBookmanning.com
  Build a Website with ChatGPTA transformer is a neural-network architecture that processes sequences using attention mechanisms to model relationships among their components.
• 

  liveBookmanning.com
  Data Analysis with LLMsThe Transformer is a neural-network architecture designed to model relationships in sequences, especially sequences with variable-length inputs or outputs.
• 

  liveBookmanning.com
  Generative AI in ActionThe Transformer architecture is a neural-network architecture based primarily on attention mechanisms for processing sequences.
• 

  liveBookmanning.com
  Coding with AIA Transformer is a neural-network architecture that processes sequence elements using attention and can process them in parallel.
• 

  liveBookmanning.com
  Optimization Algorithms: AI techniques for design, planning, and control problemsA transformer architecture is a neural-network architecture that processes sequences primarily through attention mechanisms rather than recurrence.
• 

  liveBookmanning.com
  Essential GraphRAGA transformer architecture is a neural-network architecture that processes sequences using attention-based representations and supports efficient language modeling.

Compare how 28 books explain transformer architecture →

Related concepts

• attentionuses · Attention is a neural-network mechanism that computes input-dependent weights over elements and uses them to combine information when forming representations or outputs.
• encoderhas part · An encoder is a component that transforms input data into an encoded representation for subsequent processing, reconstruction, comparison, or transmission.
• decodehas part · Decoding is the process of transforming an encoded or internal representation into an interpretable or target-form output.
• Vision Transformerincludes · A Vision Transformer is a Transformer-based neural-network architecture that processes images as sequences of tokenized regions using attention.
• model architecturekind of · Model architecture is the structural organization of a computational system’s components, relationships, and operations, defining how it processes information or carries out behavior.
• GPT-2includes · GPT-2 is a family of autoregressive, decoder-only Transformer language models developed by OpenAI that generate text by predicting successive tokens from preceding context.

This explainer was generated by Manning's knowledge graph from the text of AI-Powered Search. The section links point to the parts of the book it draws on.