Embedding

As explained in Data Storytelling with Altair and AI

An embedding is a numerical vector representation that captures semantic or structural properties of an object such as text, enabling comparison and computation in a continuous vector space.

How Data Storytelling with Altair and AI covers it

How deep it goes

Defines numerical representations and demonstrates conversion, storage, indexing, and retrieval without explaining vector-generation internals.

Examples

Uses an HTML product description, overlapping text chunks, a Chroma collection, and a SmartX 2023 retrieval query.

What it assumes

Assumes textual data and a configured OpenAI API key for the demonstrated embedding and retrieval workflow.

What you can do after

Apply embeddings via LangChain, OpenAIEmbeddings, and Chroma to build a searchable retrieval pipeline.

How it connects

Connects embeddings to text chunking, vector databases, retrieval-augmented generation, and prompt templates.

liveBookmanning.com

Read Data Storytelling with Altair and AI on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA vector representation is a numerical vector that encodes the properties or meaning of a text, statement, word, or document.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)An embedding is a numerical vector representation of an input or discrete item in a learned feature space.
• 

  liveBookmanning.com
  AI-Powered SearchA vector representation is a data structure or encoding used to store and work with the components of a vector.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningAn ordered mathematical object representing a point or direction in a coordinate space.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionA node embedding is a numerical vector representation of a graph node that captures information about the node and its graph context.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionAn ordered numeric representation used here to encode source tokens and target tokens for attention computations.
• 

  liveBookmanning.com
  Advanced Algorithms and Data StructuresA vector is a mathematical quantity with magnitude and direction that can represent a displacement or directed geometric segment.
• 

  liveBookmanning.com
  LLMs in ProductionA vector is an ordered numerical representation of values in a mathematical space.
• 

  liveBookmanning.com
  Grokking AI ApplicationsAn embedding is a numerical vector representation of a text unit that encodes information used for model computations.
• 

  liveBookmanning.com
  Outlier Detection in PythonAn embedding is a numerical representation of an item in a continuous vector space that preserves selected properties or relationships of the original data.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA continuous numeric encoding that captures the meaning of an input sentence for downstream decoding.
• 

  liveBookmanning.com
  Knowledge Graphs and LLMs in ActionA feature vector is a numerical vector whose components represent measurable characteristics of an input for machine learning.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA one-dimensional array treated as a tensor and used as a model input or feature representation.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionAn embedding is a learned numerical vector representation of an object, token, or other data item.
• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsA vector is an ordered collection of numerical values representing a point, direction, or feature set in a mathematical space.
• 

  liveBookmanning.com
  Sutskever's ListA vector is a one-dimensional ordered collection of numerical values.
• 

  liveBookmanning.com
  MongoDB 8.0 in Action, Third EditionA text embedding is a vector representation of text that captures semantic relationships and contextual nuances.
• 

  liveBookmanning.com
  Transformers in ActionA fixed-length vector is an ordered numerical representation with a predetermined number of components.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)A numerical representation used to encode text or other objects for neural computation.
• 

  liveBookmanning.com
  How Large Language Models WorkA vector is an ordered numerical quantity that represents magnitude and direction or encodes data in a multidimensional space.
• 

  liveBookmanning.com
  Optimization Algorithms: AI techniques for design, planning, and control problemsA function that maps input entities or features into numerical representations used by a model.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionAn input vector is an ordered one-dimensional array of values supplied to a computational layer.
• 

  liveBookmanning.com
  Graph Algorithms for Data ScienceNode embedding is a technique that represents graph nodes as numerical vectors so that selected structural or relational similarities are preserved.
• 

  liveBookmanning.com
  AI Agents in Action, Second EditionA dense vector is a numerical vector in which the representation generally assigns a value to every dimension.
• 

  liveBookmanning.com
  AI Agents and ApplicationsA vector type is a database data type that represents numerical vector values as stored fields.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA one-dimensional numeric data structure used here as a mathematical object on which sums and dot products can be computed.
• 

  liveBookmanning.com
  The Art of AI Product DevelopmentA numeric vector representation that encodes the semantic or structural properties of an item for computational comparison.
• 

  liveBookmanning.com
  Build Python Web Apps with StreamlitA text embedding is a numerical vector representation of text that captures features useful for semantic comparison.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionAn embedding is a numerical internal representation of data that captures features useful for computational processing.
• 

  liveBookmanning.com
  Building Reliable AI SystemsAn embedding is a numerical representation of content that captures semantic meaning in a form suitable for comparison.
• 

  liveBookmanning.com
  The AI Pocket BookA vector representation used to encode the meaning of an image, text, or other content.
• 

  liveBookmanning.com
  Classic Computer Science Problems in Swift: Essential techniques for practicing programmersA vector is an ordered collection of numerical components representing a quantity or point in a mathematical space.
• 

  liveBookmanning.com
  Generative AI in ActionA vector is an ordered sequence of numerical values representing a point or quantity in a multidimensional space.
• 

  liveBookmanning.com
  Data Pipelines with Apache Airflow, Second EditionA vector is an ordered numerical quantity representing a point, direction, or set of measurable attributes in a multidimensional space.
• 

  liveBookmanning.com
  Data Analysis with LLMsAn embedding is a numerical vector representation of an object that is intended to preserve meaningful properties of that object.
• 

  liveBookmanning.com
  Build an AI Agent (From Scratch)A vector is an ordered collection of numerical values representing an object or its properties in a mathematical space.
• 

  liveBookmanning.com
  Effective Conversational AIA text embedding is a numerical vector representation that encodes semantic or contextual properties of text.
• 

  liveBookmanning.com
  Building LLM Applications with DSPyA numerical vector representation of an item, such as text, that encodes useful features.
• 

  liveBookmanning.com
  Deep Learning with JAXA rank-1 multidimensional array with one axis, used here for model outputs such as class probabilities.
• 

  liveBookmanning.com
  Data Without LabelsA word embedding maps each word to a numerical vector whose geometry reflects usage-based meaning and relationships.
• 

  liveBookmanning.com
  Financial AI in PracticeAn embedding is a numerical vector representation of content that preserves properties useful for similarity comparison and retrieval.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIAn embedding is a learned or constructed representation that maps high-dimensional data into a lower-dimensional space while preserving selected characteristics or relationships.
• 

  liveBookmanning.com
  Delivering Machine Learning Projects: From design to deploymentAn embedding is a numerical vector representation that encodes meaningful properties of an input for comparison or downstream computation.
• 

  liveBookmanning.com
  Machine Learning System DesignAn embedding is a numerical vector representation of an object that places semantically or structurally similar objects near one another in a representation space.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthA vector is an ordered mathematical object representing magnitude and direction or coordinates in a vector space.
• 

  liveBookmanning.com
  Build Applications with Local AI Models on a MacAn embedding is a numerical vector representation of an item, such as text, positioned to capture aspects of its meaning or features.

Compare how 47 books explain embedding →

Related concepts

• vectorizationproduced by · Vectorization is the representation of data or computations as vectors or arrays so they can be processed numerically or collectively.
• encoderproduced by · An encoder is a component that transforms input data into an encoded representation for subsequent processing, reconstruction, comparison, or transmission.
• semantic cachingused by · Semantic caching is a technique that stores and reuses results for requests judged sufficiently similar in meaning, rather than requiring identical text or keys.
• t-SNEproduced by · t-SNE is a nonlinear dimensionality-reduction technique that maps high-dimensional data to a lower-dimensional space while emphasizing local similarities or neighborhood relationships.
• text encoderproduced by · A text encoder is a neural-network model that transforms textual input into numerical representations for conditioning or other downstream computation.

This explainer was generated by Manning's knowledge graph from the text of Data Storytelling with Altair and AI. The section links point to the parts of the book it draws on.