Unstructured data

As explained in AI-Powered Search

Unstructured data is information without a rigid predefined schema, often containing rich content and relationships in flexible forms such as text, images, video, and audio.

A search engine may index text, images, audio, and video that do not fit a predefined database schema. Calling this information “unstructured” is useful shorthand, but it can be misleading. Sentences have grammar and punctuation; images arrange colors into pictures; audio can carry words, music, and tone. The challenge is not an absence of structure, but extracting meaning from flexible forms. section 2.1 section 2.1.1

A SQL join links rows through an explicit shared value, such as a company ID. Search documents can also contain shared values, but their relationships are usually embedded in their content rather than declared as keys. A repeated event name, for example, can connect two separately indexed documents. Different phrases may also refer to the same entity, allowing a less exact connection through entity resolution. section 2.1.2 section 2.1.3

Finding a connection across documents

Suppose one search document says someone will speak at a conference and another describes that conference. Their shared conference name acts much like a join value. If two documents instead use a full name and a first name for the same person, connecting them requires resolving those different phrases to the same entity. A matching name alone can also be ambiguous: different people may share its spelling. section 2.1.3

Figure 2.5 Fuzzy foreign keys. In this example, the same entity is being referenced using different terms, and a join is occurring based upon multiple phrases resolving to the same entity.

The diagram shows a fuzzy connection: separate phrases refer to the same entity, so an exact shared term is not required. section 2.1.3

Event logs show how the categories can overlap: a structured date and event type may accompany a free-text message, making the record semi-structured. Across a search collection, connections among terms, entities, and documents can form a rich graph of domain knowledge. Those connections help search move beyond exact keyword occurrence, but ambiguous language makes context important. section 2.1.1 section 2.1.3 section 2.7

How AI-Powered Search covers it

How deep it goes

Defines the term, compares document links with SQL joins, and works through entity resolution; defers hands-on implementation.

Examples

Uses text, media, event logs, conference documents, and differently written person names to expose structure and ambiguity.

What it assumes

Introduces SQL rows and foreign keys as a comparison before explaining document relationships.

What you can do after

Evaluate/understand how search documents can be related without explicit foreign keys and why ambiguous matches need care.

How it connects

Connects unstructured data to SQL joins, entity resolution, knowledge graphs, and distributional semantics.

liveBookmanning.com

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

Also explained in

• 

  liveBookmanning.com
  Elasticsearch in Action, Second EditionUnstructured data is data that does not conform to a fixed field-based or tabular schema, such as free-form text.
• 

  liveBookmanning.com
  Data Without LabelsUnstructured data lacks an easily usable row-and-column schema and may include text, images, audio, or video.
• 

  liveBookmanning.com
  Delivering Machine Learning Projects: From design to deploymentAn unstructured field is a data field containing content such as images, text, or sounds without a fixed tabular representation.
• 

  liveBookmanning.com
  Essential GraphRAGUnstructured data is information without a predefined tabular or schema-based organization, such as free-form text.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIData whose varied modalities and organization do not conform to a fixed rows-and-columns schema.
• 

  liveBookmanning.com
  Fast Python: High performance techniques for large datasets
• 

  liveBookmanning.com
  The Art of AI Product DevelopmentUnstructured data is information without a consistent predefined tabular or schema-based organization, such as free text or images.
• 

  liveBookmanning.com
  Machine Learning System DesignData that lacks a fixed machine-readable schema for its content, such as free text or images.
• 

  liveBookmanning.com
  Knowledge Graphs and LLMs in ActionUnstructured data is information lacking a fixed tabular or schema-constrained organization, such as free-form documents.
• 

  liveBookmanning.com
  Financial AI in PracticeInformation that does not conform to a predefined schema for direct machine-readable interpretation.

Compare how 11 books explain unstructured data →

Related concepts

• structured datacontrasts with · Structured data is information organized according to an explicit schema or predictable fields, types, records, or relationships for consistent machine processing.
• textincludes · Text is written or digitally encoded linguistic content represented as characters, words, tokens, or other textual units.
• 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.
• language modelused by · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
• deep learningused by · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
• videoincludes · Video is time-ordered visual data represented as a sequence of image frames, often accompanied by synchronized audio.

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.