Keeping proprietary or customer-specific documents in a retrieval index rather than baking them into model weights makes deletion a scoped operation instead of requiring a full retrain. section 6.6.1
Retrieval index
A retrieval index is an organized structure that enables relevant documents or records to be found for retrieval.
How AI Governance covers it
- How deep it goes
- Explains the deletion advantage of indexed storage but leaves retrieval mechanics and index implementation unspecified.
- Examples
- Contrasts storing proprietary documents in a retrieval index with baking them into model weights.
- What you can do after
- Evaluate how storing customer-specific documents in a retrieval index can make deletion narrower than retraining.
- How it connects
- Connects retrieval indexes to model weights, fine-tuning, embedding stores, and data provenance.
Also explained in
-
Designing AI SystemsA retrieval index is a searchable data structure that organizes document representations and associated metadata so relevant information can be found efficiently.
-
Retrieval Augmented Generation, The Foundational IdeasA document index is a stored structure containing representations of documents that supports retrieval from a document collection.
-
Generative AI in ActionA document index is a data structure that organizes documents or their representations to support efficient information retrieval.
Compare how 4 books explain retrieval index →
Related concepts
- 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.
- model weightcontrasts with · A model weight is a learned numerical parameter that influences a machine-learning model’s computations and behavior.
- abstract syntax treeused by · An abstract syntax tree is a hierarchical tree representation of the syntactic structure of parsed source code or other language input, typically omitting superficial formatting details.
- similarity searchpart of · Similarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- repositoryused by · A software repository is a managed collection of a project's files and artifacts, often preserving their version history.
This explainer was generated by Manning's knowledge graph from the text of AI Governance. The section links point to the parts of the book it draws on.



