liveBook · Manning

Knowledge base

As explained in Retrieval Augmented Generation, The Foundational Ideas

The internal knowledge base is the case study's repository of Mastercard support information supplied to the assistant.

A customer-support assistant needs current, specific answers, but its training data may be outdated or lack internal documentation altogether. A knowledge base supplies documents the assistant can retrieve as evidence instead of relying only on what the model remembers. section 1.2

In a RAG system, the knowledge base sits between an offline indexing pipeline and an online query pipeline. Indexing breaks documents such as manuals, policies, and FAQs into manageable pieces, converts them into searchable representations, and stores them. At query time, retrieval fetches candidate pieces; ranking prioritizes useful matches before the language model generates an answer grounded in that evidence. section 1.2

An acronym collision

A fintech knowledge base may span product wikis, runbooks, compliance guides, and API specifications. “CMA” can name different things across those documents. Retrieving the wrong CMA document is not a lack-of-content problem: the right information may exist, but retrieval has missed the best match. In one baseline using query reformulation, single-pass vector retrieval, and answer summarization, Hit Rate @5 was 54.12% on 85 questions, with average query latency of 0.79 seconds. Procedural and multi-document questions were also difficult. section 15.7.1

Keeping knowledge in a document repository also makes it possible to update information without retraining the whole model and to inspect which document supported an answer. Neither benefit guarantees a correct response: the relevant document still has to be retrieved, ranked well, and used accurately during generation. section 3.4 section 1.2

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains offline document processing and online retrieval, ranking, and generation, but does not specify a database schema.
Examples
Uses ambiguous fintech acronyms and a baseline evaluated on 85 question-answer pairs to show retrieval difficulty.
What you can do after
Evaluate/understand knowledge-base retrieval through Hit Rate @5, latency, and errors caused by ambiguous or fragmented documentation.
How it connects
Connects the knowledge base to RAG, document indexing, vector retrieval, ranking, and grounded generation.

Also explained in

Compare how 15 books explain knowledge base →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.