How deeply does Building LLM Applications with DSPy cover knowledge base?

Describes article fields and ID links, then explains title-based retrieval, without detailing the full article corpus.

Knowledge base

As explained in Building LLM Applications with DSPy

The knowledge base is the example application's collection of Wix knowledge-base articles used as supporting information for answers.

A knowledge base is a collection of articles that can supply information for answering questions. In the WixQA example, article IDs link expert-written answers to the supporting articles. section 9.1 section 9.0

The WixQA articles include fields such as:

An ID, URL, title, and article contents; the dataset also includes HTML content and article type. section 9.1
Titles that can be embedded and searched for similarity to a customer question; retrieved article contents can then provide context for an answer. section 9.2

Table 9.2 Knowledge base example

Column	Value
`id`	860475a2cbc65c226ecf08729d0430584e46f35f23a3e10bb5500c2c4ad09168
`url`	https://support.wix.com/en/article/wix-events-about-the-event-details-and-registration -form-pages
`contents`	Wix Events: About the Event Details and Registration Form Pages and Guests visiting your site view the events you offer on the Events List page. From there they can learn more on the Event Details page (if enabled) and complete the booking on the Registration Form page. You can customize how these pages look to suit your events. Tips:\nCustomizations you make to the Event Details page and the Registration…
`title`	Wix Events: About the Event Details and Registration Form Pages

A sample Wix Events article shows the relationship between an article ID, its URL, title, and content. section 9.1

How Building LLM Applications with DSPy covers it

Cover of Building LLM Applications with DSPy

liveBook manning.com

Read Building LLM Applications with DSPy on liveBook Get the book at manning.com

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.
fine-tuningused by · Fine-tuning is adapting a pretrained machine-learning model by training it further on targeted data or objectives for a task, domain, or behavior.
Retrieverused by · A retriever is a software component that searches or queries an information source and returns items relevant to a query for use by downstream processes.

This explainer was generated by Manning's knowledge graph from the text of Building LLM Applications with DSPy. The section links point to the parts of the book it draws on.