liveBook · Manning

Vector database

As explained in Investing for Programmers

A vector database is a database designed to store and retrieve vector representations of data, typically for similarity-based search.

A vector database stores embedding vectors so retrieval-augmented generation workflows can find context related to a prompt. Documents are split, embedded, stored, and later searched by similarity. section 9.3.2

A practical preparation and retrieval workflow is:

  • Load documents into memory and add any user-specific context. section 9.3.2

In-memory RAG store

LangChain's InMemoryVectorStore uses OpenAIEmbeddings with model text-embedding-3-large; a retrieve function searches it and supplies matching documents to generation.

How Investing for Programmers covers it

How deep it goes
Explains chunking, embedding, insertion, and similarity search, but defers production database management.
Examples
Uses text files, overlapping document chunks, OpenAI embeddings, an in-memory store, and autonomous-driving company questions.
What it assumes
Assumes familiarity with documents, prompts, embeddings, and LLM calls while demonstrating the data-preparation workflow.
What you can do after
Apply it via LangChain by embedding documents, storing them, retrieving similar context, and passing results to an LLM.
How it connects
Connects embeddings, retrieval-augmented generation, similarity search, and large language models.
Cover of Investing for Programmers
liveBookmanning.com
Read Investing for Programmers on liveBook Get the book at manning.com

Also explained in

Compare how 26 books explain vector database →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Investing for Programmers. The section links point to the parts of the book it draws on.