Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Scaling up RAG with Vector Databases in Java

Go to class Write review

Overview

Scale your RAG system with a vector database. Learn to preprocess documents, store embeddings in ChromaDB, retrieve chunks using filters and weights, and build prompts for multi-chunk context. Also, manage updates and handle large-scale ingestion with batch strategies.

Syllabus

Unit 1: Document Chunking and Metadata in Java

Chunking Text into Word Groups in Java
Refining Text Chunking with Sentence Boundaries in Java
Chunking Text with Overlap in Java
Organizing Text Chunks with Metadata in Java
Enhance Text Chunking with Keyword Detection in Java

Unit 2: Storing and Managing Text Chunks in a Vector Database with Java

Exploring Vector Databases with ChromaDB in Java
Building a ChromaDB Collection in Java
Dynamically Managing ChromaDB Collections in Java

Unit 3: Retrieving and Utilizing Relevant Chunks with Java in RAG Systems

Shaping ChromaDB Collections with Keyword Deletion
Enhancing Semantic Retrieval with ChromaDB in Java
Integrating Contextual Prompts with LLM in Java
Incorporating Metadata-Based Filtering in Java Retrieval Process
Retrieving only documents in Queries
Incorporating Distance Threshold in Retrieval Process

Reviews

Start your review of Scaling up RAG with Vector Databases in Java