</>SkillRecallRECALL WHAT YOU KNOW
Sign in
Explore Library
AI Engineering / Working with LLMsRetrieval-Augmented Generation (RAG)

18 items

1

Advanced RAG Techniques

Slides / Video
2

Re-ranking in Advanced RAG

Quiz
3

Advanced RAG Techniques

Flashcard
4

Context Injection in RAG Prompts

Quiz
5

Prompt Construction and Context Injection

Slides / Video
6

Prompt Construction and Context Injection

Flashcard
7

Embeddings and Vector Representations

Flashcard
8

Chunk Size and Overlap Tradeoffs

Flashcard
9

How RAG Reduces Hallucinations

Flashcard
10

Top-K Retrieval and Choosing K

Flashcard
11

Vector Databases and Their Role

Flashcard
12

Similarity Metrics

Flashcard
13

Document Chunking Strategies

Flashcard
14

What is RAG and Why It Exists

Flashcard
15

RAG vs Fine-Tuning for Knowledge

Flashcard
16

Embedding Models and Selection

Flashcard
17

Semantic Similarity Search

Flashcard
18

The RAG Pipeline

Flashcard
QuizIntermediate

Context Injection in RAG Prompts

Understanding how retrieved documents are combined with user queries in a RAG prompt.

In a basic RAG pipeline, what is the primary purpose of injecting retrieved documents into the prompt before sending it to the LLM?