Skip to main content

RAG - retrieval-augmented generation

Presentation - Empowering GenAI with RAG

RAG is an AI framework for retrieving facts from an external knowledge base to ground large language models (LLMs) on the most accurate, up-to-date information and to give users insight into LLMs' generative process.

  • RAG combines retrieval and generation processes to enhance the capabilities of LLMs
  • In RAG, the model retrieves relevant information from a knowledge base or external sources
  • This retrieved information is then used in conjunction with the model's internal knowledge to generate coherent and contextually relevant responses
  • RAG enables LLMs to produce higher-quality and more context-aware outputs compared to traditional generation methods
  • Essentially, RAG empowers LLMs to leverage external knowledge for improved performance in various natural language processing tasks

Why is Retrieval-Augmented Generation important​

  • You can think of the LLM as an over-enthusiastic new employee who refuses to stay informed with current events but will always answer every question with absolute confidence.
  • Unfortunately, such an attitude can negatively impact user trust and is not something you want your chatbots to emulate!
  • RAG is one approach to solving some of these challenges. It redirects the LLM to retrieve relevant information from authortative, pre-determined knowledge sources.
  • Organizations have greater control over the generated text output, and users gain insights into how the ML generates the response.

Codes​

Types of RAG​

Types of RAG

🌶️ Hot take: I'm tired of RAG systems that just grab the first document and call it done. 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 is probably the only way RAG is 𝘢𝘤𝘵𝘶𝘢𝘭𝘭𝘺 going to be useful. But what’s… | Victoria Slocum | 40 comments

Advanced​

rag-architecture

RAG from Scratch

Stop Saying RAG Is Dead – Hamel’s Blog

Advanced RAG Techniques​

  • Query Expansion (with multiple queries)

Advanced RAG Techniques: Unlocking the Next Level | by Tarun Singh | Medium

RIG - Retrieval Interleaved Generation - DataGemma through RIG and RAG - by Bugra Akyildiz

Contextual Retrieval​

Contextual Retrieval (introduced by Anthropic1) addresses a common issue in traditional Retrieval-Augmented Generation (RAG) systems: individual text chunks often lack enough context for accurate retrieval and understanding.

Contextual Retrieval enhances each chunk by adding specific, explanatory context before embedding or indexing it. This preserves the relationship between the chunk and its broader document, significantly improving the system's ability to retrieve and use the most relevant information.

Chunking​

  • Fixed Size Chunking - The simplest approach - split text into chunks of consistent size (e.g., 100 words, 200 characters). Easy to implement but might break sentences awkwardly.
  • Recursive Chunking - Hierarchically splits documents, preserving structure while creating manageable chunks. Great for maintaining context across different levels of detail.
  • Document-based Chunking - Uses natural document markers like paragraphs, sections, or chapters as boundaries. Keeps related information together but can create wildly different chunk sizes.
  • Semantic Chunking - Variable-size chunks based on meaning rather than arbitrary markers. More sophisticated but computationally intensive.
  • Late Chunking - Embeds first, then chunks - preserving more contextual information in the vectors themselves.

Chunking Techniques

Chunking Strategies

Chunking Strategies to Improve Your RAG Performance | Weaviate

Reranking​

Others​

GraphRAG​

Databases

Graph RAG

Cache-Augmented Generation (CAG)​

RAG vs. CAG: Solving Knowledge Gaps in AI Models - YouTube

GitHub - hhhuang/CAG: Cache-Augmented Generation: A Simple, Efficient Alternative to RAG ⭐ 1.5k

Tools​

NoCode Tools​