Skip to content
Bot Nirvana Members
  • Home
  • Playbook
  • Use Cases
  • Tools
  • AI Papers
  • Login
Bot Nirvana Members
  • Account
  • AI & Automation Tools
  • AI Advisory Board (AAB)
  • AI Ideas / Use Cases
  • AI Papers
  • AI Papers
  • Cancel Payment
  • Change Password
  • Edit Profile
  • Forgot Password
  • Guest
  • Home
  • Latest Tools
  • Login
  • Login
  • Logout
  • Members
  • Password Reset
  • Register
  • Register
  • Session Recordings
  • Stories
  • Thank You
  • Trends
  • Use Cases
  • User

Introduction

3
  • Welcome
  • Purpose and Principles
  • How to Use the Playbook

AI Fundamentals

7
  • The origins and evolution of AI
  • Key Concepts and Terminology
  • Traditional AI (ML) vs Foundational models (Gen AI)
  • AI vs. ML vs. Deep Learning vs. Generative AI
  • Introduction To Generative AI
  • Synthetic Data
  • Computer Vision

Generative AI

13
  • LLMs and Foundational Models
  • Foundation models 101
  • Architecture for LLM Applications (Emerging)
  • Prompt Engineering
  • Tokens and Optimization
  • Retrieval Augmented Generation (RAG)
  • Four Types Of RAG (from Microsoft)
  • Mixture of Experts (MoE)
  • Model Inference
  • Small Language Models
  • Reinforcement Learning from Human Feedback (RLHF)
  • Large Vision Models (LVMs)
  • Types of RAG

AI Agents

8
  • Types of Agents
  • Agent uses and examples
  • AI Agents
  • Agentic workflow
  • AI Agent Memory
  • Intelligent Automation with AI Agents
  • AI agent challenges
  • Agentic RAG

Applying AI

5
  • Continuum for Applied AI
  • 11 ways to apply Gen AI
  • AI-led automation
  • Chatbots
  • Microsoft 365 Co-Pilot

Use Cases

2
  • 15 Best Gen AI Use Cases
  • Use Case Grid

Technologies and Tools

7
  • Top 3 AI Tools by Category
  • LLM app dev tools
  • Current LLM Landscape
  • ChatGPT Enterprise
  • OpenAI Playground
  • Vector Databases
  • Synthetic data

AI Strategies

4
  • 5-Steps to Identifying Winning AI Opportunities
  • How To Identify & Prioritize AI Opportunities
  • Create a compelling business case
  • Mastering Data Management for Business: A Comprehensive Guide

Risks & Security

5
  • Risks of AI
  • 4 Top AI Risks Right Now
  • AI – Security Risk Checklist
  • AI Security Frameworks
  • Hallucinations and other risks

AI Safety

4
  • Explainable AI
  • AI Alignment
  • Ethical Considerations And Strategies
  • Handling Sensitive Information with AI

AI Governance

6
  • AI Center of Excellence
  • The regulatory landscape for AI
  • Current compliance situation
  • AI CoE checklist
  • Data governance: ensuring data integrity and accessibility
  • Crafting AI Policies for Transparency and Bias Mitigation

AI Implementation

1
  • Key Factors to Consider When Selecting a LLM

Resources and Further Learning

2
  • Free courses
  • Best AI Resources

Prompt Engineering

4
  • Chain of Thought Prompting
  • Effective Guide To Prompting
  • One-Shot Prompting
  • Self-Consistency Prompting

Thought Leadership

1
  • AI Spanning

AI Hardware

1
  • GPUs in AI

Robotics

1
  • Robotics and AI

LLM Evaluation

3
  • Practical LLM Evaluation Techniques
  • Methods and Frameworks for LLM Evaluation
  • LLM Evaluation Explained
  • Home
  • Playbook
  • Generative AI
  • Types of RAG
View Categories

Types of RAG

4 min read

Retrieval-augmented generation (RAG) stands at the forefront of AI advancements, revolutionizing how we generate and retrieve information by merging retrieval mechanisms with generative models.

RAG implementations introduce a sophisticated blend of retrieving relevant data and generating coherent responses, enhancing the overall effectiveness of information systems. These implementations are essential as they provide varied solutions tailored to specific needs, ranging from simple data retrieval to complex decision-making environments. By understanding the different types of RAG models, organizations can better align their AI strategies with their operational demands, ensuring efficient and contextually relevant outputs.

Simple RAG #

Simple RAG focuses on streamlined processes ideal for straightforward applications. It involves receiving an input, retrieving relevant data, generating a prompt, and then producing a response. This model is best suited for applications where the questions have direct relations to stored data, such as FAQs or basic customer service queries.

Workflow #

1. Input Reception
2. Data Retrieval
3. Prompt Generation
4. Response Generation

Use Case #

1. Ideal for straightforward applications
2. Direct relation to stored data

Simple RAG with Memory #

This variation maintains context over extended interactions, crucial for applications like customer support. The process starts with input reception, followed by a memory check to understand past interactions. Then, it transforms the query, retrieves data, generates a prompt, and finally produces a response.

Workflow #

1. Input Reception and Memory Check
2. Query Transformation
3. Data Retrieval and Prompt Generation
4. Response Generation

Use Case #

1. Maintaining context over extended interactions
2. Customer support applications

Seamlessly extending from Simple RAG with Memory, we explore Branched RAG models.

Branched RAG #

Branched RAG involves determining the source based on the input, retrieving data from multiple sources, generating a relevant prompt, and then producing a response. This model excels in applications requiring diverse data sources, such as research or multi-domain knowledge systems.

Workflow #

1. Input Reception
2. Source Determination
3. Data Retrieval and Prompt Generation
4. Response Generation

Use Case #

1. Applications requiring data from multiple sources
2. Research or multi-domain knowledge systems

The transition from Branched RAG leads us to the HyDe model, emphasizing hypothetical document embedding.

HyDe (Hypothetical Document Embedding) #

HyDe enhances the relevance of retrieved information by generating a hypothetical answer, retrieving related data, and then creating a prompt before producing a response. This approach is particularly useful for queries that lack sufficient context for effective data retrieval.

Workflow #

1. Input Reception
2. Hypothetical Answer Generation
3. Data Retrieval
4. Prompt Generation and Response

Use Case #

1. Enhancing the relevance of retrieved information
2. Queries insufficient for effective data retrieval

Building on HyDe, we delve into Advanced RAG Strategies, starting with Adaptive RAG.

Advanced RAG Strategies #

Adaptive RAG #

Adaptive RAG combines query analysis with active/self-corrective mechanisms. It involves analyzing the query, executing the strategy, and then retrieving and refining data to produce an accurate response. This method is dynamic, making it suitable for environments with varied queries like search engines or AI assistants.

Concept #

Combines query analysis with active/self-corrective RAG

Implementation #

1. Query Analysis
2. Strategy Execution

Use Case #

1. Dynamic environments with varied queries
2. Search engines or AI assistants

Next, we move to Corrective RAG (CRAG), focusing on high-stakes environments.

Corrective RAG (CRAG) #

CRAG incorporates self-reflection and self-grading to enhance reliability. After an initial retrieval, it refines the knowledge, performs supplementary retrievals, and then generates the final response. It is ideal for applications in legal or medical fields where accuracy is paramount.

Concept #

Incorporates self-reflection and self-grading

Workflow #

1. Initial Retrieval
2. Knowledge Refinement
3. Supplementary Retrieval
4. Prompt Generation and Response

Use Case #

1. High-stakes environments
2. Legal or medical applications

Following CRAG, we discuss Self-RAG, designed for high reliability.

Self-RAG #

Self-RAG includes self-reflection and self-grading mechanisms to ensure the highest reliability with minimal hallucination. It involves deciding whether to retrieve, checking relevance, verifying generation, and assessing response utility. This model is perfect for automated research assistants or knowledge-base systems.

Concept #

Includes self-reflection and self-grading

Workflow #

1. Decision to Retrieve
2. Relevance Check
3. Generation Verification
4. Response Utility

Use Case #

1. High reliability and minimal hallucination
2. Automated research assistants or knowledge base systems

Lastly, we explore Agentic RAG, which uses an agent-based approach.

Agentic RAG #

Agentic RAG employs document agents and a meta-agent for coordinated question answering, making it suitable for complex tasks requiring planning and multi-step reasoning. This model excels in environments where tool use and learning over time are critical.

Concept #

An agent-based approach for coordinated question-answering

Key Components and Architecture #

1. Document Agents
2. Meta-Agent

Use Case #

1. Complex tasks requiring planning and multi-step reasoning
2. Tool use and learning over time

What do you think?
Updated on July 1, 2024
Large Vision Models (LVMs)

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Table of Contents
  • Simple RAG
  • Workflow
  • Use Case
  • Simple RAG with Memory
  • Workflow
  • Use Case
  • Branched RAG
  • Workflow
  • Use Case
  • HyDe (Hypothetical Document Embedding)
  • Workflow
  • Use Case
  • Advanced RAG Strategies
  • Adaptive RAG
  • Concept
  • Implementation
  • Use Case
  • Corrective RAG (CRAG)
  • Concept
  • Workflow
  • Use Case
  • Self-RAG
  • Concept
  • Workflow
  • Use Case
  • Agentic RAG
  • Concept
  • Key Components and Architecture
  • Use Case

Copyright © 2025 Bot Nirvana Members

Scroll to Top