Unknown Date

flow chart

Here are detailed Mermaid diagrams for each type of Augmented Generation, showing how they are implemented differently.

  1. Retrieval-Augmented Generation (RAG)

We don't have a way to export this macro.

Implementation: Retrieves relevant documents from external sources using vector search (e.g., FAISS) or keyword-based retrieval, then augments the LLM with context before generation.

  1. Knowledge-Augmented Generation (KAG)

We don't have a way to export this macro.

Implementation: Uses structured knowledge sources (e.g., Wikidata, domain ontologies) to retrieve factual information and integrate it into LLM responses.

  1. Context-Augmented Generation (CAG)

We don't have a way to export this macro.

Implementation: Uses conversation history, document history, or ongoing chat context to enhance response coherence and personalization.

  1. Database-Augmented Generation (DAG)

We don't have a way to export this macro.

Implementation: Queries structured databases (SQL, NoSQL) in real-time, retrieves relevant data, and integrates it into LLM-generated responses.

  1. Prompt-Augmented Generation (PAG)

We don't have a way to export this macro.

Implementation: Uses structured and optimized prompts (e.g., few-shot learning, chain-of-thought reasoning) to improve response accuracy.

  1. Multimodal-Augmented Generation (MMAG)

We don't have a way to export this macro.

Implementation: Uses multimodal processing (images, audio, video) to extract relevant information before passing it to the language model.

  1. Fine-Tuned Augmented Generation (FAG)

We don't have a way to export this macro.

Implementation: Uses a fine-tuned version of an LLM trained on specific datasets for domain specialization.

  1. Symbolic-Augmented Generation (SAG)

We don't have a way to export this macro.

Implementation: Integrates symbolic logic (e.g., rule-based systems, decision trees) to enhance reasoning.

  1. Tool-Augmented Generation (TAG)

We don't have a way to export this macro.

Implementation: Uses external APIs, calculators, or plugins to improve accuracy.

10. Agent-Augmented Generation (AAG)

We don't have a way to export this macro.

Implementation: Uses multiple autonomous AI agents for complex problem-solving.

11. Graph-Augmented Generation (GAG)

We don't have a way to export this macro.

Implementation: Uses graph databases (e.g., Neo4j) to retrieve relationships between entities.

12. RAG-2 (Next-Gen RAG)

We don't have a way to export this macro.

Implementation: Enhances RAG with graph databases and structured data retrieval.

13. Learning-Augmented Generation (LAG)

We don't have a way to export this macro.

Implementation: Uses continuous learning to refine responses over time.

Summary

Each Augmented Generation method enhances an LLM in a unique way:

  • RAG / RAG-2 → External retrieval sources

  • KAG → Knowledge graphs

  • CAG → Conversation context

  • DAG → Database queries

  • PAG → Optimized prompts

  • MMAG → Multimodal input

  • FAG → Fine-tuned models

  • SAG → Symbolic logic

  • TAG → External tools

  • AAG → Multi-agent collaboration

  • GAG → Graph databases

  • LAG → Adaptive learning

← Back to Library