← Back to insights

Insight · April 4, 2026 · 2 min read

8 RAG types

  1. Naive RAG
  • Retrieves documents purely based on vector similarity between the query embedding and stored embeddings.
  • Works best for simple, fact-based queries where direct semantic matching suffices.
  1. Multimodal RAG
  • Handles multiple data types (text, images, audio, etc.) by embedding and retrieving across modalities.
  • Ideal for cross-modal retrieval tasks like answering a text query with both text and image context.
  1. HyDE (Hypothetical Document Embeddings)
  • Queries are not semantically similar to documents.
  • This technique generates a hypothetical answer document from the query before retrieval.
  • Uses this generated document’s embedding to find more relevant real documents.
  1. Corrective RAG
  • Validates retrieved results by comparing them against trusted sources (e.g., web search).
  • Ensures up-to-date and accurate information, filtering or correcting retrieved content before passing to the LLM.
  1. Graph RAG
  • Converts retrieved content into a knowledge graph to capture relationships and entities.
  • Enhances reasoning by providing structured context alongside raw text to the LLM.
  1. Hybrid RAG
  • Combines dense vector retrieval with graph-based retrieval in a single pipeline.
  • Useful when the task requires both unstructured text and structured relational data for richer answers.
  1. Adaptive RAG
  • Dynamically decides if a query requires a simple direct retrieval or a multi-step reasoning chain.
  • Breaks complex queries into smaller sub-queries for better coverage and accuracy.
  1. Agentic RAG
  • Uses AI agents with planning, reasoning (ReAct, CoT), and memory to orchestrate retrieval from multiple sources.
  • Best suited for complex workflows that require tool use, external APIs, or combining multiple RAG techniques.

Read this article as markdown