Basic RAG retrieves once and answers. Newer patterns let the system reason about its own retrieval.

Patterns

PatternIdeaUseful for
GraphRAG (Edge et al. 2024)Build a graph of entities and their relations, with summaries of related groupsGlobal questions such as "what are the main themes across all audit reports", which single chunks cannot answer
Corrective RAG (Yan et al. 2024)A small evaluator grades the retrieved passages, and if they look weak the system rewrites the query or searches elsewhereQuestions where the first retrieval is often poor
Self-RAG (Asai et al. 2023)The model decides when to retrieve and critiques its own answerQuestions that may not need retrieval at all
Agentic RAGRetrieval becomes one tool inside a plan, act and observe loopMulti-step questions, see Agentic AI

Remembering tip

GraphRAG sees the big picture, Corrective RAG checks the sources, Self-RAG asks itself whether to look up, and Agentic RAG puts retrieval in a loop.

Code

Corrective RAG as a simple loop: grade the retrieval, and rewrite the query if the grade is weak.

def corrective_search(query, grade, rewrite, k=5, min_grade=0.5):
    """grade(query, chunk_ids) -> score in [0, 1], rewrite(query) -> new query (for example from an LLM)."""
    ids = hybrid_search(query, k=k)
    if grade(query, ids) < min_grade:          # retrieval looks weak
        new_query = rewrite(query)             # ask the LLM to rewrite the question
        ids = hybrid_search(new_query, k=k)
    return ids

Notes:

  • grade can be a small model or an LLM judge that scores how relevant the passages are
  • this is a sketch of the idea, so a real system also needs a limit on the number of retries

These patterns are used in production systems like the one in Bank Compliance Assistant.