RAGChain Docs
  • Introduction
  • Quick Start
  • Installation
  • RAGchain Structure
    • File Loader
      • Dataset Loader
        • Ko-Strategy-QA Loader
      • Hwp Loader
      • Rust Hwp Loader
      • Win32 Hwp Loader
      • OCR
        • Nougat Loader
        • Mathpix Markdown Loader
        • Deepdoctection Loader
    • Text Spliter
      • Recursive Text Splitter
      • Markdown Header Splitter
      • HTML Header splitter
      • Code splitter
      • Token splitter
    • Retrieval
      • BM25 Retrieval
      • Hybrid Retrieval
      • Hyde Retrieval
      • VectorDB Retrieval
    • LLM
    • DB
      • MongoDB
      • Pickle DB
    • Reranker
      • BM25 Reranker
      • UPR Reranker
      • TART Reranker
      • MonoT5 Reranker
      • LLM Reranker
    • Benchmark
      • Auto Evaluator
      • Dataset Evaluators
        • Qasper
        • Ko-Strategy-QA
        • Strategy-QA
        • ms-marco
  • Utils
    • Query Decomposition
    • Evidence Extractor
    • Embedding
    • Slim Vector Store
      • Pinecone Slim
      • Chroma Slim
    • File Cache
    • Linker
      • Redis Linker
      • Dynamo Linker
      • Json Linker
    • REDE Search Detector
    • Semantic Clustering
  • Pipeline
    • BasicIngestPipeline
    • BasicRunPipeline
    • RerankRunPipeline
    • ViscondeRunPipeline
  • For Advanced RAG
    • Time-Aware RAG
    • Importance-Aware RAG
Powered by GitBook
On this page
  • Time-Aware RAG
  • Importance-Aware RAG

For Advanced RAG

For making advanced RAG workflow. Several tips and useful utils will be introduced.

PreviousViscondeRunPipelineNextTime-Aware RAG

Last updated 1 year ago

This section introduces techniques and utilities for creating advanced Retrieval-Augmented Generation (RAG) workflows using RAGchain. In RAGchain, we delve into the complexities of constructing production-level RAG workflows. It's challenging to create a flawless RAG workflow tailored to your specific needs. However, certain patterns can enhance the effectiveness of these workflows, so we prepare patterns that you might need.

We are continually developing and improving this framework, so expect further updates.

Time-Aware RAG

In real-world applications, you'll often find that the latest information is more valuable than outdated data. However, manually discarding old information can be challenging and potentially harmful, as this information might be useful for other queries. Therefore, time-aware RAG is crucial for certain applications.

Time-aware RAG prioritizes recent information without discarding older data that might still be relevant. To learn how to implement time-aware RAG in RAGchain, please refer to .

Importance-Aware RAG

In some cases, you may want to prioritize certain passages over others. For example, when you try to find specific information at Google search, there are some websites that you trust more than others. Or, some websites that you don't want to see. In this case, you can use importance-aware RAG.

Importance-aware RAG prioritizes certain passages over others. To learn how to implement importance-aware RAG in RAGchain, please refer to .

Time-Aware RAG
Importance-Aware RAG