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
  • Overview
  • Supporting Vector Stores
  1. Utils

Slim Vector Store

PreviousEmbeddingNextPinecone Slim

Last updated 1 year ago

Overview

Slim Vector Store is vector store class designed for RAGchain. At default, Langchain's is fully compatible with RAGchain. But, it is inefficient because it stores all string contents at every vector store. Because of this limitation, you have to spend lots of storage space when using multiple retrievals.

RAGchain store vector representation using retrievals, and store string contents to independent DB. So, you don't have to store string contents to vector store.

Using Slim Vector Store, it only stores vector representation and passage ids. It will save a lot of storage when you use multiple retrievals.

Supporting Vector Stores

We are implementing many vector stores, but many vector stores are not implemented yet. When you have to use another vector stores, please find it at Langchain's Vector Store. It is fully compatible with RAGchain.

Vector Store
Chroma
Pincone