大模型应用技术原理

• RAG
  • 向量数据库 对比
    • 选型标准
      • 开源vs.闭源vs. 源码可见
      • 客户端/SDK语言
      • 托管方式
        • self-hosted/on-premise
          • redis,pgvector,milvus
        • managed/cloud-native
          • zilliz,pinecone
        • embeded+cloud-native
          • chroma,lanceDB
        • self-hosted+cloud-native
          • vald,drant,weaviate,vspa,elasticsearch
      • 索引方法
        • 算法
          • Flat
          • Tree-based
            • Annoy(Approximate Nearest Neighbors Oh Yeah)
            • KD-Tree
            • Trinary Projection Trees
          • IVF
            • IVF
            • IVMF(Inverted Multi-index File)
          • Graph-based
            • HNSW
            • NSG
            • Vamana(DiskANN)
          • Hashing-based
            • LSH
            • Spherical Hashing
            • Spect