<aside>
💡
相關頁面: AI相關工具非常非常的多,RAG開發工具會整理在RAG開發工具,LLM以及相關工具會整理在Large Language Models,Graph RAG開發工具會整理在Graph RAG,其他工具整理在Generative AI開發工具中。目前還有一些資料在Generative AI及RAG中,將逐步整理這些內容。
</aside>
開發工具簡介
Web Framework for RAG
- 開源RAG網頁套件研究
- open-webui
- Hollama
- LoLLMs Webui
- BionicGPT
- LibreChat
- LLMStack
Vector Databases
- Everything you need to know about Vector Databases — A Deep Dive
- All You Need to Know about Vector Databases and How to Use Them to Augment Your LLM Apps (Friend Link)
- Suppose we decide to use a vector store — What options do we have?
- Pure vector databases
- Chroma, Pinecone, Weaviate, Milvus
- Extended capabilities in SQL, NoSQL or text search databases
- Redis, MongoDB
- Pgvector, for example, is the open source vector similarity search for Postgres
- Simple vector libraries
- Hands-On Tutorial — Set up your first Vector Store
- Top Vector Databases— And How To Choose (Friend LInk)
- Search Indexing Algorithms:
- Hash-based
- Locality-Sensitive Hashing (LSH)
- Tree-based
- Annoy (Approximate Nearest Neighbors Oh Yeah)
- Graph-based
- HNSW (Hierarchical Navigable Small World)
- Inverted File
- IVF (Inverted File Index), IVFFlat, IVFPQ, and IVFSQ.
- Vector Libraries
- Faiss (Facebook AI Similarity Search)
- HNSWlib
- Nmslib (Non-Metric Space Library)
- Vector Databases
- Miluvs
- Weaviate
- Qdrant
- Pinecone
- ElasticSearch
- Chroma
- Non-dedicated Vector Databases — Redis, MongoDB, and PGVector
- Optimize Vector Databases, Enhance RAG-Driven Generative AI
- Milvus Vector Database Optimizations
- Reducing Memory Movement Overhead in Datanode Buffer Write
- Inverted Index Building with Reduced Memory Allocation Overhead
- Redis Vector Search Acceleration through Software Prefetch
- Explaining Vector Databases in 3 Levels of Difficulty (Friend Link)
Chroma
KDB
Milvus
Oracle