精通向量数据库
- 1. Introduction
- 1. Introduction to Vector Database
- 2. Vectors and Embeddings
- 3. Explain vector database like I'm 5
- 4. How vector database store data
- 5. How do vector database works
- 6. Vectors in 2D
- 2. The power of embeddings
- 1. Create embeddings using OpenAI
- 3. Using SQLite as vector storage
- 1. Setup and basic operations
- 2. Creating, storing and retrieving vector data
- 3. Finding nearest vector
- 4. Vector search using sqlite-vss extension
- 4. ChromaDB
- 1. Introduction to ChromaDB
- 3. Methods on collections
- 4. Storing The Matrix collections
- 5. Adding document associated embeddings
- 6. Query data with 'where' filter
- 7. ChromaDB + Langchain - QA on multiple documents - Part 1
- 8. ChromaDB + Langchain - QA on multiple documents - Part 2
- 5. Facebook AI Similarity Search (FAISS)
- 1. Introduction to FAISS
- 2. Using similarity search for nearest neighbours
- 6. Pinecone
- 1. Introduction to Pinecone
- 2. Setup account, create an index, dashboard review
- 3. Understanding index creation configuration
- 4. Index management
- 5. Insert vector data to an index
- 6. Query vector data
- 7. Upsert vector data in batches
- 8. Upsert batches in parallel
- 10. Vector IDs must be string
- 11. Sentence transformer embeddings
- 12. Semantic search with metadata filtering - news articles
- 7. Qdrant
- 1. Introduction to Qdrant vector database
- 2. Connect with APIs
- 3. Create a qdrant python client
- 4. Create a collection
- 5. Create a vector store
- 6. Add document to vector store on the cloud
- 7. Query the document