Skip to content

A minimal project to understand how cosine similarity works in a vector database ๐Ÿง ๐Ÿ“Š. It demonstrates semantic search by converting text into embeddings and comparing them using vector math.

License

Notifications You must be signed in to change notification settings

KanadShee-18/Vector-Store

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

4 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿ” Vector Similarity Search Demo


A simple visualization:

Cosine Similarity

A minimal project to understand how cosine similarity works in a vector database ๐Ÿง ๐Ÿ“Š.
It demonstrates semantic search by converting text into embeddings and comparing them using vector math.


๐Ÿงฐ Tech Stack

  • โš™๏ธ Node.js + TypeScript
  • ๐Ÿงพ Custom in-memory vector store
  • ๐Ÿ“ Cosine similarity algorithm

๐Ÿ’ก What Youโ€™ll Learn

  • ๐Ÿ”ค How text embeddings are used in vector search
  • ๐Ÿ“ How cosine similarity compares semantic meaning
  • ๐ŸŽฏ Filtering using topK and threshold parameters
  • โšก Real-world basics of how vector DBs like Pinecone, Weaviate, or FAISS work

License

MIT License

About

A minimal project to understand how cosine similarity works in a vector database ๐Ÿง ๐Ÿ“Š. It demonstrates semantic search by converting text into embeddings and comparing them using vector math.

Topics

Resources

License

Stars

Watchers

Forks