+
Skip to content

imcoza/Vector_Store

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

README.md

Implementing a VectorStore for Cosine Similarity-based Semantic Retrieval

This project demonstrates how to build the custom-based VectorStore class implemented from scratch to find similar sentences.

Vector Store

Aim of the Project

The project aims to implement a VectorStore class that can be used to effectively find similar sentences based on the Cosine Similarity Score. This involves implementing techniques for representing sentences as vectors, indexing those vectors in the custom VectorStore, and efficiently searching for similar vectors based on their meaning.

Files in the project:

  • main.py: Contains the VectorStore class definition.
  • app.py: Demonstrates using the VectorStore class for sentence similarity search.

Example Output

Query sentence:  Mango is the best fruit.
Similar sentences:
mango is my favorite fruit.: Similarity = 0.8165
I eat mangoes.: Similarity = 0.7071

Key Concepts

  1. VectorStore Class: Provides efficient storage and retrieval of vectors, optimized for similarity search.
  2. Text Vectorization: Converts sentences into numerical vectors representing their semantic content.
  3. Cosine Similarity: Measures the similarity between vectors.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载