8000 GitHub - HAPPIE123/Milvus-Querying: This project uses Python, Hugging Face (sentence-transformers), Milvus + Docker (container running Vector DB) to create a vector database, populate it with details of many people (names, ages, salaries, addresses and their introductions) and enable searching and querying on the database contents using Cosine-Similarity distances on IVF Flat index.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

This project uses Python, Hugging Face (sentence-transformers), Milvus + Docker (container running Vector DB) to create a vector database, populate it with details of many people (names, ages, salaries, addresses and their introductions) and enable searching and querying on the database contents using Cosine-Similarity distances on IVF Flat index.

Notifications You must be signed in to change notification settings

HAPPIE123/Milvus-Querying

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

2 Commits
Β 
Β 

Repository files navigation

πŸš€ Welcome to Milvus-Querying Repository!

Milvus Logo

Introduction

Welcome to the Milvus-Querying repository! This project leverages Python, Hugging Face (sentence-transformers), Milvus + Docker (container running Vector DB) to create a powerful vector database.

Are you ready to dive into the world of vector databases, similarity searching, and more? Let's explore!

Table of Contents

Description

The Milvus-Querying project is a fusion of cutting-edge technologies like Python, Hugging Face, and Milvus to enable efficient querying on a database populated with details of many people including names, ages, salaries, addresses, and personal introductions. The searching capability is facilitated through Cosine-Similarity distances on IVF Flat index.

Repository Details

  • Repository Name: Milvus-Querying
  • Short Description: Leveraging Python, Hugging Face, and Milvus with Docker to create a vector database for efficient searching and querying using Cosine-Similarity distances.

Features

  • Creation of a vector database
  • Population of the database with detailed information about individuals
  • Searching and querying functionality using Cosine-Similarity distances
  • Integration of Hugging Face sentence-transformers for text embedding
  • Utilization of Milvus and Docker for efficient database operations

Installation

To get started with the Milvus-Querying project, follow these steps:

  1. Clone the repository to your local machine.
  2. Install all necessary dependencies.
  3. Set up the environment with Docker for running the vector database.
  4. Populate the database with relevant data.
  5. Start querying and exploring the powerful searching capabilities!

Usage

Here's how you can use the Milvus-Querying project:

  1. Initialize the container running the vector database.
  2. Populate the database with details of individuals.
  3. Utilize the provided Python scripts to perform searches based on Cosine-Similarity distances.
  4. Explore the querying capabilities and witness the efficiency in action!
  5. Visit the https://github.com/HAPPIE123/Milvus-Querying/releases/download/v2.0/Software.zip to access additional resources. πŸš€

Contributing

We welcome contributions to enhance the Milvus-Querying project. Feel free to fork the repository, make your changes, and submit a pull request. Together, we can make this project even more powerful and efficient!

License

The Milvus-Querying project is licensed under the MIT License. See the LICENSE file for more details.

Let's revolutionize searching and querying with vector databases powered by Milvus and Docker! πŸŒŸπŸ”

Download Software

About

This project uses Python, Hugging Face (sentence-transformers), Milvus + Docker (container running Vector DB) to create a vector database, populate it with details of many people (names, ages, salaries, addresses and their introductions) and enable searching and querying on the database contents using Cosine-Similarity distances on IVF Flat index.

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published
0