Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Introduction to Qdrant (Vector Database) Using Python
Rating: 4.1 out of 5(48 ratings)
283 students

Introduction to Qdrant (Vector Database) Using Python

Learn the basics of Qdrant (Vector Database), Indexing the data, snapshots, Python Client with examples and more !
Created byVijay Anand Ramakrishnan
Last updated 3/2024
English

What you'll learn

  • Basics of Vector databases
  • Introduction to Qdrant and Installing Qdrant
  • Collections, Segments and Points in Qdrant
  • Vector and payload fields in a Collection
  • Vector and Payload indexing
  • Vector similarity search on a Collection and filtering the results based on payload
  • Quantizing the vectors
  • Configuring Qdrant Server

Course content

5 sections • 24 lectures • 1h 45m total length

  • Introduction2:26
  • Vector Databases4:03
  • Components of a Vector Databases3:10

    Explore the components of a vector database—storage and indexing, search and retrieval of similar vectors, APIs, role-based access control, and monitoring—contrasting with relational systems.

  • Vector Embeddings2:22

    Explore how vector embeddings convert unstructured data into fixed-length vectors using embedding models, revealing semantic similarity through vector distances and enabling image and audio search, recommendations, and question answering systems.

  • Vector Embeddings
  • Vector Similarity Metrics2:24

    Explore vector similarity metrics by comparing two vectors in a two-dimensional vector space using Euclidean distance, cosine similarity, and dot product to quantify similarity scores.

  • Vector Similarity

Requirements

  • Python
  • Fundamentals of Docker and Docker Compose
  • Basic Linux commands

Description

Qdrant is an Open Source vector database with in-built vector similarity search engine. Qdrant is written in Rust and is proven to be fast and reliable even under high load in production environment. Qdrant provides convenient API to store, search and manage vectors along with the associated payload for the vectors.


This course will provide you with solid practical Skills in Qdrant using its Python interface.  Before you begin, you are required to have basic knowledge on


  • Python Programming

  • Linux Commands

  • Docker and Docker Compose


Some of the highlights of this course are


  • All lectures have been designed from the ground up to make the complex topics easy to understand

  • Ample working examples demonstrated in the video lectures

  • Downloadable Python notebooks for the examples that were used in the course

  • Precise and informative video lectures

  • Quiz at the end of every important video lectures

  • Covers a wide range of fundamental topics in Qdrant


After completing this course, you will be able to


  • Install and work with Qdrant using Python

  • Manage Collections in Qdrant

  • Perform vector search on vectors stored in Qdrant collection

  • Filter the search results

  • Create and manage snapshots

  • Use Qdrant to build scalable real-world AI apps


This course will be updated periodically and enroll now to get lifelong access to this course!

Who this course is for:

  • Data Scientists
  • AI Engineers
  • Machine Learning Engineers
  • MLOps Engineers
  • Data Scientists
  • Anyone who is motivated to learn and work with a Vector database

Report abuse