Project
Vector Database with Qdrant
Hard
31 completions
~ 14 hours
4.5Learn the fundamentals of Qdrant, a vector-first database, including data loading, similarity matching, natural language searching, and building a simple FastAPI interface.
Provided by
JetBrains Academy
About
In this project, you will develop a solution for semantic search using Qdrant, using OpenAI's embeddings API to process data, perform similarity searches, and construct an interface that enables retrieval of data points through natural language queries and filtering techniques.
Graduate project
This project covers the core topics of the Introduction to AI Engineering with Python course, making it sufficiently challenging to be a proud addition to your portfolio.
At least one graduate project is required to complete the course.
What you'll learn
Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:
Parse the dataset and load it into Qdrant
Find the entries that are the closest to an existing embedding
Use OpenAI's embedding model to transform natural langauge queries and find the most similar entries in the database
Augment the search with a payload filter to find more relevant entries
Write a simple FastAPI wrapper to interact with the database
Reviews
4 months ago
Overall good projects, but i was struggling with qdrant memory issues for 5 days until i found out a way to insert data properly by modifying docker memory allocation size + batch size. I will see this project in my nightmares, but I liked it.
4 months ago
The project offers practical, hands-on training on vector databases, and most importantly, vector search! Wrapping everything up in an API endpoint to send requests to was super-useful, too.
5 months ago
I have learned a lot, vector databases, OpenAI API, Pydantic, and FastAPI
4.5
Learners who completed this project within the Introduction to AI Engineering with Python course rated it as follows: