Veronika K.
After 365:
Finance Student | VŠE, Prague
See all reviews
Online Course
Introduction to Vector Databases with Pinecone
with
Elitsa Kaloyanova
Gaining insights from data is crucial for businesses. With emerging AI technologies, the importance of vectorization and vector databases is set to increase significantly. In this Vector Databases with Pinecone course, you’ll have the opportunity to explore the Pinecone database—a leading vector solution—and learn to implement a vector database for semantic search using real data.
1,994 students already enrolled
Skill level:
Advanced
Duration:
2 hours
-
Lessons (2 hours)
- Lessons (2 hours)
CPE credits:
2.5
CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of
professionals must earn to maintain their licenses and stay current with regulations and best
practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's
official website: www.nasbaregistry.org
CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of
professionals must earn to maintain their licenses and stay current with regulations and best
practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's
official website: www.nasbaregistry.org
Accredited
certificate
What you learn
- Understand what vector databases are and how they compare to SQL and NoSQL.
- Explore vector spaces, distance metrics, and embedding algorithms.
- Use Pinecone and Python to build a semantic search engine.
- Embed and upsert custom data, then run similarity searches.
- Apply vector searches to real use cases like images, courses, and biomedicine.
Topics & tools
AIPythonJupyterHuggingfaceVector DatabasesEmbedding algorithmsSemantic searchPinecone
Your instructor
Senior Data Scientist at 365 Data Science | Computational Biologist | Data Visualization Expert
Track record
Bringing real-world expertise from leading global companies
Academic background
Master's degree, Bioinformatics
Course OVERVIEW
Description
CPE Credits: 2.5
Field of Study: Information Technology
Delivery Method: QAS Self Study
Delivery Method: QAS Self Study
In this Introduction to Vector Databases with Pinecone course, you’ll explore cutting-edge vector databases, focusing on embeddings and their vectorization roles alongside various embedding algorithms. Utilize the Pinecone AI (a user-friendly managed vector database) and Python to build custom databases and develop a semantic search algorithm with our 365 data. Examine different data vectorization methods at various aggregation levels. Additionally, I’ll show you how to upsert sections of the Hugging Face FineWeb dataset, providing a practical Hugging Face tutorial on working with real-world data.
Prerequisites
- Python (version 3.8 or later), Pinecone account and API key, and a code editor or IDE (e.g., VS Code or Jupyter Notebook)
- Intermediate Python skills are required.
- Familiarity with embeddings, APIs, or LangChain is helpful but not mandatory.
Advanced preparation
Curriculum
32 lessons
1 exam
- 2. Basics of Vector Space and High-Dimensional Data15 minDive into the core concepts of vector spaces and high-dimensional data. This section introduces vector spaces, covers distance metrics in these spaces, and explains vector embeddings—setting the stage for working with vector databases.15 minDive into the core concepts of vector spaces and high-dimensional data. This section introduces vector spaces, covers distance metrics in these spaces, and explains vector embeddings—setting the stage for working with vector databases.Introduction to vector space FreeDistance metrics in vector space FreeVector embeddings walkthrough
- 3. Introduction to The Pinecone Vector Database29 minThis section offers a comprehensive overview of vector database engines, focusing on Pinecone. You’ll learn about Pinecone’s features, register and create an index, and connect to Pinecone using Python. Practical lessons include creating and deleting indices, upserting data, and embedding algorithms with data from various sources, including CSV files.29 minThis section offers a comprehensive overview of vector database engines, focusing on Pinecone. You’ll learn about Pinecone’s features, register and create an index, and connect to Pinecone using Python. Practical lessons include creating and deleting indices, upserting data, and embedding algorithms with data from various sources, including CSV files.Vector databases, comparisonPinecone registration, walkthrough and creating an IndexConnecting to Pinecone using PythonCreating a new indexCreating and deleting a Pinecone index using PythonUpserting data to a pinecone vector databaseGetting to know the fine web data set and loading it to JupyterUpserting data from a text file and using an embedding algorithm
- 4. Case Study Semantic Search with Pinecone and Custom Data62 minThrough a detailed case study, this section of our Vector Databases with Pinecone course explores semantic search using Pinecone. You'll be introduced to the case study's dataset, learn about data loading and preprocessing, and compare different embedding algorithms. The practical application includes embedding data, upserting it to Pinecone, performing similarity searches, and updating the vector database. Advanced topics cover using different embedding algorithms and exploring vector databases for recommendation systems, semantic image search, and biomedical research.62 minThrough a detailed case study, this section of our Vector Databases with Pinecone course explores semantic search using Pinecone. You'll be introduced to the case study's dataset, learn about data loading and preprocessing, and compare different embedding algorithms. The practical application includes embedding data, upserting it to Pinecone, performing similarity searches, and updating the vector database. Advanced topics cover using different embedding algorithms and exploring vector databases for recommendation systems, semantic image search, and biomedical research.Introduction to semantic searchIntroduction to the case study – smart search for data science coursesGetting to know the data for the case studyData loading and preprocessingPinecone Python APIs and connecting to the Pinecone serverEmbedding algorithmsEmbedding the data and upserting the files to PineconeSimilarity search and querying the dataHow to update and change your vector databaseData preprocessing and embedding for courses with section dataCourses and Sections Together AssignmentUpserting the new updated files to PineconeSimilarity search and querying courses and sections dataWeighted semantic search assignmentUsing the BERT embedding algorithmVector database for recommendation enginesVector database for semantic image searchVector database for biomedical research
- 5. Course exam30 min30 minCourse exam
Free lessons
1.1 Introduction to the course
3 min
1.2 Database comparison: SQL, NoSQL, and Vector
5 min
1.3 Understanding vector databases
4 min
2.1 Introduction to vector space
5 min
2.2 Distance metrics in vector space
6 min
2.3 Vector embeddings walkthrough
4 min
9 in 10
of our graduates landed a new AI & data job
after enrollment
#1 most reviewed
AI and data learning platform on Trustpilot.
94%
of AI and data science graduates
successfully change
or advance their careers.
ACCREDITED certificates
Craft a resume and LinkedIn profile you’re proud of—featuring certificates recognized by leading global
institutions.
Earn CPE-accredited credentials that showcase your dedication, growth, and essential skills—the qualities
employers value most.
Certificates are included with the Self-study learning plan.
How it WORKS
Student REVIEWS
