Similarity Search Courses and Certifications

Document Processing and Retrieval with LangChainGo

Build a LangChainGo pipeline that chunks documents, creates embeddings, retrieves relevant passages, and answers questions with contextual prompts.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

Document Processing and Retrieval with LangChain in JavaScript

Build document question-answering workflows in JavaScript with LangChain by splitting documents, generating embeddings, searching with FAISS, and prompting chat models with retrieved context.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

Storing and Managing Embeddings in PostgreSQL with pgvector

Store embeddings in PostgreSQL with pgvector and compare products using cosine, inner-product, and L1 similarity queries.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

Storing, Indexing, and Managing Vector Data with Pinecone

Hands-on Pinecone workflows for creating indexes, storing and querying embeddings, filtering metadata, and maintaining vector data.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

Implementing Semantic Search with Qdrant

Implement advanced semantic search in Qdrant with hybrid metadata-vector retrieval, document reranking, multi-query expansion, and multi-field filtering.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

James Briggs

Vector Similarity Search and Faiss Course

Master vector similarity search techniques and Faiss implementation through hands-on practice with traditional methods, advanced indexing, and performance optimization strategies.

• YouTube
• 6 hours 16 minutes
• Self-Paced
• Free Video

Vector Databases for RAG: An Introduction

103 ratings at Coursera

Build a recommendation system with ChromaDB: create collections, manage embeddings from a Hugging Face model, and run similarity searches that power RAG retrieval.

• Coursera
• 2 weeks, 5 hours a week
• Self-Paced
• Paid Course

Vector Databases for RAG: An Introduction

103 ratings at Coursera

Build a food recommendation system with Chroma DB: create collections, manage embeddings, and run similarity searches that power retrieval in RAG applications.

• Coursera
• 2 weeks, 5 hours a week
• Self-Paced
• Paid Course

Vector Databases: An Introduction with Chroma DB

52 ratings at Coursera

Learn vector database fundamentals and how they differ from traditional databases, then set up environments and run updates, deletes, collections, and similarity searches in Chroma DB.

• Coursera
• 2 weeks, 2 hours a week
• Self-Paced
• Paid Course

Vector Search with Relational Databases using PostgreSQL

24 ratings at Coursera

Run vector similarity searches in PostgreSQL: create embeddings and collections, use tsvector and tsquery, and bulk insert with pgvector for Node.js and psycopg2.

• Coursera
• 6 hours
• Self-Paced
• Paid Course

Vector Database Projects: AI Recommendation Systems

16 ratings at Coursera

Build two recommendation systems — food ordering and job search — using Chroma DB and Hugging Face NLP models to generate embeddings and run similarity searches.

• Coursera
• 2 weeks, 3 hours a week
• Self-Paced
• Paid Course

Vector Database Projects: AI Recommendation Systems

16 ratings at Coursera

Build two ChromaDB recommendation systems: generate embeddings for a collection and run similarity searches over user search terms with NLP algorithms.

• Coursera
• 2 weeks, 3 hours a week
• Self-Paced
• Paid Course

Vector Databases: from Embeddings to Applications

12 ratings at Coursera

Build applications on vector databases: form embeddings, apply similarity search techniques, use fast search algorithms over large datasets, and create RAG and multilingual search apps.

• Coursera
• 1 hour 3 minutes
• Self-Paced
• Free Online Course

Packt

Vector Databases Deep Dive

Explore how vector databases work: vectors, embeddings, distance metrics, indexing strategies, and KNN versus ANN search, with hands-on demos in Pinecone, Qdrant, Milvus, and Weaviate.

• Coursera
• 8 weeks, 1 hour a week
• Self-Paced
• Paid Course

Coursera

Vector Database Foundations and Core Concepts

Build vector search systems: generate embeddings from text and images, compare cosine, dot-product and Euclidean metrics, implement FAISS and Annoy, and tune HNSW parameters.

• Coursera
• 6 weeks, 2 hours a week
• Self-Paced
• Paid Course