Learn to build and deploy vector search applications using Qdrant, a high-performance vector database and search engine. Master the fundamentals of vector embeddings, similarity search, and distance metrics while progressing through hands-on projects including a movie recommendation engine. Explore advanced indexing techniques with HNSW (Hierarchical Navigable Small World) algorithms, implement filterable search capabilities, and discover how to combine dense and sparse vectors for hybrid search solutions. Gain expertise in vector quantization for storage optimization, reranking techniques for improved relevance, and strategies for ingesting billions of vectors in large-scale applications. Practice advanced retrieval methods including multivectors and late interaction patterns, then apply your knowledge in a comprehensive final project. Enhance your learning through specialized modules featuring industry partnerships with LlamaIndex for RAG patterns and agent workflows, Unstructured.io for enterprise document processing, Superlinked for multi-modal encoders, Camel AI for multi-agent systems, Quotient for RAG monitoring, Jina AI for advanced embeddings, Haystack for agentic search, and Tensorlake for knowledge graph integration.

Syllabus

Qdrant Essentials | Course Overview
Qdrant Essentials | Qdrant Cloud Overview
Qdrant Essentials | Building Simple Vector Search in Qdrant
Qdrant Essentials | Creating Vectors and Embeddings for Vector Search in Qdrant
Qdrant Essentials | Finding Vector Similarity with Distance Metrics
Qdrant Essentials | Chunking Data for Better Vector Search Results
Qdrant Essentials | Build a Movie Recommendation Engine
Qdrant Essentials | Fast Vector Search with Qdrant HNSW Indexing
Qdrant Essentials | Combine Search & Filtering with Qdrant Filterable HNSW
Qdrant Essentials | Sparse Vector Explanation and Usage
Qdrant Essentials | Increase Search Relevance with Sparse Vectors in Qdrant
Qdrant Essentials | Hybrid Search Explanation and Overview
Qdrant Essentials | Implementing Hybrid Search in Qdrant: Merging Dense & Sparse Vectors
Qdrant Essentials | Reduce Storage & Maintain Accuracy with Qdrant Vector Quantization
Qdrant Essentials | Improve Search Relevance with Reranking in Qdrant
Qdrant Essentials | Ingest Billions of Vectors into Qdrant for Large-Scale Applications
Qdrant Essentials | Advanced Retrieval: Multivectors & Late Interaction in Qdrant
Qdrant Essentials | Final Project
Qdrant x LlamaIndex | Advanced RAG Patters and Agent Workflows
Qdrant x Unstructured.io | Process and Vectorize Documents with Enterprise ETL and Vector Search
Qdrant x Superlinked | Beyond Text: Mixture of Encoders
Qdrant x Camel AI | Multi-Agent Systems with Auto-Retrieval
Qdrant x Quotient | Inside RAG Monitoring and Evaluation
Qdrant x Jina AI | Multivector and Late Interaction Embeddings
Qdrant x Haystack | Build Smarter Recommenders with Agentic Search
Qdrant x Tensorlake | Improve Collection Querying with Knowledge Graphs