Skip to content

README.md

Latest commit

 

History

History
83 lines (62 loc) · 6.5 KB

README.md

File metadata and controls

83 lines (62 loc) · 6.5 KB

Qdrant Tutorials

This directory contains comprehensive tutorials covering various Qdrant use cases and integrations. All tutorials follow the three-part Feynman teaching structure for optimal learning:

  1. Part 1: Core Concept - Why the technique matters and real-world applications
  2. Part 2: Practical Walkthrough - Step-by-step implementation guide
  3. Part 3: Mental Models & Deep Dives - Advanced concepts and optimization strategies

Tutorial Index

# Tutorial Description Source
01 Getting Started Introduction to Qdrant basics and core concepts Source
02 Text Data Working with text embeddings and semantic search Source
03 Audio Data Audio processing and similarity search Source
04 Image Data Image embeddings and visual search Source
05 Binary Quantization Memory optimization with binary quantization Source
06 Code Search Semantic code search and analysis Source
07 Collaborative Filtering Building recommendation systems Source
08 DSPy Medical Bot Medical AI assistant with DSPy framework Source
09 Agentic RAG Multi-agent RAG systems with CrewAI Source
10 ColPali Binary Quantization Optimizing ColPali with binary quantization Source
11 Data Preparation Webinar Comprehensive data preparation techniques Source
12 E-commerce Reverse Image Search Visual product search with CLIP Source
13 Extractive QA Question answering with retriever-reader architecture Source
14 GraphRAG with Neo4j Knowledge graphs with vector search Source
15 LlamaIndex Recency Temporal-aware Q&A systems Source
16 Multimodal Search Cross-modal search capabilities Source
17 Multivector Representation Advanced dense and sparse vector combinations Source
18 PDF Retrieval at Scale Scalable document processing with vision models Source
19 RAG with Qdrant and DeepSeek Building RAG systems with DeepSeek LLM Source
20 Self Query Natural language query understanding Source
21 Sparse Vectors Movies Recommendation Collaborative filtering with sparse vectors Source

Tutorial Categories

Fundamentals

  • Getting Started, Text Data, Audio Data, Image Data

Performance Optimization

  • Binary Quantization, Multivector Representation

Advanced Applications

  • Code Search, Medical Bot, Agentic RAG, GraphRAG

Specialized Techniques

  • Multimodal Search, Self Query, Temporal Processing

Real-World Systems

  • E-commerce Search, PDF Processing, Recommendation Systems

Prerequisites

  • Basic Python programming knowledge
  • Understanding of vector embeddings concept
  • Familiarity with machine learning fundamentals
  • Docker (for local Qdrant deployment)

Getting Started

  1. Install Qdrant: Follow the installation guide
  2. Choose a tutorial: Start with Getting Started for basics
  3. Set up environment: Each tutorial includes setup instructions
  4. Follow along: Tutorials include complete, runnable code examples

Additional Resources

Contributing

These tutorials are based on the official Qdrant Examples repository. To suggest improvements or report issues:

  1. Check the original example source
  2. Create an issue in the examples repository
  3. Follow the contribution guidelines

License

These tutorials are provided under the same license as the Qdrant Examples repository.