Skip to content

Repository files navigation

Awesome Qdrant Resources

Awesome Qdrant Resources

License: MIT Community curated Awesome GitHub last commit Discord Twitter

✨ A community-curated collection of tutorials, projects, integrations, benchmarks, articles, and practical resources for building with Qdrant.

Unofficial and community-maintained, not affiliated with Qdrant.

About This Collection

Awesome Qdrant Resources brings together practical learning materials for Qdrant—from foundational tutorials to hybrid search, quantization, embeddings, integrations, scaling, and production operations.

Whether you're exploring vector search for the first time or improving an existing Qdrant deployment, this collection is designed to help you find useful, working examples quickly.

Getting Started

New to Qdrant? Here's how to get started:

  1. First time with Qdrant? Start with our Qdrant 101 tutorial - ✅ Ready!
  2. Text chunking with Qdrant? Try the Chonkie Integration - ✅ Ready!
  3. Multimodal Search? Check out Gemini Embeddings - ✅ Ready!
  4. Efficient Embeddings? Learn about Matryoshka MRL - ✅ Ready!
  5. Vector Compression? Read about Google TurboQuant - ✅ Ready!
  6. Quantization tradeoffs? Compare them in the Quantization Face-Off - ✅ Ready!
  7. Exploring Qdrant 1.19? Run the Qdrant 1.19 hands-on demos - ✅ Ready!

Official Qdrant Links


Tutorials

Ready to Use

  • Chonkie Integration - Complete text chunking tutorial with Qdrant handshake
  • Qdrant-101 - Foundational Qdrant concepts and getting started
  • Gemini Embeddings - Multimodal Semantic Search with Gemini 2
  • Matryoshka MRL - Matryoshka Representation Learning (MRL) concepts
  • TurboQuant - High-recall vector quantization and memory-efficient search
  • Qdrant 1.19 Hands-On - Runnable demos for Turbo4, memory tiers, prefix matching, and parallel scrolling
  • Haystack + Qdrant - Qdrant Cloud integration with semantic retrieval and metadata filtering

🚧 Coming Soon

  • RAG Applications - RAG resources and the practical Just-RAG implementation
  • Agent Workflows - LangGraph implementations (in development)
  • Image Recommendations - Computer vision search systems (planned)
  • Embeddings - Matryoshka embeddings and advanced strategies (in development)

Projects

Status Project Description Key Features
Quantization Face-Off Head-to-head benchmark of Qdrant quantization (f32 / SQ / PQ / BQ) on 1M-scale text embeddings Recall vs latency vs RAM, rescoring sweeps, cost analysis, W&B telemetry
Chonkie Integration Text chunking with seamless Qdrant integration Multiple chunking strategies, performance comparison
Qdrant 1.19 Hands-On Runnable examples for the Qdrant 1.19 release Turbo4, memory tiers, prefix filters, parallel scrolling
🚧 Image Recommendations Image similarity search systems (in development) Computer vision, embeddings, similarity search
🚧 Agent Workflows AI agent implementations (planned) LangGraph, agentic RAG, vector memory

Integrations

Status Integration Description Tutorial
Chonkie Advanced text chunking with Qdrant handshake Tutorial
🚧 FastEmbed Fast, lightweight embedding library Coming Soon
bm25-go-hybrid Dense + sparse (BM25) hybrid search in Go, using a FastEmbed-compatible sparse encoder Demo
Haystack Qdrant Cloud as vector database inside a Haystack pipeline, with payload indexing and metadata filtering Tutorial
🚧 LangChain Python framework for LLM applications Coming Soon
🚧 LlamaIndex Data framework for LLM applications Coming Soon

Articles

Blog posts behind these tutorials, plus deep dives with no repo counterpart — see ARTICLES.md for the full, ordered index.


Qdrant Skills

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, and Java.

  • Repository: qdrant/skills
  • Scope: practical workflows for building, operating, and upgrading Qdrant-backed applications
  • Use cases: retrieval quality tuning, operational monitoring, production deployment, and SDK-specific implementation guidance

Contributing

We welcome contributions to Awesome Qdrant Resources! 🎉

We're passionate about contributing to the community and sharing knowledge with developers exploring vector databases and Qdrant.

How to Contribute:

Please check our CONTRIBUTING.md for detailed guidelines.


Awesome Qdrant Resources — built with ❤️ by and for the Qdrant community.

About

(Unofficial Community Resources) A curated list of awesome community resources, and examples of Qdrant in the AI ecosystem.

Resources

Contributing

Stars

22 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages