Qdrant Tutorial Repository
Basic Tutorials
Get up and running with Qdrant in minutes.
| Tutorial | Objective | Stack | Time | Level |
|---|---|---|---|---|
| Qdrant Local Quickstart | Basic CRUD operations and local deployment. | Any | 10m | Beginner |
| Qdrant Cloud Quickstart | Basic CRUD operations on Qdrant Cloud. | Any | 10m | Beginner |
| Semantic Search 101 | Build a search engine for science fiction books. | Any | 10m | Beginner |
| Multimodal Search | Build a pipeline to search across text and images modalities | Python | 15m | Beginner |
| Hybrid Search | Get started with hybrid search. | Any | 15m | Beginner |
| Hybrid Search with Reranking | Rerank hybrid search results for improved accuracy. | Any | 40m | Intermediate |
| FastEmbed | Generate embeddings on CPU, then embed, index, and search with qdrant-client. | Python | 15m | Beginner |
Search Engineering Tutorials
Master vector search modalities, reranking, and retrieval quality.
| Tutorial | Objective | Stack | Time | Level |
|---|---|---|---|---|
| Relevance Feedback | Relevance Feedback Retrieval in Qdrant | Python | 30m | Intermediate |
| Collaborative Filtering | Collaborative filtering using sparse embeddings. | Python | 45m | Intermediate |
| Multivector Document Retrieval | PDF RAG using ColPali and embedding pooling. | Python | 30m | Intermediate |
| Measuring ANN Recall | Measure ANN recall with the Web UI and tune HNSW parameters. | Web UI | 15m | Beginner |
| Multivectors and Late Interaction | Effective use of multivector representations. | Python | 30m | Intermediate |
| Compressed Multivector Search | Store a ColBERT multivector as turbo4 and query it alongside a sparse vector with the Query API. | Python | 25m | Intermediate |
| Multi-Representation Search | Fuse title, summary, chunk, and tag vectors with named vectors and the Query API. | Python | 45m | Intermediate |
| Branch-Aware Search | Scope search to a branch’s live view in a versioned corpus, inherited from its ancestors. | Python | 25m | Intermediate |
| Indexing Payloads of Random Shape | Index open-ended payload keys with one nested key-value array instead of one index per key. | Python | 25m | Intermediate |
| Deterministic Collection Slicing | Split a collection into deterministic subsets for parallel scroll and reproducible sampling. | Python | 20m | Intermediate |
| Sparse Fine-Tuning, Part 1: Why Sparse Embeddings Beat BM25 | Why sparse embeddings suit e-commerce search, and how SPLADE works. | Python | 10m | Advanced |
| Sparse Fine-Tuning, Part 2: Training SPLADE on Modal | Train a SPLADE model on Amazon ESCI with Sentence Transformers on Modal GPUs. | Python | 45m | Advanced |
| Sparse Fine-Tuning, Part 3: Evaluation and Hard Negatives | Evaluate fine-tuned SPLADE in Qdrant and add hard negative mining. | Python | 30m | Advanced |
| Sparse Fine-Tuning, Part 4: Specialization vs Generalization | Test cross-domain generalization and decide when to fine-tune. | Python | 10m | Advanced |
| Sparse Fine-Tuning, Part 5: From Research to Product | Fine-tune SPLADE for your own catalog with the qdrant-finetune CLI. | Python | 2h | Advanced |
| Query Decomposition | Answer multi-hop questions by retrieving in steps and fusing the per-hop results. | Python OpenAI | 15m | Intermediate |
| Multimodal Food Search Demo | See how CLIP, grouped queries, and recommendation strategies power a food discovery app. | Python | 20m | Beginner |
Operations & Scale
Production-grade management, monitoring, and high-volume optimization.
| Tutorial | Objective | Stack | Time | Level |
|---|---|---|---|---|
| Snapshots | Create and restore collection snapshots. | Python | 20m | Beginner |
| Embedding Model Migration | Use your new model with zero downtime. | Any | 40m | Intermediate |
| Blue-Green Cluster Deployment | Deploy changes to a new cluster and switch traffic with zero production risk. | Any | 30m | Intermediate |
| Time-Based Sharding | Efficiently manage time-series data with user-defined sharding. | Any | 1h | Intermediate |
| Large-Scale Search | Cost-efficient search for LAION-400M datasets. | Any | 48h | Advanced |
| GPU-Accelerated HNSW Indexing | Speed up HNSW index builds and compare cost against CPU. | Python | 45m | Intermediate |
| Secure a Self-Hosted Instance | Enable TLS, API keys, and JWT access control. | Any | 45m | Intermediate |
| Incremental Embedding Updates | Sync embeddings with changing raw text data. | Any | 25m | Beginner |
| Prevent Unoptimized Usage | Stop bulk uploads from slowing down search without losing data. | Python | 20m | Intermediate |
| Scaling and Monitoring Hybrid Cloud | Resize CPU, memory, and disk, and know what to monitor first. | Kubernetes | 25m | Intermediate |
| Securing and Exposing a Hybrid Cloud Cluster | Set up API key authentication, database-level TLS, and TLS-terminating ingress on a self-managed Hybrid Cloud cluster. | Kubernetes | 25m | Intermediate |
| Qdrant Cloud Prometheus Monitoring | Observability with Prometheus and Grafana. | Prometheus | 30m | Intermediate |
| Monitoring with Grafana and Prometheus | Observability for hybrid/private cloud setups. | Prometheus | 30m | Intermediate |
| Monitoring with Datadog | Observability for hybrid/private cloud setups with Datadog. | Datadog | 20m | Intermediate |
| Kafka Streaming into Qdrant | Stream real-time data into Qdrant with the Kafka Sink Connector. | Kafka | 60m | Advanced |
Develop & Implement
Core tools and APIs for building with Qdrant.
| Tutorial | Objective | Stack | Time | Level |
|---|---|---|---|---|
| Build a Semantic Search API | Deploy a search service for company descriptions. | FastAPI | 30m | Beginner |
| Build a Hybrid Search API | Combine dense and sparse search. | FastAPI | 20m | Beginner |
| Async API | Use Asynchronous programming for efficiency. | Python | 25m | Intermediate |
| Semantic Search for Code | Navigate codebases using vector similarity. | Python | 45m | Intermediate |
| Serverless Semantic Search | Deploy a Rust search function on AWS Lambda with Cohere and Qdrant. | Rust | 45m | Intermediate |
| Semantic Search As You Type | Build search-as-you-type with a prefix cache and prioritized batch queries. | Python | 30m | Intermediate |
Migrate to Qdrant
Move your vectors from other databases and keep them in sync.
| Tutorial | Objective | Stack | Time | Level |
|---|---|---|---|---|
| Migration Tool Overview | Migrate vectors from any supported source. | CLI | Varies | Intermediate |
| From Pinecone | Migrate from Pinecone serverless indexes. | CLI | 15m | Intermediate |
| From Weaviate | Migrate from Weaviate (pre-create collection). | CLI | 20m | Intermediate |
| From Milvus | Migrate from Milvus/Zilliz with partitions. | CLI | 15m | Intermediate |
| From Elasticsearch | Migrate dense vectors from Elasticsearch. | CLI | 15m | Intermediate |
| From pgvector | Migrate from PostgreSQL pgvector tables. | CLI | 15m | Intermediate |
| Migration Verification | Verify data integrity and search quality. | Python | 1h+ | Intermediate |
| Keeping Postgres in Sync | Keep Postgres and Qdrant in sync. | Python | 30m | Intermediate |
Ready to try Qdrant?