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 |
Ready to try Qdrant?