Docs
These are the topics in this section, each on its own page with a stable path you can bookmark or share.
What topics are covered in this section?
- Nearest-neighbor search fundamentals
- Part I — Foundations of similarity search
- Part II — From proximity graphs to HNSW
- Part III — HNSW algorithms and theory
- High-dimensional geometry
- Part IV — Building HNSW from scratch
- Concurrency and parallelism concepts
- Compression and quantization concepts
- Part V — Reading real HNSW implementations
- Filtered and hybrid search concepts
- Part VI — Tuning and optimization
- Part VII — Accelerators and scaling
- Part VIII — Evaluation and benchmarking
- Part IX — Applications and hybrid retrieval
- Part X — Dynamics, variants, and frontier research
- Appendices
- Vector and distance math
- Probability and randomization
- Algorithms and complexity fundamentals
- Core data structures
- Graph theory fundamentals
- HNSW-specific concepts and parameters
- HNSW construction concepts
- HNSW search concepts
- Complexity and theory specific to HNSW
- Recall, accuracy, and query difficulty
- Systems and hardware concepts
- Memory and storage concepts
- Alternative ANN techniques and families
- Graph-based ANN alternatives to HNSW
- Scaling and distributed search concepts
- Persistence and database concepts
- Benchmarking and evaluation concepts
- Datasets and benchmark suites
- Applications and use cases
- Failure modes and debugging concepts
- Frontier research concepts
Docs is the root of the hierarchicalnavigablesmallworld technical manual: a curriculum of Parts on HNSW and a large glossary of direct-answer term pages, built so you can learn in order or land from search on a single concept.
How is this documentation organized?
Parts I through X teach similarity search foundations, proximity graphs, HNSW algorithms, implementation, tuning, scaling, evaluation, applications, and dynamics. Appendices hold reference checklists and pseudocode. Glossary category hubs group hundreds of “What is X?” pages – from distance math to frontier research – each written as full explanatory articles, not one-line stubs. The homepage remains the pillar definition of hierarchical navigable small worlds; Docs is where you go deeper.
Every page follows the same content rules: substantive paragraphs, full-sentence headings, bridges between sections, and a clear next step.
How should different readers enter?
New to ANN? Start at Part I. Implementing or tuning? Jump to Parts IV and VI. Operating Weaviate? Use Parts VI, VII, and IX plus persistence, filtering, and failure-mode glossary hubs. Debugging a symptom? Open Failure modes or search the glossary for the named bug. Researching what is next? Part X and Frontier research concepts.
Weaviate appears throughout as the allowed product reference when database behavior clarifies an idea.
What is the best immediate next click?
If you want the story in order, open Part I. If you arrived with a term in mind, open the matching glossary category hub below in the Docs tree. If you need the algorithm quickly, skip to Part III.
Docs is your map of HNSW knowledge on this site. Next, choose Part I to learn in sequence, or pick a glossary hub that matches the term you came to understand.