pgvector
/pgvector
Obsługuje rozszerzenie pgvector dla PostgreSQL: typy wektorowe, operatory odległości, indeksy HNSW i IVFFlat, wyszukiwanie najbliższych sąsiadów oraz biblioteki klienckie.
- Autor
- itechmeat ↗
- Repozytorium
- llm-code ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 24.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 12
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 7
Brak sygnałów. Repozytorium zmienione 24.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Obsługuje rozszerzenie pgvector dla PostgreSQL: typy wektorowe, operatory odległości, indeksy HNSW i IVFFlat, wyszukiwanie najbliższych sąsiadów oraz biblioteki klienckie.
Oryginalny opis (EN)
pgvector Postgres extension. Covers vector types, distance operators, indexing (HNSW/IVFFlat), and client library usage. Use when storing vectors in PostgreSQL, running nearest-neighbor searches, or configuring HNSW/IVFFlat indexes. Keywords: pgvector, PostgreSQL, vector search, HNSW, IVFFlat.
Jak działa
- Quick Navigation
- When to Use
- Quick Start (already installed)
- Critical Prohibitions / Gotchas
- Release Notes
- Links
Podgląd SKILL.md
---
name: pgvector
description: "pgvector Postgres extension. Covers vector types, distance operators, indexing (HNSW/IVFFlat), and client library usage. Use when storing vectors in PostgreSQL, running nearest-neighbor searches, or configuring HNSW/IVFFlat indexes. Keywords: pgvector, PostgreSQL, vector search, HNSW, IVFFlat."
metadata:
version: "0.8.7"
release_date: "2026-10-01"
---
# pgvector
PostgreSQL extension for storing vectors and running exact/approximate nearest-neighbor search in SQL.
## Quick Navigation
- Installation: `references/installation.md`
- Core concepts and SQL recipes: `references/core.md`
- Indexing (HNSW / IVFFlat) and tuning: `references/indexing.md`
- Filtering, iterative scans, and performance: `references/performance-and-filtering.md`
- Types and functions reference (vector/halfvec/bit/sparsevec): `references/types-and-functions.md`
- Troubleshooting: `references/troubleshooting.md`
- Client libraries (priority):
- Python: `references/python.md`
- Go: `references/go.md`
- Node (JS/TS): `references/node.md`
- Java: `references/java.md`
- Swift: `references/swift.md`
## When to Use
- You need vector similarity search inside Postgres (keep vectors with relational data).
- You want SQL-native ANN indexes (HNSW or IVFFlat) with tunable recall/speed.
- You want consistent patterns to store/query embeddings across multiple application languages.
## Quick Start (already installed)
Prerequisite: pgvector is installed on the Postgres server. See: `references/installation.md`.
Enable per database and run a first query:
```sql
CREATE EXTENSION vector;
CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3));
INSERT INTO items (embedding) VALUES ('[1,2,3]'), ('[4,5,6]');
SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5;
```
### Choosing distance operators
- L2 (Euclidean): use `<->`
- Inner product: use `<#>` (note: returns negative inner product)
- Cosine distance: use `<=>`
- L1: use `<+>`
- Binary vectors: Hamming `<~>` / Jaccard `<%>`
### Indexing rules of thumb
- Exact search: no pgvector index; may use parallel scan on large tables.
- ANN search:
- Prefer HNSW for better speed/recall, higher build time/memory.
- Use IVFFlat when you need faster builds/lower memory.
- Create one index per distance function/operator class you plan to use.
## Critical Prohibitions / Gotchas
- Approximate indexes can change results (recall vs speed).
- Index usage typically requires `ORDER BY <distance-op> ... LIMIT ...`.
- `<#>` returns negative inner product; multiply by `-1` to get the actual value.
- `NULL` vectors are not indexed; for cosine distance, zero vectors are not indexed.
## Release Notes
- `0.8.7` (2026-10-01) is a fix release: a race between HNSW `INSERT` and `VACUUM` that could return duplicate neighbors, a buffer overflow in IVFFlat index builds with hardened index entry points, improved `vector_combine`, and a fix for the `avg` aggregate when no rows match. Casts between `vector`, `halfvec`, and `sparsevec` were tightened and safety-checked, and `-ffp-contract=fast` was added to `PG_CFLAGS` to enable multiply-and-add.
## Links
- Docs / repo: https://github.com/pgvector/pgvector
- Client libs:
- Python: https://github.com/pgvector/pgvector-python
- Go: https://github.com/pgvector/pgvector-go
- Node: https://github.com/pgvector/pgvector-node
- Java: https://github.com/pgvector/pgvector-java
- Swift: https://github.com/pgvector/pgvector-swift
- Releases/tags: https://github.com/pgvector/pgvector/tags
Pliki w paczce (12)
- SKILL.md 3 KB
- references/core.md 2 KB
- references/go.md 1 KB
- references/indexing.md 3 KB
- references/installation.md 2 KB
- references/java.md 1 KB
- references/node.md 1 KB
- references/performance-and-filtering.md 4 KB
- references/python.md 2 KB
- references/swift.md 1 KB
- references/troubleshooting.md 2 KB
- references/types-and-functions.md 3 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · itechmeat/llm-code | 100 | MIT |
| TerminalSkills/skills | 100 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki c046bc50d2fc (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100pgvector-advanced
Obejmuje pgvector 0.7+ w PostgreSQL: strojenie HNSW i IVFFlat, typy halfvec, bit i sparsevec, kwantyzację binarną, wyszukiwanie hybrydowe z pg_trgm i tsvector oraz wzorce Supabase. - 100vector-databases-pgvector-pinecone
Przechowuje osadzenia wielowymiarowe i wykonuje przybliżone wyszukiwanie najbliższych sąsiadów w pgvector i Pinecone. - 100vector-store-stinger
Projektuje przechowywanie wektorów: schematy pgvector, HNSW i IVFFlat, indeksy hybrydowe, migracje i wybór magazynu. - 100vector-database
Projektuje i strojenie baz wektorowych: schematy pgvector, kolekcje Weaviate, indeksy HNSW, modele embeddingów i RAG. - 100laravel-vector-search
Wdraża wyszukiwanie semantyczne i wektorowe w Laravel 13 z użyciem PostgreSQL i pgvector. - 80role-database:vector-databases
Pomaga wybrać i wdrożyć bazy wektorowe, np. pgvector, Qdrant, Pinecone czy Weaviate, do wyszukiwania semantycznego i RAG.