pgvector
by @damiencronw
PostgreSQL vector database skill with pgvector extension. Enables vector similarity search, embeddings storage, RAG (Retrieval-Augmented Generation) pipeline...
β‘ When to Use
| Trigger | Action |
|---|
| 2. **RAG** - Retrieve relevant context for LLM prompts |
| 3. **Recommendations** - Find similar items/products |
| 4. **Anomaly Detection** - Find outliers in embeddings |
| 5. **Image/Video Search** - Store and query visual embeddings |
π Tips & Best Practices
Vector dimensions must match your embedding model
HNSW is better for accuracy, IVFFlat better for large datasets
Normalize vectors for cosine similarity
pgvector supports up to 16,000 dimensions clawhub install pgvector
π§ͺ Use this skill with your agent
Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.
π Can't find the right skill?
Search 60,000+ AI agent skills β free, no login needed.
