On this page
PLOMID stores dense embedding vectors as a native column type and searches them with SQL distance operators. You insert vectors as literals, rank rows with ORDER BY ... LIMIT k, and optionally accelerate large scans with an HNSW index. Supported in v0.1.0 for dense vectors; sparse, binary, and multivector types parse but have narrower execution paths (see Limitations).
flowchart LR
APP["application data"] --> EMB["embedding model\n(outside PLOMID)"] --> VEC["vector column\nVECTOR(FLOAT32, n)"]
VEC --> Q["similarity query\nORDER BY embedding <-> query LIMIT k"]
Q --> EX["exact scan\n(always correct)"]
Q --> ANN["HNSW index\n(faster at scale)"]
EX --> R["top-k rows + distances"]
ANN --> R
R --> USE["application uses\nretrieved records"]Diagram source · mermaidcopy included
flowchart LR
APP["application data"] --> EMB["embedding model\n(outside PLOMID)"] --> VEC["vector column\nVECTOR(FLOAT32, n)"]
VEC --> Q["similarity query\nORDER BY embedding <-> query LIMIT k"]
Q --> EX["exact scan\n(always correct)"]
Q --> ANN["HNSW index\n(faster at scale)"]
EX --> R["top-k rows + distances"]
ANN --> R
R --> USE["application uses\nretrieved records"]The workflow#
- Your application converts data (text, images) into embeddings with an external model. PLOMID does not generate embeddings.
- You store each embedding in a
VECTORcolumn alongside ordinary fields (id,label, metadata). - You query with a distance operator (
<->,<=>,<#>,<~>,<%>) andORDER BY ... LIMIT k. - Without an index, every query is an exact scan — always correct, slower as data grows.
- With an HNSW index, large datasets trade a small amount of recall for much faster candidate retrieval.
Status at a glance#
| Capability | Status | Details |
|---|---|---|
Dense VECTOR columns (FLOAT32/16, BFLOAT16, INT8/UINT8/INT4) |
Supported | Vector types |
Distance operators <-> <=> <#> <~> <%> |
Supported | Distance operators |
| Exact top-k similarity search | Supported | Similarity search |
| HNSW approximate search | Supported | HNSW |
Other index methods (ivf_flat, ivf_sq, ivf_pq, diskann, flat) |
Supported (declared; small scans may still run exact) | Indexes |
Metadata filtering (WHERE + vector ordering) |
Supported (served by exact path) | Filtering |
Binary vectors (VECTOR(BINARY, n)) |
Limited (DDL + string literals + Hamming/Jaccard; ANN falls back to exact) | Limitations |
| Sparse / multivector types | Experimental (DDL parses; no verified literal/insert path) | Limitations |
| GPU acceleration | Unsupported (CPU only; GPU setting degrades to CPU) | Performance |
CREATE INDEX ... USING hnsw inside an explicit transaction |
Unsupported (use autocommit) | Troubleshooting |
Where to go#
- New to vectors? Quickstart takes you from empty database to similarity search in minutes.
- Know embeddings already? Vector types → Distance operators → Similarity search.
- Scaling up? HNSW → Exact vs approximate → Performance.
- Building retrieval? Application integration → Semantic retrieval guide.
Was this page helpful? Thanks — noted locally, nothing is sent anywhere.