GitHub - pgvector/pgvector-d: pgvector examples for D

pgvector examples for D

Supports dpq2

Getting Started

Follow the instructions for your database library:

dpq2

Or check out some examples:

Embeddings with OpenAI
Binary embeddings with Cohere
Hybrid search with Ollama (Reciprocal Rank Fusion)
Sparse search with Text Embeddings Inference

dpq2

Enable the extension

conn.exec("CREATE EXTENSION IF NOT EXISTS vector");

Create a table

conn.exec("CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))");

Insert vectors

QueryParams p;
p.sqlCommand = "INSERT INTO items (embedding) VALUES ($1::vector), ($2::vector)";
p.argsVariadic([1, 2, 3], [4, 5, 6]);
conn.execParams(p);

Get the nearest neighbors

QueryParams p;
p.sqlCommand = "SELECT * FROM items ORDER BY embedding <-> $1::vector LIMIT 5";
p.argsVariadic([3, 1, 2]);
p.resultFormat = ValueFormat.TEXT;
auto result = conn.execParams(p);
foreach (row; rangify(result))
{
    writeln(row);
}

Add an approximate index

conn.exec("CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)");
// or
conn.exec("CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)");

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

See a full example

Contributing

Everyone is encouraged to help improve this project. Here are a few ways you can help:

Report bugs
Fix bugs and submit pull requests
Write, clarify, or fix documentation
Suggest or add new features

To get started with development:

git clone https://github.com/pgvector/pgvector-d.git
cd pgvector-d
createdb pgvector_d_test
dub run

Specify the path to libpq if needed:

DFLAGS="-L-L/opt/homebrew/opt/libpq/lib" dub run

To run an example:

cd examples/openai
createdb pgvector_example
dub run