Rag.NET.VectorStores.PgVector
0.1.0
dotnet add package Rag.NET.VectorStores.PgVector --version 0.1.0
NuGet\Install-Package Rag.NET.VectorStores.PgVector -Version 0.1.0
<PackageReference Include="Rag.NET.VectorStores.PgVector" Version="0.1.0" />
<PackageVersion Include="Rag.NET.VectorStores.PgVector" Version="0.1.0" />
<PackageReference Include="Rag.NET.VectorStores.PgVector" />
paket add Rag.NET.VectorStores.PgVector --version 0.1.0
#r "nuget: Rag.NET.VectorStores.PgVector, 0.1.0"
#:package Rag.NET.VectorStores.PgVector@0.1.0
#addin nuget:?package=Rag.NET.VectorStores.PgVector&version=0.1.0
#tool nuget:?package=Rag.NET.VectorStores.PgVector&version=0.1.0
Rag.NET.VectorStores.PgVector
PostgreSQL + pgvector vector store for Rag.NET: dense cosine search over a vector
column, with optional learned sparse vectors (SPLADE-style) for hybrid retrieval — your
RAG index lives in the database you already run.
Install
dotnet add package Rag.NET.VectorStores.PgVector
Install alongside the core pipeline package (dotnet add package Rag.NET), which supplies
the AddRagNet(...) builder the store registers into.
Setup
Inside your AddRagNet(...) builder callback:
using Rag.NET.PgVector;
rag.UsePgVector(
connectionString: "Host=localhost;Database=ragdb;Username=postgres;Password=secret",
vectorDimensions: 1536);
Example
Create the table and indexes once at startup, then ingest as usual:
using Microsoft.Extensions.DependencyInjection;
using Rag.NET.Abstractions;
using Rag.NET.PgVector;
var store = provider.GetRequiredService<IVectorStore>() as PgVectorStore;
await store!.InitializeAsync();
Hybrid dense + learned-sparse search stores both vector kinds side by side:
rag.UsePgVector(
connectionString: "Host=localhost;Database=ragdb;Username=postgres;Password=secret",
vectorDimensions: 1536,
enableSparseVectors: true,
sparseVocabularySize: PgVectorSparseVectorStore.DefaultSparseVocabularySize); // 30522
Full guide
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net10.0
- Npgsql (>= 10.0.3)
- Pgvector (>= 0.3.2)
- Rag.NET.Abstractions (>= 0.1.0)
NuGet packages (2)
Showing the top 2 NuGet packages that depend on Rag.NET.VectorStores.PgVector:
| Package | Downloads |
|---|---|
|
Thalos.NET.Memory.RagNet
Rag.NET pgvector adapter for Thalos.NET.Memory: IMemoryIndex over Rag.NET IVectorStore (PgVectorStore) and an IEmbeddingGenerator, with schema initialisation and dimension checks. |
|
|
Rag.NET.Hosting
Configuration-driven pipeline wiring for hosting Rag.NET in an executable: binds a RagNet configuration section to an OpenAI-compatible chat client and embedding generator, and one of the InMemory, Qdrant, or PgVector vector stores. |
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 0.1.0 | 107 | 8/11/2026 |