OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Sharpvector

Sharpvector is a C#/.NET library that stores, searches and manages text as vectors in memory, with customizable vector comparison, preprocessing and vectorization strategies.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Sharpvector — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a .NET application needs an embedded, in-memory text-vector store for semantic search or RAG retrieval.

Who it is for

  • Developers adding semantic text search to .NET applications.
  • Teams building RAG workflows that need to retrieve text context for language-model prompts.

Documented uses

  • Store and search text using vector representations within a .NET application.
  • Retrieve relevant text to supply as context in a RAG workflow.
  • Choose among supported local, OpenAI or Ollama embedding approaches.
Before you choose

Requirements & limits

The project is distributed as the Build5Nines.SharpVector NuGet package and identifies an MIT license.

  • .NET 8 or later is identified as the framework requirement.
  • The library uses in-memory storage, a different design choice from a separate database-based vector store.
  • Local, OpenAI and Ollama embeddings are listed as supported.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add chunked text to an in-memory SharpVector database

Load a document into a BasicMemoryVectorDatabase by splitting it into chunks and assigning metadata.

Before you start

  • A .NET project using SharpVector.
  • Document text to load.
  • A metadata value for each chunk; the documented example creates a JSON string.

Steps

  1. Import Build5Nines.SharpVector and Build5Nines.SharpVector.Data.

  2. Create the database with var vdb = new BasicMemoryVectorDatabase();.

  3. Create a loader with var loader = new TextDataLoader(vdb);.

  4. Call loader.AddDocument with the document text and TextChunkingOptions, choosing a documented method such as Paragraph, Sentence, FixedLength, or OverlappingWindow, and provide RetrieveMetadata for each chunk.

Expected outcome

The document is split according to the selected strategy and its chunks are loaded into the in-memory vector database with metadata stored alongside them.

Guide limitations

  • Each chunk must have metadata, even if it is only a minimal description.
  • Chunking strategy and size should be selected for the content and retrieval goals; experimentation may be needed.
  • For larger documents, the documentation says chunking is required for the best semantic search results.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
Build5Nines/SharpVector · Official homepage title · retained in its source language
How we review sourcesSuggest a correction