OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Vectaurant

Vectaurant is a C#/.NET console-based restaurant assistant that uses retrieval-augmented generation to answer questions with menu and restaurant information retrieved from Qdrant.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vectaurant — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Vectaurant to study or run a console-based example of menu ingestion, vector retrieval and plugin-orchestrated question answering.

Who it is for

  • Developers exploring a restaurant-focused RAG assistant and plugin orchestration.
  • Teams considering a vector-search pattern for answering questions from domain-specific documents.

Documented uses

  • Find menu options by describing preferences, such as asking what is vegan or spicy.
  • Request menu recommendations, including food pairings.
  • Retrieve menu information relevant to ingredient and allergen questions.
  • Explore a workflow that ingests menu data into Qdrant before serving assistant responses.
Before you choose

Requirements & limits

  • The Kitchen project loads menu data; FrontDesk handles user requests.
  • Running the documented flow requires a local Qdrant instance and an OpenAI API key.
  • The project is a console application, with no hosted customer-facing service described in its README.

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

Set up Vectaurant and start its menu assistant

Configure the documented C# projects, load the menu data into Qdrant, and start the FrontDesk assistant.

Before you start

  • A .NET environment for the console projects.
  • Docker to run Qdrant locally.
  • An OpenAI API key configured in Vectaurant.Shared/appsettings.json.

Steps

  1. Clone the Vectaurant repository.

  2. Add the OpenAI API key to the OpenAIOptions.ApiKey setting in Vectaurant.Shared/appsettings.json.

  3. Start Qdrant locally with the documented Docker command: docker run -p 6333:6333 qdrant/qdrant.

  4. In separate terminals, run Vectaurant.Kitchen with dotnet run --project ./Vectaurant.Kitchen/Vectaurant.Kitchen.csproj, then Vectaurant.FrontDesk with dotnet run --project ./Vectaurant.FrontDesk/Vectaurant.FrontDesk.csproj.

Expected outcome

Kitchen feeds menu data into the vector database, and FrontDesk starts the assistant that serves user requests.

Guide limitations

  • The README notes that using an OpenAI API key directly requires updating the base URL in configuration.
  • These are the repository's documented setup and run steps, not a guarantee of compatibility in a particular environment.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
VectaurantFind menu options by describing preferences, such as asking what is vegan or spicy.CLI, Docker, Linux, macOS
Aml Multiagent RagIngest PDF regulations, extract and chunk their text, and build a searchable vector collection.Docker, Self-hostedThe repository is public and specifies the MIT license. The documented setup is self-hosted and requires Python 3.11 or later, Docker Desktop and an OpenAI API key.
MindgeniusaiAsk questions across one or more attached PDFs using retrieval.Docker, Self-hosted, WebThe repository offers a live demo that requires visitors to bring their own API key. Local development requires Node.js 20 or later and pnpm; the README also documents a Docker image. The repository identifies the license as BSL 1.1.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
beheshty/Vectaurant · Official homepage title · retained in its source language
How we review sourcesSuggest a correction