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

What To Eat Today

What To Eat Today is a self-hostable AI cooking assistant that uses graph RAG and vector retrieval to recommend dishes and provide step-by-step cooking guidance through a conversational interface. Its documented application stack includes a Next.js frontend, Flask backend, Neo4j graph database, Milvus vector database and Docker Compose deployment.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

What To Eat Today — 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 you want recipe suggestions and cooking guidance in one conversational workflow, or when you want to inspect a self-hostable graph-RAG application.

Who it is for

  • People looking for dish ideas and guided cooking steps through a chat interface.
  • Developers exploring a graph-RAG and vector-retrieval recipe application they can run locally.

Documented uses

  • Get dish recommendations through natural-language conversation.
  • Follow step-by-step cooking guidance for a recommended dish.
  • Study or adapt a retrieval-based conversational application for recipes.
Before you choose

Requirements & limits

The README documents local deployment with Docker Compose and startup scripts for Windows, Linux and macOS. Docker Desktop is required; Node.js 18 or later is optional for frontend development. The repository states that the code is licensed under MIT.

  • The application combines Neo4j graph retrieval with Milvus vector search, rather than relying on a recipe chat interface alone.
  • Local deployment involves a frontend, backend and two databases managed through Docker Compose.
  • The README identifies HowToCook as the main source of recipe data.

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

Start the application locally

Clone the repository and start the Docker Compose application using the documented platform script.

Before you start

  • Docker Desktop
  • A Windows, Linux or macOS environment

Steps

  1. Clone https://github.com/FutureUnreal/What-to-eat-today.git and change into the repository directory.

  2. On Windows, run start.bat.

  3. On Linux or macOS, run chmod +x start.sh stop.sh and then ./start.sh.

  4. Open http://localhost after startup, or use the listed frontend address http://localhost:3000.

Expected outcome

The project’s startup instructions direct users to a locally served cooking assistant and list separate local addresses for the frontend, backend API, Neo4j and Milvus.

Guide limitations

  • Docker Desktop is a stated prerequisite.
  • The README says the first startup downloads images and may take 5–10 minutes.
  • Node.js 18 or later is optional and is listed for frontend development, not the documented container startup.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

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
What To Eat TodayGet dish recommendations through natural-language conversation.Docker, Linux, macOS, WebThe README documents local deployment with Docker Compose and startup scripts for Windows, Linux and macOS. Docker Desktop is required; Node.js 18 or later is optional for frontend development. The repository states that the code is licensed under MIT.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
FutureUnreal/What-to-eat-today · Official homepage title · retained in its source language
How we review sourcesSuggest a correction