Practical overview
When it fits
Use the hosted demo to explore conversational listing search, or the repository when you want to set up, inspect or adapt the application.
Who it is for
- People searching listings by combining criteria in a natural-language query.
- Developers evaluating or adapting an open-source real-estate search application.
Documented uses
- Find listings that match requirements such as bedrooms, location and budget.
- Explore property matches using maps and area analytics.
- Compare ownership choices or examine mortgage, ROI and total-cost estimates.
- Inspect a RAG and vector-search implementation for property data.
Requirements & limits
The repository says the hosted demo can be explored without login. Its demo mode uses simulated AI responses; production deployment requires at least one LLM-provider API key. The public repository is MIT-licensed.
- The hosted demo is for exploration and uses simulated AI responses; production use requires provider configuration.
- Local demo setup uses Docker and mock data, while the repository also documents manual backend and frontend setup.
- The stack includes a Python FastAPI API, a Next.js interface, ChromaDB retrieval and multiple LLM-provider integrations.
- The repository identifies nine interface languages: English, Polish, Russian, German, Spanish, Italian, Portuguese, Turkish and Ukrainian.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Start the local Docker demo
Launch the project’s demo environment and generate its mock data.
Before you start
- Git
- Docker and Docker Compose
- A local environment able to run the repository’s PowerShell scripts or Docker Compose instructions
Steps
Clone the repository and change into its directory.
Run the documented Docker startup command: .\start-docker.ps1, or copy deploy/compose/.env.example to deploy/compose/.env and start the compose file with docker compose -f deploy/compose/docker-compose.yml up --build.
For the separate scripted demo-data workflow, run .\scripts\demo\01-launch-docker.ps1 followed by .\scripts\demo\02-generate-data.ps1.
Open the frontend at http://localhost:3082 or the API documentation at http://localhost:8082/docs when using the scripted demo setup.
Expected outcome
A local demo with mock property and application data; the documented scripted setup lists 250+ properties across five Polish cities.
Guide limitations
- Demo mode uses mock data and simulated AI responses; production deployment requires API-provider configuration.
- The repository lists separate ports for the script-based demo and manual development setup.
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.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| AI Real Estate Assistant | Find listings that match requirements such as bedrooms, location and budget. | Server, Web | The repository says the hosted demo can be explored without login. Its demo mode uses simulated AI responses; production deployment requires at least one LLM-provider API key. The public repository is MIT-licensed. |
| Chatbot with PDF for Semantic Search | Prepare document content as embeddings and save it to a supported vector database. | Web | The repository is identified as open source and publicly visible on GitHub. |
| AI LLM Playground | Ask questions about PDF documents through an assistant interface. | Web |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 8 October 2026
- Original website title
- AleksNeStu/ai-real-estate-assistant · Official homepage title · retained in its source language