# **Build from Scratch with LanceDB π οΈπ**
Start building your GenAI applications from the ground up using **LanceDB's** efficient vector-based document retrieval capabilities! π
**Get Started in Minutes β±οΈ**
These examples provide a solid foundation for building your own GenAI applications using LanceDB. Jump from idea to **proof of concept** quickly with applied examples. Get started and see what you can create! π»
| **Build From Scratch** | **Description** | **Links** |
|:-------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| **Build RAG from Scratchππ»** | π Create a **Retrieval-Augmented Generation** (RAG) model from scratch using LanceDB. | [](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/RAG-from-Scratch)
[]() |
| **Local RAG from Scratch with Llama3π₯π‘** | π« Build a local RAG model using **Llama3** and **LanceDB** for fast and efficient text generation. | [](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Local-RAG-from-Scratch)
[](https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Local-RAG-from-Scratch/rag.py) |
| **Multi-Head RAG from Scratchππ»** | π€― Develop a **Multi-Head RAG model** from scratch, enabling generation of text based on multiple documents. | [](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Multi-Head-RAG-from-Scratch)
[](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Multi-Head-RAG-from-Scratch) |