# Retrieval Augmented Generation

Union.ai enables production-grade RAG pipelines with a focus on
performance, scalability, and ease of use.

In this section, we will see some examples demonstrating how to extract documents
from various data sources, create in-memory vector databases, and use them to
implement RAG pipelines using LLM providers and Union-hosted LLMs.

## Subpages

- [Agentic Retrieval Augmented Generation](https://www.union.ai/docs/v1/union/tutorials/retrieval-augmented-generation/agentic-rag/page.md)
- [Creating a RAG App with LanceDB and Google Gemini](https://www.union.ai/docs/v1/union/tutorials/retrieval-augmented-generation/lance-db-rag/page.md)
- [Building a Contextual RAG Workflow with Together AI](https://www.union.ai/docs/v1/union/tutorials/retrieval-augmented-generation/contextual-rag/page.md)
  - Workflow overview
  - Execution approach
  - Local execution
  - Remote execution
  - Deploy apps

---
**Source**: https://github.com/unionai/unionai-docs/blob/main/content/tutorials/retrieval-augmented-generation/_index.md
**HTML**: https://www.union.ai/docs/v1/union/tutorials/retrieval-augmented-generation/