# Compound AI Systems

Compound AI Systems refer to artificial intelligence systems that combine multiple
AI and software components to create a more complex and powerful system. Instead of
focusing on a single model or data type, Compound AI Systems combine models with
different modalities and software components like databases, vector stores, and
more to solve a given task or problem.

In the following examples, you’ll explore how Compound AI Systems can be applied
to manipulate and analyze various types of data.

## Subpages

- [Video Dubbing](https://www.union.ai/docs/v1/union/tutorials/compound-ai-systems/video-dubbing/page.md)
- [Natural Language SQL Query Agent using Smolagent](https://www.union.ai/docs/v1/union/tutorials/compound-ai-systems/text_to_sql_agent/page.md)
- [Optimizing the PDF-to-Podcast NVIDIA Blueprint for Production Use](https://www.union.ai/docs/v1/union/tutorials/compound-ai-systems/pdf-to-podcast-blueprint/page.md)
- [Serving LlamaIndex RAG with FastAPI and LanceDB](https://www.union.ai/docs/v1/union/tutorials/compound-ai-systems/llama_index_rag/page.md)
- [Taking NVIDIA’s Enterprise RAG Blueprint to Production](https://www.union.ai/docs/v1/union/tutorials/compound-ai-systems/enterprise-rag-blueprint/page.md)

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