# Should travel apps use RAG instead of fine-tuning?

> Source: <https://discuss.huggingface.co/t/should-travel-apps-use-rag-instead-of-fine-tuning/178425#post_2>
> Published: 2026-08-04 06:45:18+00:00

For a travel app, I would start with **RAG for changing facts** and use fine-tuning only if you later need to change the model’s behavior.

Use RAG for information such as:

Those facts change frequently, so they should stay in databases/APIs or an indexed knowledge base. Retrieve them at request time, include source timestamps, and show citations. Hugging Face’s RAG documentation describes the same basic pattern: retrieve documents and pass them to the generator: [RAG · Hugging Face](https://huggingface.co/docs/transformers/model_doc/rag)

Fine-tuning is better for stable behavior, for example:

Fine-tuning adapts a pretrained model to a task-specific dataset, but it is not a convenient replacement for a frequently updated source of truth: [Fine-tuning · Hugging Face](https://huggingface.co/docs/transformers/en/training)

A practical architecture is therefore:

So the short answer is: **RAG first; fine-tuning later if needed; often the best production system uses both.**