---
hide_table_of_contents: true
sidebar_label: Prompt selectors
---

# Prompt selectors

Prompt selectors are useful when you want to programmatically select a prompt based on the type of model you are using in a chain. This is especially relevant when swapping chat models and LLMs.

The interface for prompt selectors is quite simple:

```typescript
abstract class BasePromptSelector {
  abstract getPrompt(llm: BaseLanguageModel): BasePromptTemplate;
}
```

The `getPrompt` method takes in a language model and returns an appropriate prompt template.

We currently offer a `ConditionalPromptSelector` that allows you to specify a set of conditions and prompt templates. The first condition that evaluates to true will be used to select the prompt template.

```typescript
const QA_PROMPT_SELECTOR = new ConditionalPromptSelector(DEFAULT_QA_PROMPT, [
  [isChatModel, CHAT_PROMPT],
]);
```

This will return `DEFAULT_QA_PROMPT` if the model is not a chat model, and `CHAT_PROMPT` if it is.

The example below shows how to use a prompt selector when loading a chain:

```typescript
const loadQAStuffChain = (
  llm: BaseLanguageModel,
  params: StuffQAChainParams = {}
) => {
  const { prompt = QA_PROMPT_SELECTOR.getPrompt(llm) } = params;
  const llmChain = new LLMChain({ prompt, llm });
  const chain = new StuffDocumentsChain({ llmChain });
  return chain;
};
```