37 lines
876 B
Markdown
37 lines
876 B
Markdown
---
|
|
layout: default
|
|
---
|
|
|
|
# Splitters por tipo de contenido
|
|
|
|
<v-clicks>
|
|
|
|
`RecursiveCharacterTextSplitter.fromLanguage()` usa separadores adaptados a cada formato
|
|
|
|
### Markdown — respeta encabezados y listas
|
|
```typescript
|
|
import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
|
|
|
|
const mdSplitter = RecursiveCharacterTextSplitter.fromLanguage("markdown", {
|
|
chunkSize: 1000, chunkOverlap: 200,
|
|
});
|
|
```
|
|
|
|
### HTML — respeta estructura de etiquetas
|
|
```typescript
|
|
const htmlSplitter = RecursiveCharacterTextSplitter.fromLanguage("html", {
|
|
chunkSize: 1000, chunkOverlap: 200,
|
|
});
|
|
```
|
|
|
|
### Código JS/TS — respeta funciones y clases
|
|
```typescript
|
|
const codeSplitter = RecursiveCharacterTextSplitter.fromLanguage("js", {
|
|
chunkSize: 1500, chunkOverlap: 200,
|
|
});
|
|
```
|
|
|
|
Otros lenguajes soportados: `python`, `java`, `go`, `rust`, `ruby`, `php`...
|
|
|
|
</v-clicks>
|