initial commit: slides + practica_resueltos + README
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,34 @@
|
||||
---
|
||||
layout: default
|
||||
---
|
||||
|
||||
# Paso 1: Cargar el PDF y dividir en chunks
|
||||
|
||||
```typescript
|
||||
import { PDFLoader } from "@langchain/community/document_loaders/fs/pdf";
|
||||
import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
|
||||
|
||||
// Cargar PDF (cada página → un Document)
|
||||
const loader = new PDFLoader("./docs/manual-usuario.pdf");
|
||||
const docs = await loader.load();
|
||||
console.log(`📥 ${docs.length} páginas cargadas`);
|
||||
|
||||
// Dividir en chunks pequeños para mejor búsqueda
|
||||
const splitter = new RecursiveCharacterTextSplitter({
|
||||
chunkSize: 1000,
|
||||
chunkOverlap: 200,
|
||||
});
|
||||
const chunks = await splitter.splitDocuments(docs);
|
||||
console.log(`📄 Dividido en ${chunks.length} chunks`);
|
||||
```
|
||||
|
||||
<v-click>
|
||||
|
||||
<div class="mt-4 p-3 bg-blue-500/10 rounded text-sm">
|
||||
|
||||
- **chunkSize**: tamaño máximo de cada trozo en caracteres
|
||||
- **chunkOverlap**: solapamiento entre chunks para no perder contexto
|
||||
|
||||
</div>
|
||||
|
||||
</v-click>
|
||||
Reference in New Issue
Block a user