43 lines
655 B
Markdown
43 lines
655 B
Markdown
---
|
|
layout: default
|
|
---
|
|
|
|
# Streaming: Respuestas en Tiempo Real
|
|
|
|
<div class="mt-8">
|
|
|
|
<v-click>
|
|
|
|
<div class="text-sm mb-6">
|
|
|
|
**¿Por qué streaming?**
|
|
|
|
- ✅ Experiencia de usuario mejorada (como ChatGPT)
|
|
- ✅ Feedback inmediato (no esperar 10-20 segundos)
|
|
- ✅ Procesar mientras se genera
|
|
|
|
</div>
|
|
|
|
</v-click>
|
|
|
|
<v-click>
|
|
|
|
```typescript
|
|
import { ChatOpenAI } from "@langchain/openai";
|
|
|
|
const model = new ChatOpenAI({
|
|
model: "gpt-4.1-mini",
|
|
streaming: true,
|
|
});
|
|
|
|
const stream = await model.stream("Explica qué es LangChain");
|
|
|
|
for await (const chunk of stream) {
|
|
console.log(chunk.content); // Imprime palabra por palabra
|
|
}
|
|
```
|
|
|
|
</v-click>
|
|
|
|
</div>
|