> For the complete documentation index, see [llms.txt](https://docs.flowiseai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/memory/conversation-summary-memory.md).

# Conversation Summary Memory

Usa la tabla de base de datos `chat_message` de Flowise como mecanismo de almacenamiento para guardar/recuperar conversaciones.

Este tipo de memoria crea un breve resumen de la conversación a lo largo del tiempo. Esto es útil para acortar información de discusiones largas. Actualiza y guarda un resumen actual mientras la conversación continúa. Esto es especialmente útil en chats más largos, donde guardar cada mensaje anterior ocuparía demasiado espacio.

<figure><img src="/files/dcDsQosgqr7DOLkV3V8o" alt="" width="296"><figcaption></figcaption></figure>

## Entrada

| Parámetro  | Descripción                                                                             | Valor por defecto |
| ---------- | --------------------------------------------------------------------------------------- | ----------------- |
| Chat Model | LLM usado para realizar la sumarización                                                 |                   |
| Session Id | Un ID para recuperar/almacenar mensajes. Si no se especifica, se usará un ID aleatorio. |                   |
| Memory Key | Una clave usada para formatear mensajes en la plantilla de prompt                       | chat\_history     |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/memory/conversation-summary-memory.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
