> 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/retrievers/custom-retriever.md).
# Custom Retriever
Custom Retriever permite al usuario especificar el formato del contexto para el LLM
Por defecto, cuando el contexto se recupera del vector store, tiene el siguiente formato:
```json
[
{
"pageContent": "This is an example",
"metadata": {
"source": "example.pdf"
}
},
{
"pageContent": "This is example 2",
"metadata": {
"source": "example2.txt"
}
}
]
```
El **pageContent** del array se unirá como una cadena de texto y se enviará al LLM para su completado.
Sin embargo, en algunos casos, es posible que desees incluir información de los metadatos para proporcionar más información al LLM, como la fuente, el enlace, etc. Aquí es donde entra el **Custom Retriever**. Podemos especificar el formato que se devolverá al LLM.
Por ejemplo, usando el siguiente formato:
```javascript
{{context}}
Source: {{metadata.source}}
```
Resultará en la cadena combinada como se muestra a continuación:
```
This is an example
Source: example.pdf
This is example 2
Source: example2.txt
```
Esto se enviará de vuelta al LLM. Como el LLM ahora tiene las fuentes de las respuestas, podemos usar prompts para instruir al LLM para que devuelva respuestas seguidas de citas.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/retrievers/custom-retriever.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
%20(1)%20(1).png?alt=media)