> 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/vector-stores/pinecone.md).

# Pinecone

## Prerequisitos

1. Registra una cuenta en [Pinecone](https://app.pinecone.io/)
2. Haz clic en **Create index**

<figure><img src="/files/jEKTE3lqoa9eyIPyB7ET" alt=""><figcaption></figcaption></figure>

3. Completa los campos requeridos:
   * **Index Name**, nombre del índice a crear. (por ejemplo, "flowise-test")
   * **Dimensions**, tamaño de los vectores a insertar en el índice. (por ejemplo, 1536)

<figure><img src="/files/s2zBZf9tiSQHv9fM69rW" alt="" width="527"><figcaption></figcaption></figure>

4. Haz clic en **Create Index**

## Configuración

1. Obtén/Crea tu **API Key**

<figure><img src="/files/WkI7dfiHAkCfIRROO2YQ" alt=""><figcaption></figcaption></figure>

2. Agrega un nuevo nodo **Pinecone** al canvas y completa los parámetros:
   * Pinecone Index
   * Pinecone namespace (opcional)

<figure><img src="/files/8NOLz2LU2igX3zNdeb4k" alt="" width="279"><figcaption></figcaption></figure>

3. Crea una nueva credencial de Pinecone -> Completa el **API Key**

<figure><img src="/files/eRE0mIvuMgEiZOZrzPfg" alt="" width="563"><figcaption></figcaption></figure>

4. Agrega nodos adicionales al canvas e inicia el proceso de upsert
   * **Document** puede conectarse con cualquier nodo bajo la categoría [**Document Loader**](/espanol/documentacion-oficial/integraciones/langchain/document-loaders.md)
   * **Embeddings** puede conectarse con cualquier nodo bajo la categoría [**Embeddings**](/espanol/documentacion-oficial/integraciones/langchain/embeddings.md)

<figure><img src="/files/j4dff0UaudfZ7FjdHeEH" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/FtYgokn5j6341nD7Ly6A" alt=""><figcaption></figcaption></figure>

5. Verifica desde el [dashboard de Pinecone](https://app.pinecone.io) si los datos se han insertado correctamente:

<figure><img src="/files/59ODo3usqVRvIUVgnvGO" alt=""><figcaption></figcaption></figure>

## Recursos

* Integraciones de vectorstore de LangChain con Pinecone
  * [Python](https://python.langchain.com/v0.2/docs/integrations/providers/pinecone/)
  * [NodeJS](https://js.langchain.com/v0.2/docs/integrations/vectorstores/pinecone)
* [Integración de Pinecone con LangChain](https://docs.pinecone.io/integrations/langchain)
* [Integración de Pinecone con Flowise](https://docs.pinecone.io/integrations/flowise)
* [Clientes oficiales de Pinecone](https://docs.pinecone.io/reference/pinecone-clients)


---

# 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:

```
GET https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/vector-stores/pinecone.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.