# Upstash Vector

## Prequisites

1. Sign up or Sign In to [Upstash Console](https://console.upstash.com)
2. Navigate to Vector page and click **Create Index**

   <figure><img src="/files/XLVkX5ZFvW60Lyo2NvjH" alt=""><figcaption></figcaption></figure>
3. Do the necessary configurations and create the index.

   1. **Index Name**, name of the index to be created. (e.g. "upstash-demo")
   2. **Dimensions**, size of the vectors to be inserted in the index. (e.g. 1536)
   3. **Embedding Model**, the model to be used in [Upstash Embeddings](https://upstash.com/docs/vector/features/embeddingmodels). This is optional. If you enable it, you don't need to provide embeddings model.

   <figure><img src="/files/173PFwBetEhIpwrDn1CE" alt=""><figcaption></figcaption></figure>

## Setup

1. Get your index credentials

<figure><img src="/files/1dVhW0BW6nQQg0lkrk0o" alt=""><figcaption></figcaption></figure>

1. Create new Upstash Vector credential and fill in
   1. Upstash Vector REST URL from UPSTASH\_VECTOR\_REST\_URL on console
   2. Upstash Vector Rest Token from UPSTASH\_VECTOR\_REST\_TOKEN on console

<figure><img src="/files/fBSwZ3AmsaV1oB4u8B8x" alt="" width="563"><figcaption></figcaption></figure>

1. Add a new **Upstash Vector** node to canvas

<figure><img src="/files/DPZbyq3XBJEgdW3RPTpX" alt="" width="279"><figcaption></figcaption></figure>

1. Add additional nodes to canvas and start the upsert process
   * **Document** can be connected with any node under [**Document Loader**](/readme/chatflows/langchain/document-loaders.md) category
   * **Embeddings** can be connected with any node under [**Embeddings** ](/readme/chatflows/langchain/embeddings.md)category

<figure><img src="/files/a2dFpnuByLjItlYge2V8" alt=""><figcaption></figcaption></figure>

1. Verify from [Upstash dashboard](https://console.upstash.com) to see if data has been successfully updated:

<figure><img src="/files/C7thMeVzhUqtcFrI4rN7" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: 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://tailwindsdocs.innovativesol.com/readme/chatflows/langchain/vector-stores/upstash-vector.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.