---
title: Cohere Embeddings
description: Leverage Cohere to create embeddings.
---

Turn text into vectors with Cohere's embedding models, so a knowledge base can find passages by meaning.

Pick a saved connection in the **Authentication** field, or create one from there.

## What it does

Cohere Embeddings plugs into the **Embeddings** slot of a [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/) node. It does not run on its own and has no output. When the knowledge base is filled or searched, the text is sent to Cohere with your key and comes back as vectors (lists of numbers that capture meaning).

A knowledge base remembers the embedding model it was built with and always uses it. So this node decides the model when a **new, empty** knowledge base is first filled. After that, connect the same node to search it.

Your passages and questions are sent to Cohere. For text that must stay on your device, use [Local Embeddings](/nodes/builtin/ai/aidependencies/embeddings/localembeddings/).

## When to use it

* Documents in many languages: Cohere has multilingual embedding models.
* You already use Cohere and want its embeddings in AWFlow.

## Inputs and settings

Type the **Model** id as Cohere names it, for example `embed-english-v3.0`, or `embed-multilingual-v3.0` for other languages. Don't change it on a knowledge base that already has content.

## Outputs

This node has no output port. It plugs into a slot on another node instead of passing items along.

* **Embeddings** slot of [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/)

The vectors go to the knowledge base, not to the next node.

## Dependencies and credentials

* **Authentication** (connection): required. See [Connect Cohere](/app/connections/cohere/).

In **Authentication**, save your Cohere API key. Create it on the API keys page of the Cohere dashboard. See [Create a credential](/app/connections/create/).

## Example workflow

1. A [Context Menu](/nodes/builtin/trigger/contextmenu/) trigger on the page.
2. [Get All Text](/nodes/extension/getalltext/) with **Output field name** `pageText`.
3. [Indexer](/nodes/builtin/ai/aiagents/indexernode/) with **Input** `{{ $input.pageText }}`, a [Recursive Character Text Splitter](/nodes/builtin/ai/aidependencies/textsplitter/recursivecharactertextsplitter/) in its **Text Splitter** slot, and a [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/) pointing to a new knowledge base in its **Knowledge** slot.
4. Cohere Embeddings in the Local Knowledge's **Embeddings** slot, **Model** `embed-multilingual-v3.0`.

## Common issues

* **"Model parameter is required and cannot be empty".** Fill in **Model**.
* **"… was built with … embeddings. Connect that embeddings node to use it."** The knowledge base was built with this Cohere model. Connect Cohere Embeddings with the same **Model** to its Local Knowledge.
* **A "Model mismatch" warning in the run log.** The knowledge base was built with another model, so this node was ignored. Disconnect it, or re-embed the knowledge base from its settings.
* **A 401 error.** The key is wrong or revoked. Create a new key and update the credential.

## Related nodes

* [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/): the knowledge base it plugs into.
* [Voyage Embeddings](/nodes/builtin/ai/aidependencies/embeddings/voyage/), [OpenAI Embeddings](/nodes/builtin/ai/aidependencies/embeddings/openai/): other cloud embedding models.
* [Local Embeddings](/nodes/builtin/ai/aidependencies/embeddings/localembeddings/): free and on your device.