# Vision RAG and image embeddings with Cohere Command-A: n8n workflow

> Started by someone opening a chat with it, and works across Qdrant. It puts a language model behind a retrieval step, so answers are drawn from documents...

Source: https://millionrounds.com/workflow/vision-rag-and-image-embeddings-with-cohere-command-a (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [AI assistants](https://millionrounds.com/workflows?category=AI+assistants#library)

# Vision RAG and image embeddings with Cohere Command-A

Started by someone opening a chat with it, and works across Qdrant. It puts a language model behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 27 steps, 1 branch, 1 loop or waits: large, and worth reading before you trust it with anything live.

Large Calls a model Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fvision-rag-and-image-embeddings-with-cohere-command-a)

**27 steps** Large: read it before trusting it with anything live

**1** Branch: places the flow splits

**1** Loop or waits

**1** Service it connects to

## The flow

Starts it 2 Model 10 Logic 9 Service 6

The steps in the order they run, from what starts it.

- 1 **When clicking ‘Execute workflow’** Manual trigger *Starts it*
- 2 **When chat message received** Chat trigger *Starts it*
- 3 **Simple Memory** Memory Buffer Window *Model*
- 4 **Simple Memory1** Memory Buffer Window *Model*
- 5 **Technology Innovation Report Tool** Tool Code *Model*
- 6 **Chat Model via Command-R** Lm Chat Cohere *Model*
- 7 **Create Collection** Qdrant *Service*
- 8 **Embeddings** Embeddings Cohere *Model*
- 9 **Technology and Innovation Report 2025** Set *Logic*
- 10 **AI Agent** Agent *Model*
- 11 **Respond to Chat** Chat *Model*
- 12 **Respond to Chat1** Chat *Model*
- 13 **Get Relevant Images** Vector Store Qdrant *Model*
- 14 **Split Out Urls** Split Out *Logic*
- 15 **If has Tool Call?** If *Logic*
- 16 **Aggregate Results** Aggregate *Logic*
- 17 **Batch 5** Split In Batches *Logic*
- 18 **Get Query** Set *Logic*
- 19 **Image Understanding via Command-A-Vision** Http Request *Service*
- 20 **Page Ref** No Op *Logic*
- 21 **Quick Confirmation** Chat *Model*
- 22 **Download Page** Http Request *Service*
- 23 **Convert Image to Base64** Extract From File *Service*
- 24 **Image Embeddings with Cohere Embed 4** Http Request *Service*
- 25 **Prepare Points** Set *Logic*
- 26 **Aggregate Points** Aggregate *Logic*
- 27 **Insert Points** Qdrant *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 27, with 1 branch, 1 loop or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Qdrant
- **Model:** A language model, family not declared
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Qdrant account, and a key for a language model. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls a language model. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 27 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 27 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fvision-rag-and-image-embeddings-with-cohere-command-a)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Qdrant](https://millionrounds.com/workflows?service=Qdrant#library)

## Workflows like it

Also ai assistants, with the same services where possible, closest in size first.

- [**Voice AI chatbot with OpenAI and RAG** 27 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/voice-ai-chatbot-with-openai-and-rag)
- [**Build a self-updating RAG system with OpenAI and Qdrant** 25 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/build-a-self-updating-rag-system-with-openai-and-qdrant)
- [**Building RAG chatbot for movie recommendations with Qdrant** 25 steps · calls a model · GitHub, Qdrant](https://millionrounds.com/workflow/building-rag-chatbot-for-movie-recommendations-with-qdrant)
- [**Building RAG chatbot for movie recommendations with Qdrant** 25 steps · calls a model · GitHub, Qdrant](https://millionrounds.com/workflow/building-rag-chatbot-for-movie-recommendations-with-qdrant-2)
- [**Adaptive RAG strategy with Gemini and Qdrant** 30 steps · calls a model · Qdrant](https://millionrounds.com/workflow/adaptive-rag-strategy-with-gemini-and-qdrant)
- [**Adaptive RAG with Gemini and Qdrant:** 30 steps · calls a model · Qdrant](https://millionrounds.com/workflow/adaptive-rag-with-gemini-and-qdrant)