Vision RAG and image embeddings using Cohere Command-A and Embed v4
UnknownWhat this workflow does
This AI workflow has 27 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Cohere Chat Model, Qdrant Vector Store, Embeddings Cohere and Qdrant (community). It also calls api.cohere.com over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Technology and Innovation Report (Edit Fields (Set)): sets or maps fields
- AI Agent: runs an AI agent, with model: Chat Model via Command-R; 1 tool (Technology Innovation Report Tool)
- Split Out: splits a list into separate items
- If: checks a condition and branches into true / false
- Batch (Loop Over Items (Split in Batches)): loops over the items in batches
- Get Query (Edit Fields (Set)): sets 2 fields: tool, query
- Respond to Chat (Chat): uses Chat, with memory: Simple Memory
- Quick Confirmation (Chat): uses Chat
- Download Page (HTTP Request): calls an HTTP API
- Get Relevant Images (Qdrant Vector Store): searches the Qdrant vector store, with embeddings: Embeddings
…plus 9 more steps. See the full node list below.
Services it uses
HTTP calls to: api.cohere.com
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-qdrant is verified or supports 3.0 (used in Insert Points, Create Collection).
Rarely used nodes in this template: @n8n/n8n-nodes-langchain.lmChatCohere
Nodes used (18)
- Manual Trigger
n8n-nodes-base.manualTrigger - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Split Out
n8n-nodes-base.splitOut - Aggregate
n8n-nodes-base.aggregate - Qdrant
n8n-nodes-qdrant.qdrant - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - No Operation, do nothing
n8n-nodes-base.noOp - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - If
n8n-nodes-base.if - Chat
@n8n/n8n-nodes-langchain.chat - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Code Tool
@n8n/n8n-nodes-langchain.toolCode - Cohere Chat Model
@n8n/n8n-nodes-langchain.lmChatCohere - Extract from File
n8n-nodes-base.extractFromFile - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Embeddings Cohere
@n8n/n8n-nodes-langchain.embeddingsCohere
From the author
Cohere's new multimodal model releases make building your own Vision RAG agents a breeze. If you're new to Multimodal RAG and for the intent of this template, it means to embed and retrieve only document scans relevant to a query and then have a vision model…