Generate photo-based construction cost estimates with GPT-4 Vision and DDC CWICR
Ready for 3.0What this workflow does
This AI workflow has 25 nodes and runs when someone submits an n8n form (“📸 Photo Cost Estimate Pro v2”). Along the way it connects OpenAI Chat Model, Qdrant Vector Store and Embeddings OpenAI.
How it runs
Trigger: When someone submits an n8n form (“📸 Photo Cost Estimate Pro v2”).
- Extract Input (Code): runs custom JavaScript code
- Configure Language (Code): runs custom JavaScript code
- Has Photo? (If): checks a condition and branches into true / false
- STAGE 1 Vision Prompt (Edit Fields (Set)): sets 1 field: chatInput
- Error No Photo (Code): runs custom JavaScript code
- STAGE 1 Analyze Photo (Basic LLM Chain): sends a prompt to an LLM, with model: GPT-4 Vision
- Parse STAGE (Code): runs custom JavaScript code
- STAGE 4 Decompose Prompt (Edit Fields (Set)): sets 1 field: chatInput
- STAGE 4 Decompose LLM (Basic LLM Chain): sends a prompt to an LLM, with model: GPT-4 Decompose
- Parse STAGE (Code): runs custom JavaScript code
…plus 11 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- n8n Form Trigger
n8n-nodes-base.formTrigger - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - Edit Fields (Set)
n8n-nodes-base.set - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Wait
n8n-nodes-base.wait - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi
From the author
Upload a construction photo via web form → get a detailed cost estimate with work breakdown, resource costs, and professional HTML report. Powered by GPT-4 Vision and the open-source DDC CWICR database (55,000+ work items). Who's it for - Site managers who…