AI-powered knowledge assistant using Google Sheets, OpenAI, and Supabase Vector Search
Needs changesWhat this workflow does
This AI workflow has 16 nodes and runs on Google Sheets events. Along the way it connects OpenAI Chat Model, Embeddings OpenAI, Vector Store Question Answer and Supabase Vector Store and 2 more.
How it runs
Trigger: On Google Sheets events.
- Check If New Message (If): checks a condition and branches into true / false
- Extract Message (Edit Fields (Set)): sets or maps fields
- Generate Timestamp ID (Function): runs custom JavaScript (legacy Function node)
- Get Chat History (Google Sheets): uses Google Sheets
- Merge: merges the data from its input branches
- Format Conversation (Function): runs custom JavaScript (legacy Function node)
- Update AI Response (Google Sheets): uses Google Sheets
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 2 tools (Web Search Tool, Vector Store Tool); memory: Conversation Memory
Services it uses
Before you upgrade to n8n 3.0
3 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- Function (legacy) in Format Conversation, Generate Timestamp ID: replace with Code node, mode 'Run Once for All Items'.
- SerpApi (Google Search) in Web Search Tool: no direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
| Function (legacy) Format Conversation, Generate Timestamp ID | Code node, mode 'Run Once for All Items' |
| SerpApi (Google Search) Web Search Tool | No direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node |
Nodes used (13)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Edit Fields (Set)
n8n-nodes-base.set - Function
n8n-nodes-base.function - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Google Sheets Trigger
n8n-nodes-base.googleSheetsTrigger - If
n8n-nodes-base.if - Merge
n8n-nodes-base.merge - Google Sheets
n8n-nodes-base.googleSheets - SerpApi (Google Search)
@n8n/n8n-nodes-langchain.toolSerpApi
From the author
Description An intelligent conversational AI system that provides contextual responses by combining chat history, vector database knowledge retrieval, and web search capabilities. How it Works (High-level steps) Message Detection: Google Sheets trigger…