Conversational WhatsApp assistant with Gemini AI and Pinecone memory
Needs changesWhat this workflow does
This AI workflow has 11 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Google Gemini Chat Model, Embeddings OpenAI, Pinecone Vector Store and Wamm (community).
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model; 2 tools (Reading from Pinecone (from knowledge), Reading from Pinecone (at phone number))
- WAMM: Send Message (Wammpro): uses Wammpro
- Processing data for Pinecone (Code): runs custom JavaScript code
- Pinecone Vector Store: stores documents in the Pinecone vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Webhook
n8n-nodes-base.webhook - Wammpro
n8n-nodes-wamm.wammpro - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Code
n8n-nodes-base.code - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
From the author
📋 Description This template creates an intelligent AI assistant for WhatsApp that can: - Respond naturally to messages using Google Gemini AI - Remember previous conversations for each user - Access a knowledge base for answering frequently asked questions -…