Aggregate web product reviews and sentiment with Decodo and Google Gemini
UnknownWhat this workflow does
This AI workflow has 13 nodes and runs on Telegram events (message). Along the way it connects Google Gemini Chat Model, Telegram and Decodo (community).
How it runs
Trigger: On Telegram events (message).
- Set Search Query (Edit Fields (Set)): sets 1 field: query
- Google Search (Decodo): google search
- Extract URLs (Code): runs custom JavaScript code
- Scrape Page Content (Decodo): uses Decodo
- Clean HTML (Code): runs custom JavaScript code
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Merge Results (Code): runs custom JavaScript code
- Analyze Sentiment (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
- Draft Final Report (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
- Reply to User (Telegram): uses Telegram
Services it uses
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 @decodo/n8n-nodes-decodo is verified or supports 3.0 (used in Google Search1, Scrape Page Content1).
Nodes used (8)
- Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Telegram Trigger
n8n-nodes-base.telegramTrigger - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Telegram
n8n-nodes-base.telegram - Decodo
@decodo/n8n-nodes-decodo.decodo
From the author
What Problem Does It Solve? - Brands and marketers spend hours manually searching Google for product reviews. - Reading through multiple websites to gauge general sentiment is tedious and inefficient. - It is difficult to spot recurring customer complaints or…