Templates / Route and analyze customer feedback with Qwen3-VL, Tally, PostgreSQL

Route and analyze customer feedback with Qwen3-VL, Tally, PostgreSQL

Unknown

by Neloy Barman ✓ · 119 views · created 2026-02-11 · Ticket Management, AI Summarization

Unknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.

What this workflow does

This AI workflow has 26 nodes and runs on Tally events. Along the way it connects OpenAI Chat Model, Discord, Postgres and Tallyforms (community).

How it runs

Trigger: On Tally events.

  1. Field Mapping (Edit Fields (Set)): sets 4 fields: Customer Name, Email Address, Message…
  2. Sentiment Analysis (Basic LLM Chain): sends a prompt to an LLM, with model: Sentiment LLM; output parser: Sentiment Parser
  3. If: checks a condition and branches into true / false
  4. Text Classification (Basic LLM Chain): sends a prompt to an LLM, with model: Classification LLM; output parser: Classification Parser
  5. AI Results Merge (Merge): merges the data from its input branches
  6. Fetch Image (HTTP Request): calls an HTTP API
  7. Empty Keywords Handler (Edit Fields (Set)): sets 1 field: keywords
  8. Data Aggregation (Aggregate): combines items into one
  9. Image Keyword Extraction (Code): runs custom JavaScript code
  10. Image Results Merge (Merge): merges the data from its input branches

…plus 9 more steps. See the full node list below.

Services it uses

OpenAI Chat ModelDiscordPostgresTallyforms (community)

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-tallyforms is verified or supports 3.0 (used in Tally Trigger).

Nodes used (13)

From the author

Self-Hosted This workflow provides a complete end-to-end system for capturing, analyzing, and routing customer feedback. By combining local multimodal AI processing with structured data storage, it allows teams to respond to customer needs in real-time…

Excerpt from Neloy Barman's description on n8n.io.

View the original on n8n.io → Check your own copy

Get the weekly “what broke” email

New templates, newly broken ones, and n8n release changes. One short email a week.

Form not loading? Subscribe here.