Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / Reports, Analytics & Dashboards

Reports, Analytics & Dashboards

Mine Customer Insights from Reviews with Qdrant and OpenAI

When you run it, it extracts reviews from a zip file, stores embeddings in Qdrant, clusters them and has OpenAI summarize insights into Google Sheets.

What it does

## Step 3. Store Reviews in Qdrant Learn more about the Qdrant Vector Store Vector databases are a great way to store data if you're interested in perform similiarity searches which applies here as we want to group similar reviews to find patterns. Qdrant is a powerful vector database and tool of choice because of its robust API implementation and advanced filtering capabilities.

The steps

  1. When clicking ‘Test workflow’
  2. Zip Entries
  3. Extract Reviews
  4. Reviews to List
  5. Default Data Loader
  6. Recursive Character Text Splitter
  7. Embeddings OpenAI
  8. Set Variables
  9. Get Payload of Points
  10. Clusters To List
  11. OpenAI Chat Model
  12. Only Clusters With 3+ points
  13. Set Variables1
  14. Find Reviews

24 steps in total.

Similar automations