A support chatbot from your website — answering from your materials

Through tilda the scenario reads the whole site and stores it in pinecone memory, then the bot answers clients from these materials, remembering the flow of the conversation.

  • The bot answers from your site, not from thin air
  • The site is read and remembered once
  • Clients get answers instantly, no waiting
  • You stop answering the same questions over and over
Embeddings OpenAIMap Website URLsPinecone Vector StoreDefault Data Loader
Connect the services and launchScriptera

How it works

To connect tilda and Embeddings OpenAI, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: When clicking ‘Execute workflow’
  2. Then: Map Website URLs
  3. Then: Filter and Normalize URLs
  4. Check: Process URLs One by One
  5. Then: Fetch Page Content
  6. Then: Extract HTML and URL
  7. Then: Clean HTML to Text
  8. Check: Check Text Length
  9. If yes: Split Text into Chunks
  10. Then: Store in Vector Database
  11. Then: Embeddings OpenAI
  12. Then: Document Loader
  13. Starts when: When chat message received
  14. Then: Customer Support Agent
  15. Then: Chat Memory
  16. Then: OpenAI Chat Model
  17. Then: OpenAI Embeddings
  18. Then: Pinecone Vector Storage

You can launch this tilda + Embeddings OpenAI integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios