[Demo] RAG chatbot with Pinecone and Vercel's AI SDK

Created by our developer advocate, Roie Schwaber-Cohen. We use Vercel’s AI SDK and OpenAI for completion and embeddings. You can demonstrate recursive and markdown chunking and explore the difference in performance. You can easily deploy the application on your using the Vercel CLI.
We use 3 random URLs that are crawled on request - these could be changed very easily by modifying this file.

Screenshot 2024-01-19 at 5.07.31 PM

Demonstrates a URL crawl, data chunking and embedding, and semantic questioning.

  • Select a demo URL to index
  • Pick a chunking method (markdown/recursive)
  • Embed and upsert

The left pane displays your chatbot powered by Pinecone, beside the right pane allows you to compare a chatbot without context.