Skip to content

Latest commit

 

History

History
42 lines (32 loc) · 891 Bytes

README.md

File metadata and controls

42 lines (32 loc) · 891 Bytes
Raw

Ask The Documents (Embeddings / ChatGPT) with Wasp & PG Vector

Ask The Documents Cover

What does it do?

This is an example Wasp app that supports:

  • scraping whole link hierarchies (great for docs)
  • scraping a single link
  • generating embeddings for page content
  • semantic search using PG Vector
  • chatting with the documents using OpenAI's ChatGPT

Running it locally

First, makes sure you have Wasp installed.

curl -sSL https://get.wasp-lang.dev/installer.sh | sh

Then, close this repo and start the database with:

./custom-db/run_db.sh

Follow the instructions in the script.

Fill the env variables in .env.server:

OPENAI_API_KEY=<your_key>
DATABASE_URL=postgresql://postgres:devpass@localhost:5432/postgres

Migrate the database with:

wasp db migrate-dev

Then, start the server with:

wasp start