Monday back in Culver
LLM: Using GPT-4 to query a site
Here’s a quick incantation to use GPT-4 to ask questions about a site.
First off, you need a Python environment with these dependencies installed (assuming an environment is set up using poetry):
poetry add langchain beautifulsoup4 nest_asyncio ipython
poetry run ipython
Using langchain, load all pages referenced in this site’s sitemap.xml into a
vector index.
import os
from langchain.document_loaders.sitemap import SitemapLoader
from langchain.indexes import VectorstoreIndexCreator
os.environ["OPENAI_API_KEY"] = "..."
sitemap = "https://jtmoulia.srht.site/sitemap.xml"
sitemap_loader = SitemapLoader(web_path=sitemap)
index = VectorstoreIndexCreator().from_loaders([sitemap_loader])
# And now the site's vector index can be queried
index.query("When was I last in LA?")
Note: this will cost ~0.14c using OpenAI’s GPT-4 interface. The index can be persisted.
Exercise
Leg lifts using the squat rack – already feeling tight, so these legs are going to be curled tomorrow eve.
  Table 1:
  Lifting: Legs #9
| Exercise | Set | Weight | Reps | 
|---|---|---|---|
| BBell Squat | 1 | 95 | 12 | 
| BBell Squat | 2 | 135 | 14 | 
| BBell Squat | 3 | 155 | 13 | 
| BBell Squat | 3 | 155 | 10 | 
| BBell Squat | 3 | 155 | 6 | 
| Calf Raise | 1 | 0 | 14 | 
| Calf Raise | 2 | 25 | 14 | 
| Calf Raise | 3 | 0 | 14 |