I wasn't able to find much information on giving vision to GPT-4o via LangChain, but I did find these pages:
- LangChain Discussion Question
- This OpenAI documentation may also be helpful, but expects images to have a URL, so it's not likely the route I'll want to go. I could see it being useful in the event that I finagle images inside a
HumanMessage shown in the below screenshot. Documentation
