Tried following this with Llama 2 13b
https://www.pinecone.io/learn/llama-2/
I get "ValueError: unknown format from LLM: "
You could try an open source LLM like Llama 2. You could probably use Langchain tools to give it a tool to tag when a tweet has harmful content.
Got it working with Llama 2 70b following the tutorial from James Briggs. Note it did not work with Llama 2 13b which returned an empty output at the end. https://stackoverflow.com/questions/77491941/llama-2-with-langchain-tools