Difference between BaseChatModel and BaseLLM for text extraction

[konstantinoskalyfommatos]

In theory, would one of those 2 work better for text extraction, if the model is the same?

from langchain_community.llms.ollama import Ollama

llm = Ollama(model="llama3.1", temperature=0)

from langchain_ollama import ChatOllama

llm = ChatOllama(model="llama3.1", temperature=0)

[eyurtsev]

I wrote kor before chat models were a big thing, so prompts are probably better tuned for llms all else being equal.

Otherwise I'd use langchain_ollama since that's the official integration for ollama.