Ollama support?

[BluePhi09]

Is there any way to use Ollama to host the llm models?

[MikeyBeez]

This should be easy:
from langchain.llms import Ollama
ollama = Ollama(base_url='http://localhost:11434', model="llama2")
response = ollama(prompt)

Cheers!

[shaileshjswl]

Import the Ollama class from langchain.llms

from langchain.llms import Ollama

Create an instance of the Ollama class with specified parameters

ollama = Ollama(base_url='http://localhost:11434', model="llama2")

Define the prompt you want to send to the Ollama model

prompt = "Your prompt goes here"

Make a request to the Ollama model with the provided prompt

response = ollama(prompt)

Print the response from the Ollama model

print(response)