Run Llama 3.1 with Ollama and Google Colab for Free Using AdalFlow

 This video shows hands-on tutorial as how to run Llama 3.1 8B model with Ollama on free Google colab with AdalFlow.

Code:

!sudo apt-get install -y pciutils

!curl -fsSL https://ollama.com/install.sh | sh # download ollama api

from IPython.display import clear_output

# Create a Python script to start the Ollama API server in a separate thread

import os

import threading

import subprocess

import requests

import json

def ollama():

    os.environ['OLLAMA_HOST'] = '0.0.0.0:11434'

    os.environ['OLLAMA_ORIGINS'] = '*'

    subprocess.Popen(["ollama", "serve"])

ollama_thread = threading.Thread(target=ollama)

ollama_thread.start()

from IPython.display import clear_output

!ollama pull llama3.1:8b  

clear_output()

!pip install -U lightrag[ollama]

from lightrag.core.generator import Generator

from lightrag.core.component import Component

from lightrag.core.model_client import ModelClient

from lightrag.components.model_client import OllamaClient, GroqAPIClient

import time

qa_template = r"""<SYS>

You are a helpful assistant.

</SYS>

User: {{input_str}}

You:"""

class SimpleQA(Component):

    def __init__(self, model_client: ModelClient, model_kwargs: dict):

        super().__init__()

        self.generator = Generator(

            model_client=model_client,

            model_kwargs=model_kwargs,

            template=qa_template,

        )

    def call(self, input: dict) -> str:

        return self.generator.call({"input_str": str(input)})

    async def acall(self, input: dict) -> str:

        return await self.generator.acall({"input_str": str(input)})

       

from lightrag.components.model_client import OllamaClient

from IPython.display import Markdown, display

model = {

    "model_client": OllamaClient(),

    "model_kwargs": {"model": "llama3.1:8b"}

}

qa = SimpleQA(**model)

output=qa("what is happiness")

display(Markdown(f"**Answer:** {output.data}"))