Unable to get llama3 to serve json reponse on a local ollama installaiton using jupyter notebook

Question

On a windows 11 machine, I am trying to get a json reponse from the llama3 model on my local ollama installation on jupyter notebook but it does not work
Steps I tried:

This below snippet works

import ollama
prompt = "What is the capital of France?"
response = ollama.chat(
    model="llama3",
    messages=[{"role":"user","content":prompt}]
)
print(response['message']['content'])

But this one does not work:

import requests

def query_ollama(prompt: str, model: str = "llama3") -> dict:
    url = "http://localhost:11434/completion"  # Try this endpoint
    payload = {"model": model, "prompt": prompt}
    response = requests.post(url, json=payload)

    # Debug output
    print("Status Code:", response.status_code)
    print("Raw Response:", response.text)

    if response.status_code == 200:
        try:
            return response.json()
        except ValueError as e:
            print("JSON Decode Error:", e)
            return {"error": "Invalid JSON response"}
    else:
        return {"error": f"Request failed with status code {response.status_code}"}

# Test the function
prompt = "What is the capital of France?"
response_json = query_ollama(prompt)
print(response_json)

Output is Status Code: 404 Raw Response: 404 page not found {'error': 'Request failed with status code 404'}

I tried

!taskkill /F /IM ollama.exe 
!ollama serve #(which kind of hangs,maybe coz its busy serving!) 
!curl http://localhost:11434/models #(gives 404 page not found)

I'm so confused, what is wrong here? TIA