pip install llama-cpp-python

pip install uvicorn
pip install anyio
pip install starlette
pip install fastapi
pip install pydantic_settings
pip install sse_starlette

from llama_cpp import Llama
llm = Llama(model_path="./models/7B/ggml-model.bin")
output = llm("Q: Name the planets in the solar system? A: ", max_tokens=32, stop=["Q:", "\n"], echo=True)
print(output)

{
  "id": "cmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "object": "text_completion",
  "created": 1679561337,
  "model": "./models/7B/ggml-model.bin",
  "choices": [
    {
      "text": "Q: Name the planets in the solar system? A: Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, Neptune and Pluto.",
      "index": 0,
      "logprobs": None,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 28,
    "total_tokens": 42
  }
}

import llama_cpp
import ctypes
params = llama_cpp.llama_context_default_params()
# use bytes for char * params
ctx = llama_cpp.llama_init_from_file(b"./models/7b/ggml-model.bin", params)
max_tokens = params.n_ctx
# use ctypes arrays for array params
tokens = (llama_cpp.llama_token * int(max_tokens))()
n_tokens = llama_cpp.llama_tokenize(ctx, b"Q: Name the planets in the solar system? A: ", tokens, max_tokens, add_bos=llama_cpp.c_bool(True))
llama_cpp.llama_free(ctx)

python3 -m llama_cpp.server --model models/7B/ggml-model.bin

import requests
  
url = 'http://localhost:8000/v1/chat/completions'
headers = {
	'accept': 'application/json',
	'Content-Type': 'application/json'
}
data = {
	'messages': [
		{
		'content': 'You are a helpful assistant.',
		'role': 'system'
		},
		{
		'content': 'What is the capital of France?',
		'role': 'user'
		}
	]
}
  
response = requests.post(url, headers=headers, json=data)
print(response.json())
print(response.json()['choices'][0]['message']['content'])