运行本地 LLM 和发出 API 请求的快速指南

curl https://api.openai.com/v1/chat/completions   -h "content-type: application/json"   -h "authorization: bearer $openai_api_key"   -d '{     "model": "gpt-4o-mini",     "messages": [{"role": "user", "content": "say this is a test!"}],     "temperature": 0.7   }'

curl http://localhost:1234/v1/chat/completions   -h "content-type: application/json"   -d '{    "model": "llama-3.1-8b-lexi-uncensored-v2",    "messages": [      { "role": "system", "content": "always answer in rhymes. today is thursday" },      { "role": "user", "content": "what day is it today?" }    ],    "temperature": 0.7,    "max_tokens": -1,    "stream": false}'

import requestsimport jsonurl = "http://localhost:1234/v1/chat/completions"headers = {    "Content-Type": "application/json"}data = {    "model": "llama-3.1-8b-lexi-uncensored-v2",    "messages": [        {"role": "system", "content": "You are a helpful assistant."},        {"role": "user", "content": "What is the capital of France?"}    ],    "temperature": 0.7,    "max_tokens": -1,    "stream": False}response = requests.post(url, headers=headers, data=json.dumps(data))if response.status_code == 200:    result = response.json()    print(result["choices"][0]["message"]["content"])else:    print(f"Error: {response.status_code}")