python调用本地ollama部署的模型

使用langchain调用ollama部署的模型

from langchain_community.llms import ollama
host = "127.0.0.1"
port = "11434"
URL_ADDRESS = f"http://{host}:{port}"
model = "qwen2.5"
llm = ollama.Ollama(model=model, base_url=URL_ADDRESS, temperature=0)
res = llm.invoke(message)
print(res)

使用requests调用ollama部署的模型

host = "127.0.0.1"
port = "11434"
url = f"http://{host}:{port}/api/chat"
model = "qwen2.5"
headers = {"Content-Type": "application/json"}
data = {
    "model":model,#模型选择
    "options": {
    "temperature":0.#为0表示不让模型自由发挥,输出结果相对较固定,>0的话,输出的结果会比较放飞自我
    },
    "stream":False,#流式输出
    "messages": [
        {
            "role": "system",
            "content":"你是谁?"
        }
    ]#对话列表
}
response=requests.post(url,json=data,headers=headers,timeout=60)
res=response.json()
print(res)