AI agent 大模型实战之 本地部署及调用大模型ollama

https://ollama.com/

下载安装

可以安装各种大模型

安装
ollama run deepseek-r1:7b

提问 1+2+3 一直加到50等于多少

python 调用当前大模型

安装 langchain-ollama
uv add langchain-ollama

from langchain_core.prompts import ChatPromptTemplate
from langchain_ollama.llms import OllamaLLM

template = """Question: {question}

Answer: Let's think step by step."""

prompt = ChatPromptTemplate.from_template(template)

model = OllamaLLM(model="deepseek-r1:7b")

chain = prompt | model

resp = chain.invoke({"question": "你是谁?"})
print(resp)

# 流式打印
resp = chain.stream({"question": "你是谁?"})
for chunk in resp:
    print(chunk,end="")