#  配置一下解释器
#  uv add langchain_ollama

from langchain_core.messages import HumanMessage
from langchain_ollama import ChatOllama

#此时调用的是本地的大模型。省略base_url、api-key
llm = ChatOllama(
    model = "gemma4:26b",
)


# llm.invoke("你好，请介绍一下你自己！")


messages = [
    HumanMessage(content="你好，请介绍一下你自己！")
]

# response = llm.invoke(messages)
# print(response.content)

chunks = []
for chunk in llm.stream(messages):
    # chunks.append(chunk)
    print(chunk.content, end="", flush=True)