Ollama 网址下载

再cmd，用 library 里面的库

英文对话：

Gemma is available in both 2b and 7b parameter sizes:

• ollama run gemma:2b
• ollama run gemma:7b (default)

中文对话

• ollama run qwen:0.5b
• ollama run qwen:1.8b

用vscode而不是cmd调用 D:\Research\flower_exif\gemma_local.py

from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain_community.llms.ollama import Ollamallm = Ollama(base_url="http://localhost:11434",model="qwen:1.8b",)def get_completion_ollama(prompt):return llm.invoke(prompt)prompt = 'could you describe a storm weather'
res = get_completion_ollama(prompt=prompt)
print(res)