公司服务器无法联网，有本地加载模型和数据集的例子嘛？

[mitergpt]

System Info

谢谢，公司服务无法联网

Reproduction

Put your message here.

Others

No response

[Ki-Seki]

examples/basic_modules/llm.py 里有使用本地模型的示例，修改 model_name_or_path 即可。

from memos.configs.llm import LLMConfigFactory
from memos.llms.factory import LLMFactory


config = LLMConfigFactory.model_validate(
    {
        "backend": "huggingface",
        "config": {
            "model_name_or_path": "Qwen/Qwen3-1.7B",
            "temperature": 0.8,
            "max_tokens": 1024,
            "top_p": 0.9,
            "top_k": 50,
        },
    }
)
llm = LLMFactory.from_config(config)
messages = [
    {"role": "user", "content": "Hello, who are you"},
]
response = llm.generate(messages)
print("Scenario 4:", response)
print("==" * 20)

[Liulongfang]

LLM模型使用的本地网络部署的，如何配置LLM的URL？

[louroy411-art]

我这里测试的结果，
chat model 用的 back end 是 "openai"
然后 api_base 指向你本地 LLM 的 url 地址，比如：http://localhost:8087/v1
不需要在地址后添加 /chat/completions，这个好像是 MemoryOS自动补全

embedder同理，不过用的back end是 "universal_api"

[mitergpt]

谢谢 么么哒

[archieang]

Hey @mitergpt, @Liulongfang and @louroy411-art! Thanks for the contribution — already solved the issue, thanks for helping us to improve our project! 📈

Btw if you enjoyed contributing and want to stay connected with the project, we run a Discord server for contributors, a chill space to discuss features, ask questions, or pick up new issues  👉🏻 MemOS Discord Server (Contributor Exclusive)

Thanks again for shipping this, and happy MemOSing 🧠✨