LM Studio

https://lm-studio.cn/docs/basics/server

提示

我们支持所有 LM Studio 模型，只需在发送 litellm 请求时将 model=lm_studio/<any-model-on-lmstudio> 设置为前缀即可

属性	详情
描述	发现、下载并运行本地 LLM。
LiteLLM 上的提供商路由	lm_studio/
提供商文档	LM Studio ↗
支持的 OpenAI 端点	/chat/completions, /embeddings, /completions

API 密钥

# env variable
os.environ['LM_STUDIO_API_BASE']
os.environ['LM_STUDIO_API_KEY'] # optional, default is empty

示例用法

from litellm import completion
import os

os.environ['LM_STUDIO_API_BASE'] = ""

response = completion(
    model="lm_studio/llama-3-8b-instruct",
    messages=[
        {
            "role": "user",
            "content": "What's the weather like in Boston today in Fahrenheit?",
        }
    ]
)
print(response)

示例用法 - 流式传输

from litellm import completion
import os

os.environ['LM_STUDIO_API_KEY'] = ""
response = completion(
    model="lm_studio/llama-3-8b-instruct",
    messages=[
        {
            "role": "user",
            "content": "What's the weather like in Boston today in Fahrenheit?",
        }
    ],
    stream=True,
)

for chunk in response:
    print(chunk)

与 LiteLLM 代理服务器一起使用

以下是如何使用 LiteLLM 代理服务器调用 LM Studio 模型

1. 修改 config.yaml

   model_list:
     - model_name: my-model
       litellm_params:
         model: lm_studio/<your-model-name>  # add lm_studio/ prefix to route as LM Studio provider
         api_key: api-key                 # api key to send your model

2. 启动代理

   $ litellm --config /path/to/config.yaml

3. 向 LiteLLM 代理服务器发送请求

   OpenAI Python v1.0.0+

   import openai
   client = openai.OpenAI(
       api_key="sk-1234",             # pass litellm proxy key, if you're using virtual keys
       base_url="http://0.0.0.0:4000" # litellm-proxy-base url
   )
   
   response = client.chat.completions.create(
       model="my-model",
       messages = [
           {
               "role": "user",
               "content": "what llm are you"
           }
       ],
   )
   
   print(response)

   curl

   curl --location 'http://0.0.0.0:4000/chat/completions' \
       --header 'Authorization: Bearer sk-1234' \
       --header 'Content-Type: application/json' \
       --data '{
       "model": "my-model",
       "messages": [
           {
           "role": "user",
           "content": "what llm are you"
           }
       ],
   }'

支持的参数

请参阅 支持的参数 查看支持的参数。

嵌入

from litellm import embedding
import os 

os.environ['LM_STUDIO_API_BASE'] = "http://localhost:8000"
response = embedding(
    model="lm_studio/jina-embeddings-v3",
    input=["Hello world"],
)
print(response)

结构化输出

LM Studio 通过 JSON Schema 支持结构化输出。您可以使用 response_format 传递 pydantic 模型或原始 schema。LiteLLM 将 schema 作为 { "type": "json_schema", "json_schema": {"schema": <your schema>} } 发送。

from pydantic import BaseModel
from litellm import completion

class Book(BaseModel):
    title: str
    author: str
    year: int

response = completion(
    model="lm_studio/llama-3-8b-instruct",
    messages=[{"role": "user", "content": "Tell me about The Hobbit"}],
    response_format=Book,
)
print(response.choices[0].message.content)