文档
本地运行 LLM
用户界面
高级
OpenAI 兼容性 API
发送请求到 Chat Completions(文本和图像)、Completions 和 Embeddings 终端节点。
LM Studio 接受对多个 OpenAI 终端节点的请求,并返回类 OpenAI 的响应对象。
GET /v1/models POST /v1/chat/completions POST /v1/embeddings POST /v1/completions
您可以通过切换 “base URL” 属性以指向您的 LM Studio 而不是 OpenAI 的服务器,来重用现有的 OpenAI 客户端(在 Python、JS、C# 等中)。
base url
以指向 LM Studio1234
from openai import OpenAI client = OpenAI( + base_url="https://127.0.0.1:1234/v1" ) # ... the rest of your code ...
import OpenAI from 'openai'; const client = new OpenAI({ + baseUrl: "https://127.0.0.1:1234/v1" }); // ... the rest of your code ...
- curl https://api.openai.com/v1/chat/completions \ + curl https://127.0.0.1:1234/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ - "model": "gpt-4o-mini", + "model": "use the model identifier from LM Studio here", "messages": [{"role": "user", "content": "Say this is a test!"}], "temperature": 0.7 }'
/v1/models
GET
请求curl https://127.0.0.1:1234/v1/models
/v1/chat/completions
POST
请求lms log stream
以查看模型接收到的输入# Example: reuse your existing OpenAI setup from openai import OpenAI # Point to the local server client = OpenAI(base_url="https://127.0.0.1:1234/v1", api_key="lm-studio") completion = client.chat.completions.create( model="model-identifier", messages=[ {"role": "system", "content": "Always answer in rhymes."}, {"role": "user", "content": "Introduce yourself."} ], temperature=0.7, ) print(completion.choices[0].message)
/v1/embeddings
POST
请求# Make sure to `pip install openai` first from openai import OpenAI client = OpenAI(base_url="https://127.0.0.1:1234/v1", api_key="lm-studio") def get_embedding(text, model="model-identifier"): text = text.replace("\n", " ") return client.embeddings.create(input = [text], model=model).data[0].embedding print(get_embedding("Once upon a time, there was a cat."))
/v1/completions
OpenAI 不再支持此类似 OpenAI 的终端节点。LM Studio 继续支持它。
将此终端节点与聊天调优模型一起使用可能会导致意外行为,例如模型发出多余的角色 token。
为了获得最佳结果,请使用基础模型。
POST
请求lms log stream
以查看模型接收到的输入有关每个参数的说明,请参阅https://platform.openai.com/docs/api-reference/chat/create。
model top_p top_k messages temperature max_tokens stream stop presence_penalty frequency_penalty logit_bias repeat_penalty seed
在 LM Studio Discord 服务器上与其他 LM Studio 开发者聊天,讨论 LLM、硬件等。