GLM Embedding 3 是智譜 AI 的嵌入模型,可產生 2048 維向量,專為中英雙語檢索調校。廣泛應用於中文 RAG 管線,並以極低的成本在 C-MTEB 上達到與頂尖英文嵌入模型相當的水準。
可直接取代 OpenAI。只需變更 base_url 和 model。
# Python - pip install openai from openai import OpenAI client = OpenAI( base_url="https://meshtok.com/v1", api_key="sk-your-MeshTok-key", ) resp = client.chat.completions.create( model="bigmodel/embedding-3", messages=[{"role":"user","content":"Hello!"}], ) print(resp.choices[0].message.content)
# cURL curl https://meshtok.com/v1/chat/completions \ -H "Authorization: Bearer sk-your-MeshTok-key" \ -H "Content-Type: application/json" \ -d '{"model":"bigmodel/embedding-3","messages":[{"role":"user","content":"Hello!"}]}'
其他您可能考慮的模型。
Zhipu’s flagship with a 1M context window.
Balanced daily-driver from Zhipu.
Fast GLM variant for low-latency apps.
General-purpose chat model.