> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aihubmix.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 向量嵌入

> AiHubMix 提供 OpenAI 相容的高效率向量嵌入解決方案。

## 使用指南

AiHubMix 嵌入模型能夠高效地將文本或文件內容轉換為可搜尋的向量資料，廣泛應用於 RAG 問答系統和智能客戶支援。無論是純文本還是完整文件，您都可以透過單次呼叫生成嵌入，大幅改善語義處理能力。

<CodeGroup>
  ```py 通用嵌入 theme={null}
  from openai import OpenAI
  import os

  client = OpenAI(
      api_key="sk-***", # 替換為您在 AIHUBMIX 控制台生成的密鑰
      base_url="https://aihubmix.com/v1"
  )

  response = client.embeddings.create(
      input="您的文本字串放在這裡",
      model="gemini-embedding-001"
  )

  print(response.data[0].embedding)
  ```

  ```py 讀取文件並嵌入 theme={null}
  from openai import OpenAI
  import os

  client = OpenAI(
      api_key="sk-***", # 替換為您在 AIHUBMIX 控制台生成的密鑰
      base_url="https://aihubmix.com/v1"
  )

  # 讀取文件
  def read_whimery_file():
      try:
          with open('yourpath/file.md', 'r', encoding='utf-8') as file:
              return file.read()
      except Exception as e:
          print(f"讀取文件錯誤: {e}")
          return None

  # 讀取內容並建立嵌入
  content = read_whimery_file()
  if content:
      response = client.embeddings.create(
          input=content,
          model="gemini-embedding-001"
      )
      
      print("文件內容已成功處理為嵌入")
      print(f"嵌入維度: {len(response.data[0].embedding)}")
      print("前10個嵌入值:", response.data[0].embedding[:10])
  else:
      print("讀取文件內容失敗")

  ```
</CodeGroup>

## 可用模型

* gemini-embedding-001
* gemini-embedding-exp-03-07
* text-embedding-3-large
* text-embedding-3-small
* text-embedding-ada-002
* jina-embeddings-v4
* jina-embeddings-v3
* jina-embeddings-v2-base-code
* text-embedding-v4
* Qwen/Qwen3-Embedding-0.6B
* doubao-embedding-large-text-240915
* doubao-embedding-text-240715

***

最後更新：2026-06-01