# 向量儲存 API

向量儲存 API 允許您在 Rememberizer 中創建、管理和搜尋向量儲存。向量儲存使您能夠使用語義相似性搜尋來儲存和檢索文件。

## 可用的向量存儲端點

### 管理端點

* [獲取向量儲存的資訊](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/get-vector-stores-information.md)
* [獲取向量儲存中的文件列表](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/get-a-list-of-documents-in-a-vector-store.md)
* [獲取文件的資訊](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/get-the-information-of-a-document.md)

### 文件操作

* [將新文本文件添加到向量存儲](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/add-new-text-document-to-a-vector-store.md)
* [上傳文件到向量存儲](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/upload-files-to-a-vector-store.md)
* [更新向量存儲中文件的內容](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/update-files-content-in-a-vector-store.md)
* [在向量存儲中移除文件](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/remove-a-document-in-vector-store.md)

### 搜尋操作

* [根據語義相似性搜尋向量儲存文件](/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store/search-for-vector-store-documents-by-semantic-similarity.md)

## 創建向量存儲

要創建新的向量存儲，請使用以下端點：

```
POST /api/v1/vector-stores/
```

### 請求主體

```json
{
  "name": "商店名稱",
  "description": "商店描述",
  "embedding_model": "sentence-transformers/all-mpnet-base-v2",
  "indexing_algorithm": "ivfflat",
  "vector_dimension": 128,
  "search_metric": "cosine_distance"
}
```

### 回應

```json
{
  "id": "store_id",
  "name": "向量商店名稱",
  "description": "商店描述",
  "created": "2023-05-01T00:00:00Z",
  "modified": "2023-05-01T00:00:00Z"
}
```

## 向量儲存配置

要檢索可用的向量儲存配置，請使用：

```
GET /api/v1/vector-stores/configs
```

這將返回可用的嵌入模型、索引算法和搜索指標，這些可以在創建或配置向量儲存時使用。

## 認證

所有 Vector Store 端點都需要使用以下方式進行認證：

* 用於管理操作的 JWT 令牌
* 用於文檔和搜索操作的 API 密鑰


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.rememberizer.ai/zh-hk/kai-fa-zhe-zi-yuan/api-docs/vector-store.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.