Skip to content

Commit baf125c

Browse files
authored
Merge pull request #280 from Rabithua/codex/rename-ai-memory-to-memory
[codex] Rename AI Memory wording to Memory
2 parents be2da02 + f7220d5 commit baf125c

15 files changed

Lines changed: 57 additions & 57 deletions

File tree

README.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -35,7 +35,7 @@
3535
- **Self-Hosted Deployment**: One-click deployment using Docker or Dokploy
3636
- **Separated Architecture**: Frontend and backend use separated architecture design, deploy only the services you need
3737
- **Markdown Articles**: Standalone Article support, can be referenced by notes, offering a pure writing and reading experience
38-
- **AI Memory**: Optional AI chat over your own notes and articles, with semantic search, related notes, streamed responses, and source references
38+
- **Memory**: Optional AI chat over your own notes and articles, with semantic search, related notes, streamed responses, and source references
3939
- **Admin-Controlled AI**: AI, vector storage, automatic indexing, and public semantic discovery are disabled by default and must be explicitly enabled by an administrator
4040
- **iOS Client**: More elegant App client
4141

@@ -49,7 +49,7 @@ Copy [docker-compose.yml](docker-compose.yml) to your server with Docker and Doc
4949
>
5050
> Rote now uses `pgvector/pgvector:pg17-trixie` by default. It behaves like PostgreSQL 17 and additionally supports the optional AI vector extension. Plain `postgres:17` is only a temporary compatibility path and may not be supported by future Rote versions.
5151
>
52-
> `latest` is the stable image. If you are reading the develop branch documentation or testing unreleased AI Memory features, use `IMAGE_TAG=develop`.
52+
> `latest` is the stable image. If you are reading the develop branch documentation or testing unreleased Memory features, use `IMAGE_TAG=develop`.
5353
5454
```bash
5555
# 1. Create a .env file beside docker-compose.yml
@@ -85,7 +85,7 @@ After the containers are running:
8585
1. Open `http://<your-ip-address>:18001`.
8686
2. Complete the setup page and create the first administrator account.
8787
3. Sign in and configure site settings from the Admin dashboard.
88-
4. Optional: if your image tag includes AI Memory support, open `Admin -> AI Settings` to configure chat and embedding providers, enable pgvector, and backfill existing notes/articles.
88+
4. Optional: if your image tag includes Memory support, open `Admin -> AI Settings` to configure chat and embedding providers, enable pgvector, and backfill existing notes/articles.
8989

9090
#### Method 2: Using Dokploy (Recommended)
9191

@@ -104,9 +104,9 @@ The iOS app can connect to your self-hosted backend.
104104
2. Set `API Base` to your public backend URL (or reverse-proxy URL).
105105
3. Continue with the normal login flow.
106106

107-
### AI Memory
107+
### Memory
108108

109-
AI Memory is optional and disabled by default. It is available in the `develop` image and will be available in stable images after the next release that includes AI Memory. Administrators can enable it from `Admin -> AI Settings` after configuring chat and embedding providers. Rote supports OpenAI-compatible providers, including OpenAI, OpenRouter, Ollama / LM Studio, DeepSeek, SiliconFlow, DashScope / Qwen, Zhipu GLM, Moonshot / Kimi, Volcengine Ark, Tencent Hunyuan, Baidu Qianfan, and custom OpenAI-compatible endpoints.
109+
Memory is optional and disabled by default. It is available in the `develop` image and will be available in stable images after the next release that includes Memory. Administrators can enable it from `Admin -> AI Settings` after configuring chat and embedding providers. Rote supports OpenAI-compatible providers, including OpenAI, OpenRouter, Ollama / LM Studio, DeepSeek, SiliconFlow, DashScope / Qwen, Zhipu GLM, Moonshot / Kimi, Volcengine Ark, Tencent Hunyuan, Baidu Qianfan, and custom OpenAI-compatible endpoints.
110110

111111
Only authenticated, email-verified users can use AI features. AI conversations stay in the current browser session and are not persisted to the database. Notes and articles are indexed only when AI vector storage and automatic indexing are enabled by an administrator.
112112

@@ -117,7 +117,7 @@ For more deployment options and configuration instructions, please check the doc
117117
- [Self-Hosted Deployment Guide](https://rote.ink/doc/selfhosted) - Complete deployment and configuration guide
118118
- [API Documentation](doc/userguide/API-ENDPOINTS.md) - API interface usage guide
119119
- [API Key Guide](doc/userguide/API-KEY-GUIDE.md) - How to use API Key
120-
- [AI Vector Migration Guide](doc/userguide/AI-VECTOR-MIGRATION.zh.md) - Upgrade an existing self-hosted database to AI Memory and pgvector support (Chinese)
120+
- [AI Vector Migration Guide](doc/userguide/AI-VECTOR-MIGRATION.zh.md) - Upgrade an existing self-hosted database to Memory and pgvector support (Chinese)
121121
- [User-local AI Guide](doc/userguide/LOCAL-AI.zh.md) - Run Gemma on the user's own computer without sending model requests through the Rote server (Chinese)
122122

123123
### Video Tutorials (Bilibili)

doc/README.zh.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -35,7 +35,7 @@
3535
- **自托管部署**:使用 Docker 或者 Dokploy 一键部署
3636
- **分离架构**:前后端采用分离的架构设计,按需部署你需要的服务
3737
- **Markdown 文章**:独立文章支持,可被笔记引用,提供纯粹的读写体验
38-
- **AI 记忆**:可选的 AI 对话、语义搜索、相关笔记、流式回答和来源引用,基于你自己的笔记与文章工作
38+
- **记忆**:可选的 AI 对话、语义搜索、相关笔记、流式回答和来源引用,基于你自己的笔记与文章工作
3939
- **管理员控制 AI**:AI、向量存储、自动索引和公开 Explore 语义发现默认关闭,必须由管理员显式启用
4040
- **iOS 客户端**:更优雅的 App 客户端
4141

@@ -49,7 +49,7 @@
4949
>
5050
> Rote 现在默认使用 `pgvector/pgvector:pg17-trixie`。它保持 PostgreSQL 17 行为,并额外支持可选的 AI 向量扩展。普通 `postgres:17` 只作为临时兼容路径,后续 Rote 版本可能不再支持。
5151
>
52-
> `latest` 是稳定版镜像。如果你正在阅读 develop 分支文档,或者测试尚未发布的 AI 记忆能力,请使用 `IMAGE_TAG=develop`
52+
> `latest` 是稳定版镜像。如果你正在阅读 develop 分支文档,或者测试尚未发布的记忆能力,请使用 `IMAGE_TAG=develop`
5353
5454
```bash
5555
# 1. 在 docker-compose.yml 旁边创建 .env 文件
@@ -85,7 +85,7 @@ POSTGRES_IMAGE=postgres:17
8585
1. 打开 `http://<your-ip-address>:18001`
8686
2. 在初始化页面创建第一个管理员账号。
8787
3. 登录后进入管理员后台完成站点配置。
88-
4. 可选:如果当前镜像包含 AI 记忆能力,进入 `管理 -> AI 相关` 配置对话模型和向量模型,启用 pgvector,并为存量笔记/文章建立索引。
88+
4. 可选:如果当前镜像包含记忆能力,进入 `管理 -> AI 相关` 配置对话模型和向量模型,启用 pgvector,并为存量笔记/文章建立索引。
8989

9090
#### 方式二:使用 Dokploy(推荐)
9191

@@ -104,9 +104,9 @@ iOS App 支持连接到你自部署的后端。
104104
2.`API Base` 修改为你自部署后端的公网地址(或反向代理地址)。
105105
3. 按正常流程登录即可。
106106

107-
### AI 记忆
107+
### 记忆
108108

109-
AI 记忆是可选能力,默认关闭。它已经可以在 `develop` 镜像中使用,并会在包含 AI 记忆的下一个稳定版发布后进入稳定镜像。管理员可以在 `管理 -> AI 相关` 配置对话模型和向量模型后启用。Rote 支持 OpenAI-compatible 供应商,包括 OpenAI、OpenRouter、Ollama / LM Studio、DeepSeek、SiliconFlow、DashScope / Qwen、Zhipu GLM、Moonshot / Kimi、Volcengine Ark、Tencent Hunyuan、Baidu Qianfan,以及自定义 OpenAI-compatible 接口。
109+
记忆是可选能力,默认关闭。它已经可以在 `develop` 镜像中使用,并会在包含记忆的下一个稳定版发布后进入稳定镜像。管理员可以在 `管理 -> AI 相关` 配置对话模型和向量模型后启用。Rote 支持 OpenAI-compatible 供应商,包括 OpenAI、OpenRouter、Ollama / LM Studio、DeepSeek、SiliconFlow、DashScope / Qwen、Zhipu GLM、Moonshot / Kimi、Volcengine Ark、Tencent Hunyuan、Baidu Qianfan,以及自定义 OpenAI-compatible 接口。
110110

111111
只有已登录且已认证的用户可以使用 AI 功能。AI 对话只保存在当前浏览器会话中,不会持久化写入数据库。只有在管理员开启 AI 向量存储和自动索引后,笔记与文章才会进入向量索引。
112112

@@ -117,7 +117,7 @@ AI 记忆是可选能力,默认关闭。它已经可以在 `develop` 镜像中
117117
- [自托管部署指南](https://rote.ink/doc/selfhosted) - 完整的部署和配置说明
118118
- [API 文档](doc/userguide/API-ENDPOINTS.md) - API 接口使用指南
119119
- [API Key 指南](doc/userguide/API-KEY-GUIDE.md) - 如何使用 API Key
120-
- [AI Vector 迁移指南](doc/userguide/AI-VECTOR-MIGRATION.zh.md) - 旧版线上数据库升级到 AI 记忆与 pgvector 的操作说明
120+
- [AI Vector 迁移指南](doc/userguide/AI-VECTOR-MIGRATION.zh.md) - 旧版线上数据库升级到记忆与 pgvector 的操作说明
121121
- [用户本地 AI 指南](userguide/LOCAL-AI.zh.md) - 在用户自己的电脑运行 Gemma,模型请求不经过 Rote 服务端
122122

123123
### 视频教程(B 站)

doc/userguide/AI-VECTOR-MIGRATION.zh.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# 旧版线上数据库迁移到 AI Vector 特性指南
22

3-
本文档面向已经在线上运行 Rote 的自托管实例,说明如何从旧版普通 PostgreSQL 数据库升级到支持 AI 记忆、语义搜索和 pgvector 的新版。
3+
本文档面向已经在线上运行 Rote 的自托管实例,说明如何从旧版普通 PostgreSQL 数据库升级到支持记忆、语义搜索和 pgvector 的新版。
44

55
新版会新增 `document_embeddings``embedding_jobs` 两张表。原有笔记、文章、用户、配置等业务数据不会被重写。AI、向量存储和公开 Explore 语义检索默认关闭,必须由管理员在后台显式开启。
66

@@ -10,7 +10,7 @@
1010

1111
- 旧版使用 `docker-compose.yml``docker-compose.build.yml` 部署。
1212
- 数据库容器原来使用 `postgres:17` 或旧版 compose 默认 PostgreSQL 镜像。
13-
- 希望升级到新版 AI 记忆、相关笔记、语义搜索、RAG 对话能力。
13+
- 希望升级到新版记忆、相关笔记、语义搜索、RAG 对话能力。
1414

1515
不适用于 PostgreSQL 大版本迁移。本文默认旧库和新库都保持 PostgreSQL 17。不要在同一个数据卷上跨 PostgreSQL 大版本直接换镜像。
1616

doc/userguide/API-ENDPOINTS.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -84,7 +84,7 @@
8484

8585
参数:`keyword`(必填),可选 `skip/limit/archived/tag`
8686

87-
### 7) AI Memory
87+
### 7) Memory
8888

8989
| 路径 | 方法 | 认证 | 描述 |
9090
| --------------------------- | ---- | ---- | ---------------------------- |

doc/userguide/HERMES-LIKE-AHENT.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -827,7 +827,7 @@ Timeline 应该尽早出现,不等第一段回答文本。推荐规则:
827827

828828
```txt
829829
Sources
830-
- note_123: AI Memory Plan
830+
- note_123: Memory Plan
831831
- note_456: Rote 检索设计
832832
- article_789: Agent Runtime 草案
833833
```

doc/userguide/LOCAL-AI.zh.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -54,7 +54,7 @@ bun run scripts/local-ai-bridge.ts
5454

5555
## 3. 在 Rote 中连接
5656

57-
1. 登录 Rote 并进入 `AI 记忆`
57+
1. 登录 Rote 并进入 `记忆`
5858
2. 选择 `本地模型`
5959
3. 填写:
6060
- 桥接器地址:`http://127.0.0.1:11435`

server/authz/aiAccess.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ import { getPgvectorStatus, getStoredAiConfig } from '../utils/dbMethods/ai';
33
import { getEffectiveCapabilitiesForUser } from './capabilityService';
44

55
export const AI_CERTIFICATION_REQUIRED_MESSAGE = 'AI features require a certified account';
6-
export const AI_MEMORY_UNAVAILABLE_MESSAGE = 'AI memory tools are not available';
6+
export const AI_MEMORY_UNAVAILABLE_MESSAGE = 'Memory tools are not available';
77

88
type AiAccessUser = {
99
id: string;

server/route/v2/ai.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -258,7 +258,7 @@ aiRouter.post('/site/test', authenticateJWT, async (c: HonoContext) => {
258258
? 'Site chat model works, but tool calling was not detected'
259259
: vectorAvailable
260260
? 'Site AI test successful'
261-
: 'Site chat model works, but AI memory vector index is not ready'
261+
: 'Site chat model works, but memory vector index is not ready'
262262
),
263263
200
264264
);

server/tests/aiIntegration.test.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
/**
2-
* AI Memory Integration Tests
2+
* Memory Integration Tests
33
*
44
* 直接调用 prepareRoteChatContext + createChatCompletionStream,
55
* 验证完整的 LLM Planner → pgvector 检索 → Chat 补全 pipeline。

server/utils/dbMethods/ai.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -118,7 +118,7 @@ export async function getOwnerAiMemoryStats(ownerId: string): Promise<{
118118
indexedRoteCount: Number(indexedRoteRows[0]?.count) || 0,
119119
};
120120
} catch (error: any) {
121-
throw new DatabaseError('Failed to get AI memory stats', error);
121+
throw new DatabaseError('Failed to get memory stats', error);
122122
}
123123
}
124124

0 commit comments

Comments
 (0)