docs(features): 更新本地知识库和记忆系统描述

Author: Licoy

README-EN.md

@@ -35,8 +35,8 @@
 ### Search & Knowledge
 
 - **Web Search** — Integrated with Tavily, Zhipu WebSearch, Bocha, and more, with citation source annotations
-- **Local Knowledge Base (RAG)** (Coming Soon) — Upload documents to build vector indices (LanceDB), with semantic retrieval during conversations
-- **Memory System** (Coming Soon) — Global and project-level memory, added manually or extracted automatically by AI
+- **Local Knowledge Base (RAG)** — Supports multiple knowledge bases; upload documents for automatic parsing, chunking, and indexing, with semantic retrieval of relevant passages during conversations
+- **Memory System** — Supports multi-namespace conversational memory, with manual entry or AI-powered auto-extraction (auto-extraction coming soon)
 - **Context Management** — Flexibly attach file attachments, search results, knowledge base passages, memory entries, and tool outputs
 
 ### Tools & Extensions

README.md

@@ -35,8 +35,8 @@
 ### 搜索与知识
 
 - **联网搜索** — 集成 Tavily、智谱 WebSearch、Bocha 等，搜索结果附带引用来源标注
-- **本地知识库（RAG）**（即将推出） — 上传文档后自动构建向量索引（LanceDB），对话时语义检索相关段落
-- **记忆系统**（即将推出） — 支持全局记忆与项目级记忆，可手动添加或由 AI 自动提取
+- **本地知识库（RAG）** 支持多知识库，上传文档后自动解析分段并且构建索引，对话时语义检索相关段落
+- **记忆系统** 支持对话多命名空间记忆，可手动添加或由 AI 自动提取（AI自动提取部分即将支持）
 - **上下文管理** — 灵活挂载文件附件、搜索结果、知识库片段、记忆条目、工具输出
 
 ### 工具与扩展

website/docs/features.md

@@ -31,12 +31,12 @@ AQBot goes far beyond plain-text chat with a rich, interactive rendering pipelin
 Augment your conversations with live web data, local documents, and persistent memory.
 
 - **Web Search** — Integrated with Tavily, Zhipu WebSearch, Bocha, and more. Search results include citation source annotations so you can verify claims at a glance.
-- **Local Knowledge Base (RAG)** — Upload documents to build vector indices powered by LanceDB. During conversations, relevant passages are retrieved semantically and injected into context automatically.
-- **Memory System** — Global and project-level memory entries can be added manually or extracted automatically by the AI. Memories persist across conversations to give the model long-term awareness.
+- **Local Knowledge Base (RAG)** — Supports multiple knowledge bases. Upload documents for automatic parsing, chunking, and vector indexing (LanceDB). During conversations, relevant passages are retrieved semantically and injected into context automatically.
+- **Memory System** — Supports multi-namespace conversational memory. Entries can be added manually or extracted automatically by the AI (auto-extraction coming soon). Memories persist across conversations to give the model long-term awareness.
 - **Context Management** — Flexibly attach file attachments, search results, knowledge-base passages, memory entries, and tool outputs to any message for precise context control.
 
 ::: tip Coming Soon
-The Local Knowledge Base and Memory System are under active development and will be available in an upcoming release.
+AI-powered automatic memory extraction is under active development and will be available in an upcoming release.
 :::
 
 ## Tools & Extensions

website/docs/zh/features.md

@@ -35,12 +35,12 @@ AI 回复中的各种格式内容都能得到精准渲染，提供出色的阅
 让 AI 不再局限于训练数据，实现联网搜索与本地知识的无缝融合。
 
 - **联网搜索** — 集成 Tavily、智谱 WebSearch、Bocha 等搜索引擎，搜索结果附带引用来源标注
-- **本地知识库（RAG）** — 上传文档后自动构建向量索引（LanceDB），对话时语义检索相关段落
-- **记忆系统** — 支持全局记忆与项目级记忆，可手动添加或由 AI 自动提取关键信息
+- **本地知识库（RAG）** — 支持多知识库，上传文档后自动解析分段并且构建索引，对话时语义检索相关段落
+- **记忆系统** — 支持对话多命名空间记忆，可手动添加或由 AI 自动提取（AI自动提取部分即将支持）
 - **上下文管理** — 灵活挂载文件附件、搜索结果、知识库片段、记忆条目和工具输出作为对话上下文
 
 ::: warning 即将推出
-本地知识库（RAG）和记忆系统目前正在开发中，将在后续版本中正式发布。
+AI 自动提取记忆功能目前正在开发中，将在后续版本中正式发布。
 :::
 
 ## 工具与扩展