From 89ae61bfc115db0a54af2dccfd933ee7fe6232cd Mon Sep 17 00:00:00 2001 From: lanceyq <1982376970@qq.com> Date: Wed, 29 Apr 2026 14:13:46 +0800 Subject: [PATCH] docs(readme): update image paths from docs/ to assets/ Migrate all image src references in README.md and README_CN.md from ./docs/generated/ and ./docs/screenshots/ to ./assets/generated/ and ./assets/screenshots/ to match the actual directory structure. Also replace an external GitHub user-attachments URL with a local ./assets/screenshots/frontend-ui.png path in README.md. --- README.md | 36 ++++++++++++++++++------------------ README_CN.md | 34 +++++++++++++++++----------------- 2 files changed, 35 insertions(+), 35 deletions(-) diff --git a/README.md b/README.md index 97806114..873b2390 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -MemoryBear Hero Banner +MemoryBear Hero Banner
@@ -53,13 +53,13 @@ Unlike traditional memory tools that treat knowledge as static data to be retrie - Domain jargon, colloquial expressions, and context-dependent references are not accurately encoded, leading to semantic drift in memory interpretation - Cross-language memory associations fail in multilingual or dialect-rich scenarios -Why MemoryBear +Why MemoryBear --- ## Core Features -MemoryBear Core Features +MemoryBear Core Features ### Memory Extraction Engine @@ -121,7 +121,7 @@ Unified service architecture exposing two API surfaces: ## Architecture -MemoryBear System Architecture +MemoryBear System Architecture **Celery Three-Queue Async Architecture:** @@ -139,15 +139,15 @@ Evaluation metrics include F1 score (F1), BLEU-1 (B1), and LLM-as-a-Judge score MemoryBear consistently outperforms competing systems including Mem0, Zep, and LangMem across all four task categories: -Benchmark Results +Benchmark Results **Vector version (non-graph)**: Achieves substantially improved retrieval efficiency while maintaining high accuracy. Overall accuracy surpasses the best existing full-text retrieval methods (72.90 ± 0.19%), while maintaining low latency at both p50 and p95 for Search Latency and Total Latency. -Vector Version Metrics +Vector Version Metrics **Graph version**: Integrating the knowledge graph architecture pushes overall accuracy to a new benchmark (**75.00 ± 0.20%**), delivering performance metrics that significantly surpass all other methods. -Graph Version Metrics +Graph Version Metrics --- @@ -229,7 +229,7 @@ npm install && npm run dev git clone https://github.com/SuanmoSuanyangTechnology/MemoryBear.git ``` -Directory Structure +Directory Structure ### 3. Backend API Service @@ -260,19 +260,19 @@ Download [Docker Desktop](https://www.docker.com/products/docker-desktop/) and p **PostgreSQL** — search → select → pull -PostgreSQL Pull +PostgreSQL Pull -PostgreSQL Container +PostgreSQL Container -PostgreSQL Running +PostgreSQL Running **Neo4j** — pull the same way. When creating the container, map two required ports and set an initial password: - `7474`: Neo4j Browser - `7687`: Bolt protocol -Neo4j Container +Neo4j Container -Neo4j Running +Neo4j Running **Redis** — same steps as above. @@ -343,9 +343,9 @@ Apply all migrations to create the full schema: alembic upgrade head ``` -Alembic Migration +Alembic Migration -Database Tables +Database Tables #### 3.5 Start the API Service @@ -355,7 +355,7 @@ uv run -m app.main Access API documentation at http://localhost:8000/docs -API Docs +API Docs #### 3.6 Start Celery Workers (Optional, for async tasks) @@ -401,9 +401,9 @@ proxy: { npm run dev ``` -Frontend Start +Frontend Start -Frontend UI +Frontend UI ### 5. Initialize the System diff --git a/README_CN.md b/README_CN.md index f69dbc8e..4fbe88a7 100644 --- a/README_CN.md +++ b/README_CN.md @@ -1,4 +1,4 @@ -MemoryBear Hero Banner +MemoryBear Hero Banner
@@ -53,13 +53,13 @@ MemoryBear 是红熊 AI 自主研发的新一代 AI 记忆系统，核心突破 - 行业术语、口语化表达、上下文指代未被准确编码，导致模型对记忆内容的语义解析失真 - 多语言混用场景中，跨语种记忆关联失效 -Why MemoryBear +Why MemoryBear --- ## 核心特性 -MemoryBear Core Features +MemoryBear Core Features ### 记忆萃取引擎 @@ -120,7 +120,7 @@ MemoryBear 是红熊 AI 自主研发的新一代 AI 记忆系统，核心突破 ## 架构总览 -MemoryBear System Architecture +MemoryBear System Architecture **Celery 三队列异步架构：** @@ -138,15 +138,15 @@ MemoryBear 是红熊 AI 自主研发的新一代 AI 记忆系统，核心突破 MemoryBear 在四大任务类型的核心指标中，均优于行业内竞争对手 Mem0、Zep、LangMem 等现有方法： -Benchmark Results +Benchmark Results **向量版本（非图谱）**：在保持高准确性的同时极大优化了检索效率，总体准确性明显高于现有最高全文检索方法（72.90 ± 0.19%），且在 Search Latency 和 Total Latency 的 p50/p95 上保持较低水平。 -Vector Version Metrics +Vector Version Metrics **图谱版本**：通过集成知识图谱架构，将总体准确性推至新高度（**75.00 ± 0.20%**），在保持准确性的同时整体指标显著优于所有其他方法。 -Graph Version Metrics +Graph Version Metrics --- @@ -228,7 +228,7 @@ npm install && npm run dev git clone https://github.com/SuanmoSuanyangTechnology/MemoryBear.git ``` -Directory Structure +Directory Structure ### 三、后端 API 服务启动 @@ -261,13 +261,13 @@ source .venv/bin/activate 拉取镜像：search → select → pull -PostgreSQL Pull +PostgreSQL Pull 创建容器： -PostgreSQL Container +PostgreSQL Container -PostgreSQL Running +PostgreSQL Running **Neo4j** @@ -275,9 +275,9 @@ source .venv/bin/activate - `7474`：Neo4j Browser - `7687`：Bolt 协议 -Neo4j Container +Neo4j Container -Neo4j Running +Neo4j Running **Redis**：同上步骤拉取并创建容器。 @@ -348,9 +348,9 @@ sqlalchemy.url = postgresql://用户名:密码@数据库地址:端口/数据库 alembic upgrade head ``` -Alembic Migration +Alembic Migration -Database Tables +Database Tables #### 3.5 启动 API 服务 @@ -360,7 +360,7 @@ uv run -m app.main 访问 API 文档：http://localhost:8000/docs -API Docs +API Docs #### 3.6 启动 Celery Worker（可选，用于异步任务） @@ -406,7 +406,7 @@ proxy: { npm run dev ``` -Frontend Start +Frontend Start Frontend UI