{"id":21803020,"url":"https://github.com/litongjava/java-maxkb","last_synced_at":"2025-10-07T23:30:54.473Z","repository":{"id":263099377,"uuid":"889335009","full_name":"litongjava/java-maxkb","owner":"litongjava","description":"java-maxkb","archived":false,"fork":false,"pushed_at":"2025-06-14T01:20:29.000Z","size":460,"stargazers_count":49,"open_issues_count":4,"forks_count":12,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-23T13:54:04.184Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/litongjava.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-11-16T05:20:59.000Z","updated_at":"2025-07-23T02:18:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"138e91a0-b872-4553-aac9-a4147f8095d3","html_url":"https://github.com/litongjava/java-maxkb","commit_stats":null,"previous_names":["litongjava/java-maxkb"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/litongjava/java-maxkb","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/litongjava%2Fjava-maxkb","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/litongjava%2Fjava-maxkb/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/litongjava%2Fjava-maxkb/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/litongjava%2Fjava-maxkb/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/litongjava","download_url":"https://codeload.github.com/litongjava/java-maxkb/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/litongjava%2Fjava-maxkb/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278862794,"owners_count":26059016,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-07T02:00:06.786Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-27T11:37:16.394Z","updated_at":"2025-10-07T23:30:54.467Z","avatar_url":"https://github.com/litongjava.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 智能知识库系统（java-maxkb）\n\n## 功能演示\n\n[!演示视频](https://www.bilibili.com/video/BV1yJU8YHEgg/?vd_source=69e3cff470444b21e8c322dddec00def)\n\n## 前端和后端代码\n\n[前端代码github](https://github.com/litongjava/MaxKB/tree/main/ui)\n[后端代码gitee](https://github.com/litongjava/java-maxkb)\n\n## 开发文档\n\n[!开发文档](https://www.tio-boot.com/zh/63_knowlege_base/01.html)\n\n## 项目简介\n\n**java-maxkb** 是一个基于 Java 开发的智能知识库系统，利用先进的自然语言处理和向量检索技术，为用户提供高效、准确的问答服务。通过集成文档管理、片段向量化、语义搜索和大语言模型（如 GPT-4）等功能，系统能够理解用户的问题，并从知识库中检索最相关的内容生成回答。\n\n## 功能特性\n\n1. **数据库设计** [查看 01.html](https://www.tio-boot.com/zh/63_knowlege_base/01.html)  \n   设计并实现项目所需的数据表结构与数据库方案，为后续的数据操作打下坚实基础。\n\n2. **用户登录** [查看 02.html](https://www.tio-boot.com/zh/63_knowlege_base/02.html)  \n   实现了安全可靠的用户认证系统，保护用户数据并限制未经授权的访问。\n\n3. **模型管理** [查看 03.html](https://www.tio-boot.com/zh/63_knowlege_base/03.html)  \n   支持针对不同平台的模型（如 OpenAI、Google Gemini、Claude）进行管理与配置。\n\n4. **知识库管理** [查看 04.html](https://www.tio-boot.com/zh/63_knowlege_base/04.html)  \n   提供创建、更新及删除知识库的功能，方便用户维护与管理文档内容。\n\n5. **文档拆分** [查看 05.html](https://www.tio-boot.com/zh/63_knowlege_base/05.html)  \n   可将文档拆分为多个片段，便于后续向量化和检索操作。\n\n6. **片段向量** [查看 06.html](https://www.tio-boot.com/zh/63_knowlege_base/06.html)  \n   将文本片段进行向量化处理，以便进行语义相似度计算及高效检索。\n\n7. **命中率测试** [查看 07.html](https://www.tio-boot.com/zh/63_knowlege_base/07.html)  \n   通过语义相似度和 Top-N 算法，检索并返回与用户问题最相关的文档片段，用于评估检索的准确性。\n\n8. **文档管理** [查看 08.html](https://www.tio-boot.com/zh/63_knowlege_base/08.html)  \n   提供上传和管理文档的功能，上传后可自动拆分为片段便于进一步处理。\n\n9. **片段管理** [查看 09.html](https://www.tio-boot.com/zh/63_knowlege_base/09.html)  \n   允许对已拆分的片段进行增、删、改、查等操作，确保内容更新灵活可控。\n\n10. **问题管理** [查看 10.html](https://www.tio-boot.com/zh/63_knowlege_base/10.html)  \n    为片段指定相关问题，以提升检索时的准确性与关联度。\n\n11. **应用管理** [查看 11.html](https://www.tio-boot.com/zh/63_knowlege_base/11.html)  \n    提供创建和配置应用（智能体）的功能，并可关联指定模型和知识库。\n\n12. **向量检索** [查看 12.html](https://www.tio-boot.com/zh/63_knowlege_base/12.html)  \n    基于语义相似度，在知识库中高效检索与用户问题最匹配的片段。\n\n13. **推理问答调试** [查看 13.html](https://www.tio-boot.com/zh/63_knowlege_base/13.html)  \n    提供检索与问答性能的评估工具，帮助开发者进行系统优化与调试。\n\n14. **对话问答** [查看 14.html](https://www.tio-boot.com/zh/63_knowlege_base/14.html)  \n    为用户提供友好的人机交互界面，结合检索到的片段与用户问题实时生成回答。\n\n15. **统计分析** [查看 15.html](https://www.tio-boot.com/zh/63_knowlege_base/15.html)  \n    对用户的提问与系统回答进行数据化分析，并以可视化图表的形式呈现系统使用情况。\n\n16. **用户管理** [查看 16.html](https://www.tio-boot.com/zh/63_knowlege_base/16.html)  \n    提供多用户管理功能，包括用户的增删改查及权限控制。\n\n17. **API 管理** [查看 17.html](https://www.tio-boot.com/zh/63_knowlege_base/17.html)  \n    对外提供标准化 API，便于外部系统集成和调用本系统的功能。\n\n18. **存储文件到 S3** [查看 18.html](https://www.tio-boot.com/zh/63_knowlege_base/18.html)  \n    将用户上传的文件存储至 S3 等对象存储平台，提升文件管理的灵活性与可扩展性。\n\n19. **文档解析优化** [查看 19.html](https://www.tio-boot.com/zh/63_knowlege_base/19.html)  \n    介绍与对比常见的文档解析方案，并提供提升文档解析速度和准确性的优化建议。\n\n20. **片段汇总** [查看 20.html](https://www.tio-boot.com/zh/63_knowlege_base/20.html)  \n    对片段内容进行汇总，以提升总结类问题的查询与回答效率。\n\n21. **文档多分块与检索** [查看 21.html](https://www.tio-boot.com/zh/63_knowlege_base/21.html)  \n    将片段进一步拆分为句子并进行向量检索，提升检索的准确度与灵活度。\n\n22. **多文档支持** [查看 22.html](https://www.tio-boot.com/zh/63_knowlege_base/22.html)  \n    兼容多种文档格式，包括 `.doc`, `.docx`, `.xls`, `.xlsx`, `.ppt`, `.pptx` 等。\n\n23. **对话日志** [查看 23.html](https://www.tio-boot.com/zh/63_knowlege_base/23.html)  \n    记录并展示对话日志，用于后续分析和问题回溯。\n\n24. **检索性能优化** [查看 24.html](https://www.tio-boot.com/zh/63_knowlege_base/24.html)  \n    提供整库扫描和分区检索等多种方式，进一步提高检索速度和效率。\n\n25. **Milvus** [查看 25.html](https://www.tio-boot.com/zh/63_knowlege_base/25.html)  \n    将向量数据库切换至 Milvus，以在大规模向量检索场景中获得更佳的性能与可扩展性。\n\n26. **文档解析方案和费用对比** [查看 26.html](https://www.tio-boot.com/zh/63_knowlege_base/26.html)  \n    对比不同文档解析方案在成本、速度、稳定性等方面的差异，为用户提供更加经济高效的选择。\n\n27. **爬取网页数据** [查看 27.html](https://www.tio-boot.com/zh/63_knowlege_base/27.html)  \n    支持从网页中抓取所需内容，后续处理流程与本地文档一致：分段、向量化、存储与检索。\n\n## 项目地址\n\n后端\n- GitHub：[https://github.com/litongjava/java-maxkb](https://github.com/litongjava/java-maxkb)\n- Gitee：[https://gitee.com/ppnt/java-maxkb](https://gitee.com/ppnt/java-maxkb)\n\n前端\n- GitHub：[https://github.com/litongjava/MaxKB/tree/main/ui](https://github.com/litongjava/MaxKB/tree/main/ui)\n\n\n## 安装与使用指南\n\n### 环境要求\n\n- **操作系统**：Windows、Linux 或 macOS\n- **Java 开发工具包（JDK）**：版本 8 或更高\n- **Maven**：用于项目构建和依赖管理\n- **PostgreSQL**：用于数据库存储\n\n### 安装步骤\n\n1. **克隆项目代码**\n\n   ```bash\n   # 从 GitHub 克隆\n   git clone https://github.com/litongjava/java-maxkb.git\n   cd java-maxkb\n\n   # 或从 Gitee 克隆\n   git clone https://gitee.com/ppnt/java-maxkb.git\n   cd java-maxkb\n   ```\n\n2. **配置数据库**\n\n   - 安装并启动 PostgreSQL 数据库。\n   - 创建项目所需的数据库和用户。\n   - 在 `src/main/resources/application.properties` 中配置数据库连接信息。\n\n3. **构建项目**\n\n   ```bash\n   mvn clean install -DskipTests -Dgpg.skip=true\n   ```\n\n4. **运行项目**\n\n   ```bash\n   java -jar target/java-maxkb-web.jar\n   ```\n\n5. **访问系统**\n\n   启动前端,打开浏览器，访问 `http://localhost:3000`，即可进入系统登录界面。\n\n## 贡献指南\n\n我们欢迎所有对本项目感兴趣的开发者贡献代码和建议。请按照以下步骤参与贡献：\n\n1. **Fork 仓库**\n\n   点击页面右上角的 “Fork” 按钮，将项目仓库复制到您的账户下。\n\n2. **克隆仓库到本地**\n\n   ```bash\n   # 从 GitHub 克隆\n   git clone https://github.com/yourusername/java-maxkb.git\n   ```\n\n3. **创建新分支**\n\n   ```bash\n   git checkout -b feature/your-feature-name\n   ```\n\n4. **提交更改**\n\n   ```bash\n   git commit -am '添加新功能: your-feature-name'\n   ```\n\n5. **推送到远程仓库**\n\n   ```bash\n   git push origin feature/your-feature-name\n   ```\n\n6. **创建 Pull Request**\n\n   在 GitHub 上提交 Pull Request，描述您的更改内容和目的。\n\n## 许可证信息\n\n本项目采用 MIT 许可证，详细信息请参阅 [LICENSE](LICENSE) 文件。","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flitongjava%2Fjava-maxkb","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flitongjava%2Fjava-maxkb","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flitongjava%2Fjava-maxkb/lists"}