{"id":23173405,"url":"https://github.com/ziweek/tec-chat","last_synced_at":"2025-04-05T00:24:48.443Z","repository":{"id":237518144,"uuid":"773244848","full_name":"ziweek/tec-chat","owner":"ziweek","description":"🏆 Chief of Staff of the Republic of Korea Army Award, in 11th Republic of Korea Army Entrepreneurship Competition - 🤖🪖 Guide Chatbot to Field Training Utilizing Generative AI","archived":false,"fork":false,"pushed_at":"2024-11-28T15:20:14.000Z","size":77384,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-10T08:48:57.168Z","etag":null,"topics":["huggingface","langchain","langsmith","mistral-7b","nextjs","retrieval-augmented-generation","transformers"],"latest_commit_sha":null,"homepage":"https://tec-chat.vercel.app","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ziweek.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2024-03-17T06:02:49.000Z","updated_at":"2025-01-11T02:47:09.000Z","dependencies_parsed_at":"2024-11-28T16:33:56.616Z","dependency_job_id":null,"html_url":"https://github.com/ziweek/tec-chat","commit_stats":null,"previous_names":["ziweek/tec-chat"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Ftec-chat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Ftec-chat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Ftec-chat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Ftec-chat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ziweek","download_url":"https://codeload.github.com/ziweek/tec-chat/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247268083,"owners_count":20911074,"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","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":["huggingface","langchain","langsmith","mistral-7b","nextjs","retrieval-augmented-generation","transformers"],"created_at":"2024-12-18T05:15:35.976Z","updated_at":"2025-04-05T00:24:48.421Z","avatar_url":"https://github.com/ziweek.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Hello, Tech_Chat\n\n\u003cimg src=\"./src/banner_en.png\"/\u003e\n\n\u003cp align=\"center\"\u003e\n \u003cstrong\u003e🏆 Chief of Staff of the Army Award, in 11th ROKA Entrepreneurship Competition 🏆\u003c/strong\u003e\n \u003cbr/\u003e\n \u003cbr/\u003e\n \u003ca href='https://github.com/ziweek/desirable-sea/blob/main/README.md'\u003eKOREAN\u003c/a\u003e\n \u0026nbsp;|\u0026nbsp;\n \u003ca href='https://github.com/ziweek/desirable-sea/blob/main/README_EN.md'\u003eENGLISH\u003c/a\u003e\n \u003cbr/\u003e\n \u003cbr/\u003e\n \u003cstrong\u003eGuide Chatbot to Field Training Utilizing Generative AI\u003c/strong\u003e\n \u003cbr/\u003e\n \u003cbr/\u003e\n \n \u003ca href='https://paperswithcode.com/paper/mistral-7b'\u003e\n \u003cimg src=\"https://img.shields.io/badge/Paperswithcode-Mistral%207B-25c2a0?style=flat-square\"/\u003e\n \u003c/a\u003e\n  \u003ca href='https://paperswithcode.com/paper/gemma-open-models-based-on-gemini-research'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Paperswithcode-Gemma-25c2a0?style=flat-square\"/\u003e\n  \u003c/a\u003e\n  \u003ca href='https://ollama.com/'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/LLM%20Env-Ollama-faf9f6?style=flat-square\"/\u003e\n  \u003c/a\u003e\n  \u003ca href='https://github.com/Chainlit/chainlit'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/LangChain-Chainlit-FF0A6B?style=flat-square\"/\u003e\n  \u003c/a\u003e\n  \u003cbr/\u003e\n \n  \u003cimg src=\"https://img.shields.io/badge/Next.js-000000?style=flat-square\u0026logo=nextdotjs\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/PWA-5A0FC8?style=flat-square\u0026logo=pwa\u0026logoColor=white\"/\u003e \n  \u003cimg src=\"https://img.shields.io/badge/NestJS-E0234E?style=flat-square\u0026logo=nestjs\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/MySQL-4479A1?style=flat-square\u0026logo=mysql\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/MongoDB-47A248?style=flat-square\u0026logo=mongodb\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Jenkins-D24939?style=flat-square\u0026logo=jenkins\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Docker-2496ED?style=flat-square\u0026logo=docker\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/AWS-232F3E?style=flat-square\u0026logo=amazonaws\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Redis-DC382D?style=flat-square\u0026logo=redis\u0026logoColor=white\"/\u003e\n\u003c/p\u003e\n\u003cbr/\u003e\n\u003cbr/\u003e\n  \n\u003cp align=\"center\"\u003e  \n  \u003cstrong\u003eCheck out prototypes in the badge below\u003cstrong\u003e\n  \u003cbr/\u003e\n  \u003cbr/\u003e\n  \u003ca href='https://tec-chat.vercel.app/'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Product-Vercel-000000?style=flat-square\"/\u003e\n  \u003c/a\u003e\n  \u003ca href='https://goor.me/edkv2g6bKZt7nopy6'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Model-goorm-ffffff?style=flat-square\"/\u003e\n  \u003c/a\u003e\n  \u003ca href='https://colab.research.google.com/drive/13-VZyx3LiYPRS8aw-AcMSBK0Z4--TF2j?usp=sharing'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Tutorial-Google%20Colab-F9AB00?style=flat-square\"/\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cbr/\u003e\n\u003cbr/\u003e\n\n# 1. Introduction\n\n\u003e [!NOTE]\n\u003e\n\u003e - This idea is a project that won the Chief of Staff of the Army Award (Excellence Award) at the [2024 11th Korea Army Startup Competition](https://www.army-startup.co.kr/) hosted by the Republic of Korea Army Headquarters.\n\u003e - This idea involves developing an intelligent chatbot service powered by Large Language Models (LLMs) to overcome the limitations of traditional booklet-style field manuals. The project aims to research and develop an intelligent electronic manual platform that enables quick and accurate access to essential information for operating military equipment.\n\nhttps://github.com/ziweek/tec-chat/assets/99459331/1265acf4-f164-467d-b7c6-bc51e887ddad\n\n\u003ctable\u003e\n  \u003ctr\u003e\n     \u003ctd\u003e\n      \u003cp align='center'\u003e\n        On-premise LLM ensemble architecture\n      \u003c/p\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003cp align='center'\u003e\n       Realtime 3D rendering of equipments\n      \u003c/p\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003cp align='center'\u003e\n        Project Application\n      \u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n   \u003ctr\u003e\n    \u003ctd\u003e\n      \u003cimg src=\"./src/intro1.png\" width=\"100%\"/\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003cimg src=\"./src/intro2.png\" width=\"100%\"/\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003cimg src=\"./src/intro3.png\" width=\"100%\"/\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\u003cbr/\u003e\n\n\u003cbr/\u003e\n\u003cbr/\u003e\n\n# 2. Implementation\n\n\u003cdetails \u003e\n \u003csummary\u003e\u003cb\u003e핵심기능\u003c/b\u003e\u003c/summary\u003e\u003cbr/\u003e\n\n#### 1. On-Premise 환경의 LLM 앙상블 구조\n\n \u003ctable\u003e\n   \u003ctr\u003e\n     \u003ctd width=\"50%\"\u003e\n      \u003cimg src=\"./src/func1.png\" width=\"100%\"\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n     \u003cp align=\"left\"\u003e이 기능은 로컬 환경에 여러 언어 모델을 구축하고 연동하여 보안성을 강화하며, 대규모 데이터를 실시간으로 처리하는 데 필요한 성능을 제공합니다. 이를 통해 신속한 응답 및 정확한 정비 지원을 가능케 합니다.\u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cbr/\u003e\n\n#### 2. 운용장비 구조도의 실시간 3D 렌더링\n\n \u003ctable\u003e\n   \u003ctr\u003e\n     \u003ctd width=\"50%\"\u003e\n      \u003cimg src=\"./src/func2.png\" width=\"100%\"\u003e\n    \u003c/td\u003e\n    \u003ctd width=\"50%\"\u003e\n      \u003cp align=\"left\"\u003e이 기능은 운용되는 장비의 구조도를 실시간으로 3D 렌더링하여 사용자에게 제공합니다. 이를 통해 사용자는 복잡한 장비 구조를 명확하게 이해할 수 있으며, 효율적으로 정비를 마칠 수 있습니다.\u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cbr/\u003e\n\n#### 3. 멀티모달 지원으로 사용자 편의성 개선\n\n \u003ctable\u003e\n   \u003ctr\u003e\n     \u003ctd width=\"50%\"\u003e\n      \u003cimg src=\"./src/func3.png\" width=\"100%\"\u003e\n    \u003c/td\u003e\n    \u003ctd width=\"50%\"\u003e\n     \u003cp align=\"left\"\u003e해당 기능은 텍스트, 음성, 이미지 등 다양한 멀티모달 자원을 대상으로 질의어 입력을 지원하여 사용자의 편의성을 높입니다. 사용자는 자신에게 가장 편한 방식으로 상호작용할 수 있으며, 이를 통해 사용자 편의성을 극대화할 수 있습니다.\u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cbr/\u003e\n\u003cbr/\u003e\n\n\u003c/details\u003e\n\n\u003cdetails \u003e\n  \u003csummary\u003e\u003cb\u003e아키텍처\u003c/b\u003e\u003c/summary\u003e\u003cbr/\u003e\n\n#### 프로덕트 아키텍처\n\n \u003ctable\u003e\n  \u003ctr\u003e\n     \u003ctd\u003e\n      \u003cimg width=\"100%\" src=\"./src/ux-flow-chart.png\"\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n   \u003ctr\u003e\n    \u003ctd width=\"50%\"\u003e\n           \u003cp align=\"left\"\u003e본 프로젝트의 아키텍처는 데이터 전처리 수행 서버(초고해생도 이미지 개선 딥러닝 모델), 핵심 기능 수행 서버(소형 객체 식별 딥러닝 모델), 그리고 웹 어플리케이션(프론트엔드와 벡엔드 및 데이터베이스)으로 구성되어 있습니다.\u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\u003c/details\u003e\n\n\u003cbr/\u003e\n\u003cbr/\u003e\n\n# 3. 팀원\n\n \u003ctable\u003e\n  \u003ctr\u003e\n     \u003ctd\u003e\n      \u003cimg width=\"100%\" src=\"./src/team.png\"\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fziweek%2Ftec-chat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fziweek%2Ftec-chat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fziweek%2Ftec-chat/lists"}