https://github.com/ziweek/tec-chat
π Chief of Staff of the Republic of Korea Army Award, in 11th Republic of Korea Army Entrepreneurship Competition - π€πͺ Guide Chatbot to Field Training Utilizing Generative AI
https://github.com/ziweek/tec-chat
huggingface langchain langsmith mistral-7b nextjs retrieval-augmented-generation transformers
Last synced: about 1 year ago
JSON representation
π Chief of Staff of the Republic of Korea Army Award, in 11th Republic of Korea Army Entrepreneurship Competition - π€πͺ Guide Chatbot to Field Training Utilizing Generative AI
- Host: GitHub
- URL: https://github.com/ziweek/tec-chat
- Owner: ziweek
- Created: 2024-03-17T06:02:49.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-11-28T15:20:14.000Z (over 1 year ago)
- Last Synced: 2025-02-10T08:48:57.168Z (over 1 year ago)
- Topics: huggingface, langchain, langsmith, mistral-7b, nextjs, retrieval-augmented-generation, transformers
- Language: TypeScript
- Homepage: https://tec-chat.vercel.app
- Size: 73.8 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Hello, Tech_Chat

π Chief of Staff of the Army Award, in 11th ROKA Entrepreneurship Competition π
KOREAN
Β |Β
ENGLISH
Guide Chatbot to Field Training Utilizing Generative AI
Check out prototypes in the badge below
# 1. Introduction
> [!NOTE]
>
> - 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.
> - 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.
https://github.com/ziweek/tec-chat/assets/99459331/1265acf4-f164-467d-b7c6-bc51e887ddad
On-premise LLM ensemble architecture
Realtime 3D rendering of equipments
Project Application
# 2. Implementation
ν΅μ¬κΈ°λ₯
#### 1. On-Premise νκ²½μ LLM μμλΈ κ΅¬μ‘°
μ΄ κΈ°λ₯μ λ‘컬 νκ²½μ μ¬λ¬ μΈμ΄ λͺ¨λΈμ ꡬμΆνκ³ μ°λνμ¬ λ³΄μμ±μ κ°ννλ©°, λκ·λͺ¨ λ°μ΄ν°λ₯Ό μ€μκ°μΌλ‘ μ²λ¦¬νλ λ° νμν μ±λ₯μ μ 곡ν©λλ€. μ΄λ₯Ό ν΅ν΄ μ μν μλ΅ λ° μ νν μ λΉ μ§μμ κ°λ₯μΌ ν©λλ€.
#### 2. μ΄μ©μ₯λΉ κ΅¬μ‘°λμ μ€μκ° 3D λ λλ§
μ΄ κΈ°λ₯μ μ΄μ©λλ μ₯λΉμ ꡬ쑰λλ₯Ό μ€μκ°μΌλ‘ 3D λ λλ§νμ¬ μ¬μ©μμκ² μ 곡ν©λλ€. μ΄λ₯Ό ν΅ν΄ μ¬μ©μλ 볡μ‘ν μ₯λΉ κ΅¬μ‘°λ₯Ό λͺ
ννκ² μ΄ν΄ν μ μμΌλ©°, ν¨μ¨μ μΌλ‘ μ λΉλ₯Ό λ§μΉ μ μμ΅λλ€.
#### 3. λ©ν°λͺ¨λ¬ μ§μμΌλ‘ μ¬μ©μ νΈμμ± κ°μ
ν΄λΉ κΈ°λ₯μ ν
μ€νΈ, μμ±, μ΄λ―Έμ§ λ± λ€μν λ©ν°λͺ¨λ¬ μμμ λμμΌλ‘ μ§μμ΄ μ
λ ₯μ μ§μνμ¬ μ¬μ©μμ νΈμμ±μ λμ
λλ€. μ¬μ©μλ μμ μκ² κ°μ₯ νΈν λ°©μμΌλ‘ μνΈμμ©ν μ μμΌλ©°, μ΄λ₯Ό ν΅ν΄ μ¬μ©μ νΈμμ±μ κ·Ήλνν μ μμ΅λλ€.
μν€ν
μ²
#### νλ‘λνΈ μν€ν
μ²
λ³Έ νλ‘μ νΈμ μν€ν
μ²λ λ°μ΄ν° μ μ²λ¦¬ μν μλ²(μ΄κ³ ν΄μλ μ΄λ―Έμ§ κ°μ λ₯λ¬λ λͺ¨λΈ), ν΅μ¬ κΈ°λ₯ μν μλ²(μν κ°μ²΄ μλ³ λ₯λ¬λ λͺ¨λΈ), κ·Έλ¦¬κ³ μΉ μ΄ν리μΌμ΄μ
(νλ‘ νΈμλμ 벑μλ λ° λ°μ΄ν°λ² μ΄μ€)μΌλ‘ ꡬμ±λμ΄ μμ΅λλ€.
# 3. νμ