🤖 TRAIL AI

📦 Requirements

• ⚙️ Ollama - For running LLMs
• 📊 ChromaDB - For data ingestion
• 🔮 gemma2:2b-instruct-q5_1 - For generation
• 🧠 all-mpnet-base-v2 - For embeddings
• 🔰 mxbai-rerank-base-v1 - For reranking
• 💬 nli-deberta-v3-base - For coherence
• 🐍 Python 3.12 - For ml apis
• 🦕 Node.js 23.10.0 - For JS runtime
• 🌐 Next.js - For web application

---

🛠️ Setup

1️⃣ Install Node JS v23.10.0

🖥️ Windows

📦 Install PNPM

Run:

npm install -g pnpm

---

▶️ Run the App

Start the application with:

pnpm run dev
pnpm run vectordb

---

🤝 Contributing

1. Fork the repository 🍴
2. Create a new branch 🌱
3. Commit your changes 📌
4. Submit a pull request 🔄

---

📄 Draft Paper

This project involves the development of Trail AI, focusing on Natural Language Processing (NLP) models and student handbook embedding.

---

📅 Extension Project (Deadline: September 30)

• 🔧 Task for DEDS (Deadline: September 30)

🎓 Research Congress Butuan (Deadline: September 30)

• 📢 Contribution to the Research Congress event in Butuan.

🔗 RAG

• 🤝 Involvement with RAG.

📘 Student Handbook Embedding

• 🔍 Embedding of the student handbook into the project.

---

✅ TO-DO List

1. 🚀 Benchmark NLP Models

   • Evaluate various NLP models to determine the best fit for the project.

2. 💻 Make Front END & Back END of PangutanAI

   • Develop both the front-end and back-end components of the PangutanAI system.

3. 📝 Note

   • Make sure to keep track of any other important notes.

---

🔗 Useful Links

• 🎥 YouTube Video