Industry-Ready RAG Chatbot (FREE APIs + MLOps) (Still Not Completed)

This is a production-style Retrieval-Augmented Generation (RAG) chatbot using 100% free & open-source tools.

Tech Stack

• LLM: Ollama (LLaMA3 / Mistral) – FREE, local
• Embeddings: SentenceTransformers
• Vector DB: FAISS
• Backend: FastAPI
• Frontend: Streamlit
• MLOps: MLflow
• Orchestration: LangChain
• Containerization: Docker (optional)

---

1. Setup (Local)

Install system dependency

curl -fsSL https://ollama.com/install.sh | sh
ollama pull llama3

Create virtual environment

python -m venv venv
source venv/bin/activate   # Linux/Mac
venv\Scripts\activate    # Windows

Install requirements

pip install -r requirements.txt

---

2. Index Documents (RAG)

Put your PDFs or TXTs inside data/ and run:

python ingest.py

---

3. Run Backend (API)

uvicorn app.main:app --reload

API available at:

http://127.0.0.1:8000/docs

---

4. Run Chat UI

streamlit run ui/chat_ui.py

---

5. MLflow Tracking

mlflow ui

Open:

http://127.0.0.1:5000

---

Folder Structure

rag_chatbot_project/
│── app/
│   ├── main.py
│   ├── rag.py
│── data/
│── vectorstore/
│── ui/
│   ├── chat_ui.py
│── ingest.py
│── requirements.txt
│── Dockerfile

---

Ready For

• Internship / Job Portfolio
• Startup MVP
• Research demo
• Production extension (Auth, Redis, CI/CD)