Chat with multiple PDFs, using Ollama and LlamaIndex

Setup

Install Ollama

Linux

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

MacOS

• Download

Clone project

git clone https://github.com/datvodinh/rag-chatbot.git
cd rag-chatbot

Local

• Install

pip install .

• Run

python app.py --host localhost

• Go to: http://0.0.0.0:7860/ after setup completed!

Docker

• Build

docker compose up --build

• Go to: http://0.0.0.0:7860/ after setup completed!

Use OpenAI API

• Create file .env and input:

OPENAI_API_KEY = "[YOUR API KEY]"

Todo List

• Support better Embedding Model for Vietnamese.
• Knowledge Graph (for Structure Data).
• Better Document Processing.

Overview RAG Pipeline (Beta)

• High Level

• Retriever