gemini-rag

A Retrieval-Augmented Generation (RAG) system built with TypeScript. This project allows you to load a PDF, split it into chunks, and interactively ask questions to an AI assistant that references the PDF content.

---

🧱 Features

• Load and process PDF content into text.
• Split text into chunks for efficient retrieval.
• Interactive Q&A loop with context-aware responses.
• Maintains a conversation history to provide continuity.
• Type-safe implementation using TypeScript.

---

⚙️ Setup

1. Clone the repository:

   git clone https://github.com/jmrl23/gemini-rag.git
   cd gemini-rag

2. Provide necessary environment variables (create a .env file)

   check .env.example for reference

3. Install dependencies:

   yarn install

4. Build application

   yarn run build

5. RUN

   yarn run start
   

---

⚙️ Setup (Docker)

1. Clone the repository:

   git clone https://github.com/jmrl23/gemini-rag.git
   cd gemini-rag

2. Provide necessary environment variables (create a .env file or put them directly inside docker-compose.yaml)

   check .env.example for reference

3. RUN

   docker compose run -it rag /bin/bash