metadata

title: Test
emoji: 🏢
colorFrom: gray
colorTo: yellow
sdk: docker
pinned: false
license: mit
short_description: test

The-Ultimate-RAG

Overview

[S25] The Ultimate RAG is an Innopolis University software project that generates cited responses from a local database.

Prerequisites

Before you begin, ensure the following is installed on your machine:

Installation

Clone the repository

git clone https://github.com/PopovDanil/The-Ultimate-RAG
cd The-Ultimate-RAG

Set up a virtual environment (recommended)

To isolate project dependencies and avoid conflicts, create a virtual environment:
- On Unix/Linux/macOS:
```
python3 -m venv env
source env/bin/activate
```
- On Windows:
```
python -m venv env
env\Scripts\activate
```
Install required libraries

Within the activated virtual environment, install the dependencies:
```
pip install -r ./app/requirements.txt
```
Note: ensure you are in the virtual environment before running the command
Set up Docker
- Ensure Docker is running on your machine
- Open a terminal, navigate to project directory, and run:
```
docker-compose up --build
```
Note: The initial build may take 10–20 minutes, as it needs to download large language models and other dependencies. Later launches will be much faster.
Server access

Once the containers are running, visit http://localhost:5050. You should see the application’s welcome page

To stop the application and shut down all containers, press Ctrl+C in the terminal where docker-compose is running, and then run:

   docker-compose down

Usage

Upload your file: click the upload button and select a supported file (.txt, .doc, .docx, or .pdf)
Ask a question: Once the file is processed, type your question into the prompt box and submit.
Receive your answer

A note on performance

Response generation is a computationally intensive task. The time to receive an answer may vary depending on your machine's hardware and the complexity of the query.

License

This project is licensed under the MIT License.