mini-rag

This is minimal implementation of the RAG model for question answering.

Requirements

• Python 3.8 or later

Install Dependencies

sudo apt update
sudo apt install libpq-dev gcc python3-dev

Install python using MiniConda

1. Download and install MiniConda From [here] (https://www.anaconda.com/docs/getting-started/miniconda/install)

2. Create a new environnement using the following command:

$ conda create -n mini-rag python=3.8

3. Activate the environment:

$ conda activate  mini-rag-app

(Optional) Setup you command line interface for better readability

export PS1="\[\033[01;32m\]\u@\h:\w\n\[\033[00m\]\$ "

Installation

Install the required packages

$ pip install -r requirements.txt

Setup the environment variables

$ cp .env.example .env

Set your environment variables in the .env file. Like OPENAI_API_KEY value.

Run Docker Compose Services

$ cd docker
$ cp .env.example .env
$ docker-compose up 

Run the FastAPI server

$ uvicorn main:app --reload --host 0.0.0.0 --port 5000

POSTMAN collection

download the POSTMAN collection from /assets/mini-rag-app.postman_collection.json