DocQuery

January 30, 2025 · View on GitHub

Overview

DocQuery is a comprehensive project consisting of both frontend and backend components. The frontend is built with Next.js and Tailwind CSS, providing a user-friendly interface to create powerful knowledge bases for LLMs using markdown documentation. The backend leverages FastAPI to provide endpoints for different agents built using the langgraph library and integrated into the FastAPI application using CopilotKitSDK.

Video: Click to view

Setup

Frontend

Clone the repository:

git clone https://github.com/md-abid-hussain/docquery.git
cd docquery-frontend

Install dependencies:
```
npm install
```
Copy the example environment file and fill in the required values:
```
cp .env.example .env
```
Start the development server:
```
npm run dev
```
The application will be available at http://localhost:3000.

Backend

Clone the repository:

git clone <repository-url>
cd docquery-backend

Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

Install dependencies:
```
pip install -r requirements.txt
```
Copy the example environment file and fill in the required values:
```
cp .env.example .env
```
Start the FastAPI server:
```
uvicorn app.main:app --reload
```
The application will be available at http://127.0.0.1:8000.

Features

Frontend

GitHub Integration: Easily fetch repository details and select markdown files for ingestion.
Markdown Processing: Ingest and process markdown files used for documentation or detailed explanations.
Knowledge Base Creation: Build comprehensive knowledge bases for LLMs from your documentation.
AI-Powered Insights: Leverage advanced LLMs to generate insights and answer queries based on your knowledge base.