QueryNest

An AI-powered enterprise knowledge assistant for grounded document Q&A using FastAPI, ChromaDB, OpenAI embeddings/chat, and a simple Streamlit UI.

What it does

QueryNest lets users:

• upload internal documents
• index them into chunks
• generate embeddings
• store them in a vector store
• ask grounded questions over those documents
• see source snippets used in the answer
• log queries and latency for debugging and monitoring

This project is intentionally small, clean, and easy to explain in interviews.

Tech Stack

• Python
• FastAPI
• ChromaDB
• OpenAI API
• SQLite
• Streamlit
• PyPDF2
• PyTest

Setup

1. Clone the repo

git clone https://github.com/<your-username>/QueryNest.git
cd QueryNest

2. Create a virtual environment

python -m venv .venv
source .venv/bin/activate

On Windows:

python -m venv .venv
.venv\Scripts\activate

3. Install dependencies

pip install -r requirements.txt

4. Configure environment variables

cp .env.example .env

Update .env with your OpenAI API key.

5. Run the backend

uvicorn app.main:app --reload

6. Run the frontend

streamlit run frontend/streamlit_app.py

API Endpoints

• POST /upload-doc
• POST /ask
• GET /documents
• GET /logs
• GET /health

GitHub Description

QueryNest - Enterprise AI knowledge assistant using FastAPI, embeddings, vector search, and RAG for grounded Q&A over uploaded documents.