Skip to content

LinkLens is a modular, GenAI-Powered Interest Discovery Framework that captures, analyzes, and leverages user behavior using a graph-based approach. Designed for scalability and deep personalization, LinkLens turns raw user interactions into meaningful, real-time recommendations by modeling behavior as relationships and patterns.

Notifications You must be signed in to change notification settings

GoodGuyAdy/LinkLens

Repository files navigation

🔗 LinkLens

Graph-Augmented GenAI for Personalized Suggestions and Smart QA

LinkLens is a GenAI system that models user-entity interactions as a graph, enabling intelligent suggestions and natural language question answering using LLMs.
Built with Django, Neo4j, and LangChain, it turns raw interaction events (like, dislike, follow, etc.) into meaningful knowledge and context-aware recommendations.


Postman Collection For an easier experience with the API, you can explore my Postman collection.


📌 Key Features

  • 🧠 Graph-Powered AI Reasoning — Every user interaction is stored as a relationship in Neo4j.
  • 💬 Smart Chat API — Ask natural language questions like "What courses are popular among users who liked The Great Gatsby?" or "What are some common interests among users who viewed Tesla Model 3?"
  • 🎯 Suggestion Engine — Recommend relevant entities for a user using real-time graph traversal + LLMs.
  • 👤 Full CRUD APIs — Create, update, and delete users, entities, and their interaction events.
  • 📊 Real-Time Logging — Integrated with Logstash, Elasticsearch, and Kibana.
  • 🐳 Containerized — Easily deployable with Docker Compose.

🧠 How It Works

Users + Entities + Events → Neo4j Graph → LangChain → LLM Response

🔧 Tech Stack

Layer Stack
Backend Django, Django REST Framework (DRF)
GenAI Langchain + OpenAI/AI21
Graph DB Neo4j
Logging Logstash, Kibana (ELK Stack)
Deployment Docker + Docker Compose

📁 Project Structure

QueryBaseAI/
├── Backend/           # Django logic (views, serializers, APIs)
├── Core/              # Core database logics
├── LLM/               # LLM providers (OpenAI & AI21 logic)
├── GraphDB /          # Neo4J logics aand connector
├── Constants/         # LinkLens project constants
├── Models/            # All django models like user, entity, event
└── README.md          # Project documentation

💻 Getting Started

  1. Clone the repository from GitHub to your local machine
git clone https://github.com/GoodGuyAdy/LinkLens.git
  1. Change the current directory to the cloned project folder
cd LinkLens
  1. Install the Python dependencies listed in the requirements.txt file
pip install -r requirements.txt
  1. Build and starts the Docker containers defined in the docker-compose.yml file
docker-compose up --build
  1. Run the Django development server for the project
python manage.py runserver

🧑🏻‍🔧 Troubleshooting :-

  • Ensure that your .env file contains a valid OPENAI_API_KEY or AI21_API_KEY.
  • Make sure you have an active internet connection.

About

LinkLens is a modular, GenAI-Powered Interest Discovery Framework that captures, analyzes, and leverages user behavior using a graph-based approach. Designed for scalability and deep personalization, LinkLens turns raw user interactions into meaningful, real-time recommendations by modeling behavior as relationships and patterns.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages