Freelancers using Neo4j in PakistanFreelancers using Neo4j in Pakistan
ProjectsPeople
Usman Haider's avatar
Usman Haider
Lahore, Pakistan
AI/ML & Data Solutions Engineer
New to Contra
AI/ML & Data Solutions Engineer
Cover image for Retail Knowledge Graph In this project,
Retail Knowledge Graph In this project, we built a semantic knowledge graph tailored to the retail industry. The pipeline involved developing AI agents to transform heterogeneous data into standardized formats. Ontologies were created to represent domain knowledge accurately. Using Gemini models and LangChain, user queries were converted into Cypher queries to retrieve insights from a Neo4j database. We utilized an MCP server for orchestration and LangSmith for secure login and audit trails. This system enhances complex data exploration for non-technical users.
2
2
175
Cover image for Student Medical Chatbot Built a chatbot
Student Medical Chatbot Built a chatbot to assist MBBS students in navigating medical literature. Leveraged Llama Index and fine-tuned language models to ensure accuracy. Embeddings were stored in OpenSearch, hosted on AWS. The Django backend included secure authentication and session management for a robust user experience.
0
94
Cover image for Prompt Engineering Mini-Academy is a
Prompt Engineering Mini-Academy is a digital learning product built using Kajabi. It helps users learn how to write better AI prompts and use AI tools for daily tasks such as writing, research, summarization, and productivity. The problem it solves is that many people use AI tools without a proper structure, which leads to weak or generic results. This product gives users a clear learning path, practical prompt templates, and workflow examples to improve the quality of their AI outputs. I used Kajabi to create the landing page, email capture form, downloadable prompt resource, product offer, checkout page, and course structure. A sample video is attached to demonstrate the product flow and user experience.
1
120
Cover image for Developed a full-stack language learning
Developed a full-stack language learning application tailored for Luxembourgish, combining speech recognition, natural language understanding, and generative AI. Fine-tuned OpenAI’s Whisper model for accurate Luxembourgish transcription and built a custom text-to-speech (TTS) engine for realistic audio feedback. A RAG-based architecture enables the app to answer user queries contextually, making learning highly interactive. The frontend is built with React, while Flask powers the backend. Designed to deliver an immersive, conversation-driven auditory learning experience.
1
159
Neo4j(1)
abdullah masood's avatar
abdullah masood
Lahore, Pakistan
AI & Full-Stack Engineer | Building Production AI SaaS, APIs
New to Contra
AI & Full-Stack Engineer | Building Production AI SaaS, APIs
Cover image for 🚀 Building a Graph-Based Fraud
🚀 Building a Graph-Based Fraud Detection System with Neo4j A single transaction may look normal. Its connections can tell a different story. I’m building a learning project using Neo4j and Cypher to explore relationships between customers, accounts, transactions, and devices—and flag patterns worth investigating. 🔍 Patterns I’m exploring: • Multiple customers sharing the same device • Unusually large transactions • Rapid transactions within a short period • Multiple accounts sending money to one account • Circular transfers between connected accounts The focus is explainability: showing the relationships behind each flag so the suspicious activity is easier to understand. Through this project, I’m strengthening my graph data modelling, Cypher queries, and rule-based detection skills. Next: FastAPI integration, transaction risk scores, fraud alerts, and an interactive monitoring dashboard. 🛠️ Currently a learning prototype, with more updates coming as I build. What would you investigate first: shared devices or circular transfers? #Neo4j #GraphDatabase #FraudDetection #Cypher #BackendDevelopment #LearningInPublic
1
211
Cover image for 🚀 Introducing GraphBridge – Turn
🚀 Introducing GraphBridge – Turn JSON into Grafana Dashboards One thing I've noticed while working on different projects is that applications already have valuable metrics, but getting those metrics into Grafana often requires exporters, custom integrations, or additional setup. I wanted something much simpler. So I built GraphBridge. The idea is straightforward: Your Application ↓ Send JSON ↓ GraphBridge ↓ Prometheus ↓ Grafana Instead of writing custom exporters, your application simply sends JSON metrics to GraphBridge. For example: { "active_users": 85, "orders_today": 42, "revenue_today": 9840, "failed_jobs": 3, "latency_ms": 210 } GraphBridge automatically converts the data into Prometheus metrics, making it immediately available for Grafana dashboards. Current features ✅ JSON Webhook API ✅ REST API polling ✅ JSON & CSV data sources ✅ Prometheus /metrics endpoint ✅ Docker Compose deployment ✅ Auto-configured Grafana dashboard ✅ Example integrations for Laravel, FastAPI, Node.js, and custom applications Possible use cases • Application monitoring • Queue & background job metrics • Business dashboards • API performance monitoring • FFmpeg streaming statistics • IoT sensor metrics • Internal analytics • Custom operational dashboards The goal is simple: Send JSON. Visualize everything. This is the first public MVP, and I'm planning to continue improving it with additional integrations and monitoring templates. I'd love your feedback and suggestions! ⭐ GitHub: https://lnkd.in/dAYdNJxg
1
160
Cover image for A Kubernetes deployment should be
A Kubernetes deployment should be easy to trace: what changed, who changed it, and why. That’s what interests me about GitOps. With GitOps, the desired state of your infrastructure and applications lives in Git. Changes go through commits and pull requests, while a controller such as Argo CD or Flux continuously reconciles the running environment with that desired state. A typical workflow looks like this: • Build and test the application through CI. • Push the Docker image to a registry. • Update the image version in the Git configuration. • Review and merge the change. • Let the GitOps controller reconcile the cluster. The benefits go beyond automated deployments: ✅ A versioned history of configuration changes ✅ Reviewable changes before deployment ✅ Visibility into configuration drift ✅ A repeatable way to manage environments One important detail: reverting a Git commit can restore an earlier configuration, but database migrations and changes to application data still need their own recovery plan. For me, GitOps connects development and operations through a workflow both teams already understand: Git. Are you using Argo CD, Flux, or CI-driven deployments for your Kubernetes workloads?
1
245
Cover image for Production Kubernetes & Cloud Deployment
Production Kubernetes & Cloud Deployment
1
205
Neo4j(1)