Akhtar Abbas
AI Workflow & RAG Pipeline Specialist | WordPress Dev
New to Contra
Akhtar is ready for their next project!
While building Mahir AI, a service booking app for the Pakistani market, I needed the assistant to recommend real services based on natural language queries, not just keyword matches. That meant building a RAG pipeline on top of Supabase's pgvector extension.
The first version was straightforward: embed every service listing as is, store the vectors, run similarity search. Results were mediocre. A user asking for "someone to fix my kitchen sink" wasn't reliably matching plumbers, because the raw listing data was too sparse and inconsistent, some entries were a single line, others had five.
The fix was in the preprocessing, not the retrieval logic. I restructured each listing into a consistent, context rich chunk before embedding: service type, common problem descriptions, location context, and price range folded into a short natural language paragraph. That alone improved match quality more than any tuning I did on the retrieval side.
This pipeline now sits behind a Gemini based multi agent layer that handles the conversation, decides when to search, and formats the final recommendation. But the lesson that stuck with me: in RAG systems, embedding quality is a data problem before it's a model problem. Most teams over invest in the model and under invest in how they structure what goes into it.
1
32
Designed and developed the official website for a digital agency to present services including web development and digital solutions. Implemented a clean, professional layout with strong branding. Focused on performance optimization, mobile responsiveness, and SEO structure to attract potential clients and improve conversion.
0
35
Developed a modern and professional website for an architecture firm to showcase their portfolio and services. Built using WordPress with a clean, responsive design tailored to highlight projects visually. Optimized the website for fast loading speed and SEO to improve online visibility. Delivered a user-friendly structure that enhances navigation and client engagement.
0
48
Developed a fully responsive and visually engaging travel and tour website for showcasing adventure packages and destinations. The platform was designed to provide a seamless browsing experience with intuitive navigation, ensuring users can easily explore tours and travel offerings.
Implemented performance optimization techniques to enhance website loading speed and applied SEO best practices to improve search engine visibility and organic reach. The design focuses on user engagement, clarity, and mobile-first responsiveness.
0
66
The Higher Education Finder Agent is an AI-powered academic advisor designed to help students discover and evaluate global university programs. Rather than relying on outdated static training data, the agent performs real-time web searches to aggregate current application guidelines, tuition fees, and admission criteria for the upcoming intake cycles.
0
107