Makhfi AI is an intelligent assistant designed for Furqan Qureshi Blogs, a research platform exploring the Quran, Hadith, Modern Science, Archaeology, and Ancient History. It can answer questions, guide users through complex topics, and even summarize videos, based entirely on content from Furqan Qureshi Blogs.
Key Features:
- Modern UI: Built with Next.js and Tailwind CSS, Makhfi AI offers a clean and responsive interface for a smooth user experience.
- Conversational Q&A: Ask questions naturally and receive insightful, well-structured responses based on curated video content.
- Personalized Chat History: Securely manage and revisit past conversations with options to rename or delete.
- Long-Term Memory: Makhfi remembers key facts from past sessions, enabling context-aware and personalized responses over time.
- Verifiable Sources: Every answer comes with direct links to the original videos for transparent fact-checking.
- Video Insights: Share any Furqan Qureshi Blogs video link, and Makhfi will generate summaries and key takeaways to help you grasp the content quickly.
Tech Stack:
- Backend & API: Powered by FastAPI for high-performance, asynchronous APIs handling AI interactions, chat sessions, and message persistence.
- Database: Built with SQLModel atop PostgreSQL (via Supabase) to efficiently manage user data, chat history, and metadata.
- Core Agent Framework: Utilizes LangGraph to implement an Agentic RAG pipeline that enables intelligent reasoning and tool orchestration.
- Vector Database: Pinecone enables fast and accurate semantic search across a rich video knowledge base for relevant information retrieval.
- Memory Management: Integrates Mem0 for external, persistent long-term memory—critical for personalized AI behavior.
- Authentication: Uses Supabase Auth for secure, JWT-based user authentication and session management.
