Open AI emebdding, vector database, semantic tagging, website scraping PoC Project

Critical requirements : Open AI, Embedding, Vector databases, Scraping *** If you are interested you must be able to show me a previous related (Open AI embedding) project in your portolfio. Please send me a notification with a link to this project**** General Concept We are building a data-driven content creation system for our agency / clients. The project involves extracting content from client websites, structuring it into JSON packets, tagging it with metadata via a user-friendly web interface, and using OpenAI's embedding with a vector database and GPT APIs to retrieve and generate new content. This will be a new independent prorotype project to get the integrations and workflow set up and working correctly. Full-Stack Developer (Preferred One-Dev Solution) Responsibilities: Develop and maintain a backend pipeline to: - Scrape and preprocess data from client websites. - Chunk content into JSON packets and prepare it for tagging. - Integrate with Supabase for data storage. Build a simple web app for manual metadata tagging: - Design a clean UI for reviewing and tagging content. - Integrate pre-defined tag options for consistency. Set up a vector database for semantic search. Integrate OpenAI’s text-embedding-ada-002 and GPT models to: - Generate embeddings for tagged data. - Retrieve and pass relevant data to GPT for content generation. - Ensure scalability for multi-client support. Requirements: Essential experience with: - APIs: OpenAI API, vector database APIs (Pinecone, Weaviate). - Proficiency in web scraping tools (BeautifulSoup, Puppeteer). - Familiarity with embedding and vector database concepts. - Understanding of token limits and prompt engineering. Other requirements: - Backend: Python (FastAPI), Node.js (Express). - Frontend: React, Vue, or Next.js. - Databases: Supabase, PostgreSQL. ===============================