Build an AI chatbot with RAG integration for our custom business knowledge base

We're a small startup looking to build an AI-powered chatbot that can answer questions based on our own internal business data. We need someone who understands RAG (Retrieval-Augmented Generation), vector databases, and LLM integration to build this from scratch and deploy it to production. We need: a working AI chatbot trained on our custom business documents; a RAG pipeline using a vector database (Pinecone, Weaviate, or similar) for accurate context-aware responses; LLM integration using OpenAI API or Gemini with proper prompt engineering; a clean REST API (FastAPI or Node.js) to power the chatbot backend; a simple frontend interface built in React or Next.js; deployed via Docker.