In this video, I will guide you on how to build a chatbot using Retrieval Augmented Generation (RAG) from scratch. We will use OpenAI’s gpt-3.5-turbo LLM, which we will implement through LangChain’s ChatOpenAI class. Furthermore, we will use OpenAI’s text-embedding-3-small for embedding and the Qdrant vector database as our knowledge base. I hope you like it; there’s a little surprise waiting for you at the end of the video!
– Notebook: https://github.com/infoslack/qdrant-example/blob/main/rag_chatbot_qdrant.ipynb
– Dataset: https://huggingface.co/datasets/infoslack/mistral-7b-arxiv-paper-chunked
