15,960 views
In this video, we will build a chatbot using Retrieval Augmented Generation (RAG) from scratch. We will use OpenAI's gpt-3.5-turbo LLM and at the end an example with Llama 3.1-70b through the Groq API. All this using LangChain! Additionally, we will use OpenAI's text-embedding-3-small embedding model and Qdrant vector database as our knowledge base. I hope you like it! Notebook: https://github.com/infoslack/youtube/... Groq: https://groq.com/ Qdrant: https://qdrant.tech/ Word Embeddings video: • How to use OpenAI Embeddings and Pin.. .