{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/476c1addac204830bdbc60292ad52d4e\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/476c1addac204830bdbc60292ad52d4e-00001.gif","duration":300.6,"title":"Building Naive King Lear RAG in Python","description":"In this video,  I give a high level walkthrough of building your first RAG/RAQA application:\n -  Split docs into chunks\n-  create embeddings for each chunks using an openai embedding model\n-  Store embeddings in a local vector database\n- Wrap the vector store  in  a Retriever\n-  Take the user query and compute cosine similarity between our question and stuff in vector store\n-  Setup Visiblity and Eval using Wandb so that we can inspect what went wrong \n-  Using GPT4 as a custom evaluator for our RAG application\n\nGithub Notebook Link: https://github.com/rajkstats/AIE2/blob/main/Week%202/Day%201/Pythonic%20RAG%20Assignment_rk.ipynb"}