vault backup: 2025-07-23 14:43:14

Affected files:
.obsidian/workspace.json
.obsidian_iphone/plugins/obsidian-spaced-repetition/data.json
.obsidian_iphone/workspace-mobile.json
Temporary/RAG.md

Temporary/RAG.md

@@ -0,0 +1,16 @@
+---
+title: RAG
+created_date: 2025-07-23
+updated_date: 2025-07-23
+aliases:
+tags:
+---
+# RAG
+## LangChain Tutorial
+[Build a Retrieval Augmented Generation (RAG) App: Part 1 | 🦜️🔗 LangChain](https://python.langchain.com/docs/tutorials/rag/)
+
+### Indexing
+The indexing is a pipeline for ingesting data and index it. This usually happens offline.
+1. We need to *load* the data. This can come from a variety of different sources
+2. We need to *split* the data into chunks because its easier for indexing and for passing it into a model.
+3. We need to *store* and index the splits such that we can search over them later. Examples are VectorStore and Embeddings model.