Added general outlines

Author: codingbandit

01_Overview_Cosmos_DB/README.md

@@ -1 +1,17 @@
 # Overview of Azure Cosmos DB (high-level with links to docs for more information)
+
+
+https://learn.microsoft.com/en-us/azure/cosmos-db/introduction
+
+Azure Cosmos DB is a globally distributed, multi-model database service that enables you to query and store data using NoSQL models using one of five APIs: SQL (document database), Cassandra (column-family), MongoDB (document database), Azure Table, and Gremlin (graph database). It provides turnkey global distribution, elastic scaling of throughput and storage worldwide, single-digit millisecond latencies at the 99th percentile, and guaranteed high availability with multi-homing capabilities. Azure Cosmos DB provides comprehensive service level agreements (SLAs) for throughput, latency, availability, and consistency guarantees, something not found in any other database service.
+
+## Azure Cosmos DB for Mongo DB
+### RU Architecture
+### vCore Architecture
+### comparison?
+### Reference
+https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/introduction
+
+### Azure Cosmos DB Mongo DB vCore
+Intro to Azure Cosmos DB Mongo DB vCore, mentioning vector search, AI enablement - very high level.
+https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/introduction

04_Provision_Azure_Resources/README.md

@@ -2,3 +2,10 @@
 
 - Have deployment scripts
 - Walk through the deployed environment
+
+
+This should be included as a step in 05_Create_First_Cosmos_DB_Project
+
+NEEDS:
+- full solution architecture diagram
+- deployment scripts (ARM/Bicep?)

05_Create_First_Cosmos_DB_Project/README.md

@@ -2,3 +2,17 @@
 
 - How to use the Cosmos DB SDK
 - How to develop locally
+
+## Emulator support (does it support vector search?)
+## Authentication options
+## Create a database
+## Create a collection
+## Create a document
+
+## INCLUDE 08_Load_Data here
+
+## Read a document
+## Update a document
+## Delete a document
+## Query documents
+

07_Vector_Search_Cosmos_DB/README.md

@@ -5,3 +5,12 @@
 - Store vectors
     - Load a text file (policy, FAQ, etc.)
 - Perform a vector search on the index
+
+INCLUDED IN 11_Prompt_Engineering
+
+## The RAG process
+Show in context of Azure Cosos DB Mongo DB vCore
+diagram showing RAG process (highlighting vectorization)
+- Vectorization in RAG
+- Retrievers
+- Prompt stuffing

08_Load_Data/README.md

@@ -3,3 +3,10 @@
 - Manually load data and ask questions about it
 - Run data generator to load sample data
     - We need to find a good data set
+
+Included in 05_Create_First_Cosmos_DB_Project
+NEEDS:
+- What is our scenario/story?
+- data generator/kaggle ? Existing dataset?
+- raw format storage (csv, json, etc.)
+- develop data loader (raw to db)

11_Prompt_Engineering/README.md

@@ -5,3 +5,19 @@
 - Manage contextual data
 - Create a flow that communicates with the deployed Azure OpenAI and Azure Cosmos DB services
 - Implement a web search plugin
+
+## What is a prompt
+## What is prompt engineering
+## General anatomy of a prompt
+Instruction, context, input, output indicator
+## Zero-shot prompting
+## Few-shot prompting
+## RAG
+## Chain of thought
+## ReAct
+
+## Lab
+### Diagram RAG using Azure Cosmos DB for MongoDB vCore as a retriever
+### Using Azure Cosmos DB for MongoDB vCore as a retriever
+### Sample prompts
+