User Tools

Site Tools


wiki:ai:rag-app

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
wiki:ai:rag-app [2025/08/05 19:19] – created mcarverwiki:ai:rag-app [2025/08/06 14:06] (current) – [How It Works] mcarver
Line 38: Line 38:
 ---- ----
  
-===== How It Works ===== 
- 
-==== 1. Document Ingestion ==== 
-  - Connects to your Azure Blob Storage 
-  - Parses `.txt`, `.docx`, and other file types 
-  - Splits documents into manageable chunks 
-  - Generates embeddings using OpenAI (e.g., `text-embedding-ada-002`) 
-  - Indexes both text and vectors into Azure Cognitive Search 
- 
-==== 2. Query Workflow ==== 
-  - User submits a question 
-  - App: 
-    - Generates embedding for the question 
-    - Searches Cognitive Search for top-K relevant chunks 
-    - Constructs a prompt with context + question 
-    - Uses GPT model to answer the question 
-    - Returns answer along with source documents 
- 
----- 
  
 ===== Use Cases ===== ===== Use Cases =====
wiki/ai/rag-app.1754421548.txt.gz · Last modified: by mcarver