Gen-AI Developer Classroom notes 25/Aug/2025

RAG

Generation Pipeline

• When a user asks a question, we retrieve the data from vector database and add it to the prompt, pass it across to LLM to get a response

• In the below image block in green color refers to indexing pipeline and blue refers to generation pipeline.
  

• The steps:

  • user query will be passed to vector database
  • response should be injected ina prompt
  • Pass the prompt to LLM
  • Send the response back to the user

• Lets build a generation pipeline with fake indexing Refer Here for the notebook.

• To do the activities in langchain style, lets look into

  • prompt templates
  • chaining

Practical Scenario 1

• Idea 1: Have a collection of story books and ask questions
• Idea 2: Have a collection of KB Articles and as an employee you can ask questions.