Home

• Prompt Engineering
• RAG (Retrieval Augmented Generation)
• Embeddings + Vector
• DB Function Calling / Tools

Prompt Engineering

📌 What is it?

Writing smart input (prompt) to get correct output from LLM

🎯 Example

❌ Bad Prompt: Tell me about milk

✅ Good Prompt: You are a shop assistant.

Extract product name and quantity: Input: "2 milk and 1 bread"

Output JSON:

👉 Output becomes structured:

{ "milk": 2, "bread": 1 }

RAG (Retrieval Augmented Generation)

Overview

Retrieval-Augmented Generation (RAG) is an AI architecture that enhances large language models (LLMs) by allowing them to retrieve relevant external information before generating a response.

Instead of relying only on pre-trained knowledge, RAG enables models to access up-to-date, domain-specific, and private data sources, making responses more accurate and context-aware.

RAG is widely used in:

• Customer support chatbots
• Healthcare report summarization
• Legal and compliance systems
• Financial analysis tools
• Enterprise knowledge search systems

Why RAG is Important

Traditional LLMs like GPT-style models generate responses based only on training data. This creates limitations:

Limitations of standard LLMs

• Knowledge cutoff (no real-time updates)
• Hallucinations (false or made-up answers)
• No access to private company data
• Lack of personalization/context

RAG solves these problems by:

• Fetching real-time relevant data
• Grounding answers in actual documents
• Reducing hallucinations
• Keeping knowledge updated without retraining

Real-Life Example

Imagine two students preparing for an exam:

Student 1 (LLM only)

• Reads books once
• Answers from memory only
• Cannot verify facts

Student 2 (RAG system)

• Reads books
• Can open books during exam
• Verifies answers in real-time

Student 2 performs better because they can retrieve information when needed.

Key Benefits of RAG

1. Reduces Hallucination

   LLMs generate more factual and grounded responses. Some LLM is more overconfitent 
   and giving wrong response. In LLM we can not verified data but in RAG we can verified
   then respose will be more grounded and real data.
   

2. Keeps Knowledge Updated

    Works with real-time and dynamic data sources. In LLM there is a knowlege cutoff date 
    mean till training date all info present. But by using RAG we can use current data or uptodate.
   

3. Cost Efficient

    Avoids expensive retraining or fine-tuning of models mean new data then we can give access 
    by using RAG without training and finetuning.
   

4. Data Privacy

   Sensitive enterprise data stays within controlled systems. Becuase our not access whole data same time for particular query 
   it is fetching/access only data. Suppose big company do not want to give full access to model. So he can control by using 
   RAG.
   

5. Context Awareness

   Personalized responses using user-specific data.
   

Example:

     Airline chatbot knows your booking details (PNR, flight time, delay status)

RAG Architecture Overview

RAG consists of two major pipelines:

1. Ingestion Pipeline

This prepares data for retrieval.

Steps:

• Data Collection
  • PDFs
  • Web pages
  • Databases
  • Excel files
  • APIs
• Chunking
  • Large documents are split into smaller pieces (chunks)

Types of chunking:

• Fixed-size chunking
• Hierarchical chunking
• Semantic chunking
• Embedding Generation
• Text is converted into numerical vectors using embedding models.

Popular embedding tools:

• OpenAI Embeddings
• Google Gemini Embeddings
• Sentence Transformers (Hugging Face)
• Vector Database Storage
• Embeddings are stored in vector databases such as:
• Pinecone
• ChromaDB
• FAISS
• Elasticsearch

Vector databases enable semantic search (meaning-based search), not just keyword matching.

2. Retrieval Pipeline

This handles user queries.

Steps:

• User Query Input

  User asks a question.
  

• Query Embedding

  Query is converted into vector form.
  

• Similarity Search

  System finds the most relevant document chunks from the vector database.
  

• Context Creation

  Retrieved data is used as context.
  

• Augmentation

  Prompt is enriched with:
  

• User query

  Retrieved context
  

• Generation

  LLM generates final response using grounded context.
  

Combined flow

Why It is Called RAG

• Retrieval → Fetch relevant data
• Augmented → Add context to prompt
• Generation → Produce final AI response

RAG Technologies & Tools

Frameworks

• LangChain
• LlamaIndex
• Haystack

Embedding Models

• OpenAI text-embedding models
• Gemini embeddings
• Sentence Transformers

Vector Databases

• Pinecone
• FAISS
• ChromaDB
• Elasticsearch