What is RAG?RAG kya hai?

🧸 Think of it likeAise samjho

Like an open book exam: first find the right pages in the book, then write the answer from them and mention the page.Open book exam jaisa: pehle kitaab mein sahi pages dhoondho, phir unse jawaab likho aur page number batao.

📘 ExplainedVistaar se

RAG has two phases. Indexing: split documents into chunks, create embeddings and store them in a vector database with metadata and permissions. Answering: embed the question, retrieve the best chunks (often hybrid search plus reranking), put them in the prompt with instructions to answer only from them and cite sources, then generate. RAG keeps answers current and grounded without retraining. Most failures are retrieval failures, so measure retrieval and answer quality separately.RAG ke do phases hain. Indexing: documents ko chunks mein todo, embeddings banao aur metadata aur permissions ke saath vector database mein rakho. Answering: sawaal ka embedding banao, best chunks nikaalo (aksar hybrid search plus reranking), unhe prompt mein daalo is instruction ke saath ki sirf unhi se jawaab de aur sources cite kare, phir generate karo. RAG bina retrain jawaab current aur grounded rakhta hai. Zyaadatar failures retrieval ke hote hain, isliye retrieval aur jawaab ki quality alag naapo.

💡 Real exampleAsli example

An HR bot that answers 'how many casual leaves do I get?' from the latest policy PDF, with the page reference.HR bot jo 'mujhe kitni casual leaves milti hain?' ka jawaab latest policy PDF se, page reference ke saath deta hai.

📖 Learn it step by stepStep by step seekho

• RAG: letting an LLM answer from your documentsRAG: LLM ko aapke documents se jawaab dene dena
• Embeddings and vector databases: searching by meaningEmbeddings aur vector databases: matlab se search karna
• Evaluating AI: how to know it actually worksAI ko evaluate karna: kaise pata chale ki sach mein kaam karta hai

🔗 Related termsJude hue shabd

• EmbeddingA list of numbers that captures the meaning of text, images or items, so similar meanings are close together.Numbers ki list jo text, images ya items ka matlab pakadti hai, taaki milte julte matlab paas paas hon.
• Vector databaseA database built to store embeddings and quickly find the ones closest in meaning to a query.Database jo embeddings store karne aur query ke matlab ke sabse paas wale jaldi dhoondhne ke liye bana hai.
• ChunkingSplitting documents into smaller pieces before embedding them for search and RAG.Search aur RAG ke liye embed karne se pehle documents ko chhote tukdon mein todna.
• Hybrid searchCombining keyword search and vector search to get the best of both.Keyword search aur vector search ko milana taaki dono ka faayda mile.
• GroundingMaking an LLM base its answer on provided sources or tool results, not just its memory.LLM ke jawaab ko diye gaye sources ya tool results pe based banana, sirf uski yaad pe nahi.