Ashwanth Kumar Daggula

Want to ace your next AI/ML interview? Most engineers know about embeddings, but not the full vocabulary of vector databases that power RAG and search systems. This guide breaks it down clearly: ▪️Vector embeddings & similarity search ▪️ANN vs. exact search (speed vs. accuracy) ▪️Indexing methods: Flat, HNSW, IVF, PQ, IVFPQ ▪️Key performance metrics: recall, latency, throughput, QPS ▪️Scaling concepts: filtering, sharding, reindexing ▪️Popular DBs: FAISS, Pinecone, Milvus, Weaviate, Qdrant, Chroma 👉If you’re serious about RAG, search, or AI infra, you need to know these terms. ➕ Follow Naresh Edagotti for more content that makes complex AI topics feel simple.

153

36 Comments

What things in Gen AI a Data Engineer should know! LLM - Large Language Model (act's like a brain) This LLM has 2 main stages - Pre training - Fine tuning although there are more.. In Pre training Big Companies will take a big chunk of data (100's of TB) available on internet, blogs, wikipedia etc and get a gist of it in a few GB's. Lets consider 70 Billion parameter model, each parameter here will be a float of 2 bytes and will take 140 GB. This will take 10's of days and 1000's of heavy machines, and 10's or 100's of million dollars to do this and we get a base/foundation model. This base model cannot answer question, rather if you give it a question it might give more questions. Now, we can leverage the foundation model and develop something. As a Data Engineer, => Prompt Engineering is the easiest thing to do, but when creating applications you need to write it in a programatic way. writing better prompts with more context can help us get better results. => Retrieval Augmented Generation (RAG) - As a Data Engineer you can index your company documents, here you would require to clean the data and index it in a vector database. Later when a prompt is given, it will try to do a simarity search and will search in your vector database. whatever results come will be augmented to your prompt and it's like more context is passed as part of the prompt for better results. So, setting up a vector DB, cleaning documents, and storing in vector DB can be directly in a Data Engineers portfolio. => Model Fine Tuning - This is where the world is moving towards. Instead of striving for bigger and bigger base model, it has been seen that a decent size base model with a good fine tuning done for specific tasks can perform better. So, we will take a foundation mode, and we might have 10's or 100's of thousands of quality questions and answers (high quality training data) on which we fine tune the model. There can be different fine tuned models specific to each task. Do not try using a single LLM for everything. A better way is to use specialised LLM's fine tuned differently to do different stuff's. A model might be good at summarisation, other might be good at judging which summaries are better. Also the LLM's can be given access to various tools like google search, libraries to plot a graph, calculator etc in order to achieve a task. => Now when you develop complex application, it might happen you use a LLM for summarisation, and the output of this LLM goes to other LLM for judging. So there can be a big pipeline, this can be developed using langchain. So I feel - A basic understanding of terminologies around Pre training - Vector Database - RAG (Augmenting the prompt) - Model Fine tuning - Lang Chain - Agentic AI are the things which at the minimum a Data Engineer should know. But there are many more things within this, which I will cover in extreme depth in my "AI for Data Engineers Program" I hope you learnt something new!

50

3 Comments

🚀 The RAG Developer Stack 2025 – Build Intelligent AI That Thinks, Remembers & Acts 🌟 Retrieval-Augmented Generation (RAG) isn’t just hype—it’s powering next-gen AI. From copilots to enterprise search, RAG blends memory, precision & reasoning into one pipeline. How do you go from raw data to smart agents? Here’s your 2025 full-stack guide to designing, deploying, and scaling RAG-powered apps: 1. LLMs – The System's Brain Language models respond using both retrieved context + pre-trained knowledge. • Open Source: LLaMA 3.3, Mistral, DeepSeek, Yi, Falcon, Command-R, Qwen • Commercial APIs: GPT-4o (OpenAI), Claude 3 (Anthropic), Gemini 1.5 (Google), Cohere Command R+, Amazon Titan 💡 Use open models for edge deployments or privacy-sensitive tasks. 2. Frameworks – RAG Orchestration Made Easy Chain retrieval, embedding & generation steps: • LangChain & LlamaIndex – RAG-native, modular • Haystack, txtai – NLP/search optimized • Amazon Bedrock, Azure AI Studio – Model access with guardrails ✨ Try Flowise, Superagent for low-code agent creation. 3. Vector Databases – Fast Context Retrieval Embed & store knowledge for relevant recall: • Chroma, Qdrant, Pinecone, Weaviate, Milvus, FAISS, LanceDB • pgvector (PostgreSQL extension) for hybrid search 📈 Hybrid = vector + keyword = better precision. 4. Data Extraction – Clean Inputs, Smart Outputs RAG is only as good as the source material: • Crawl4AI, FireCrawl, LlamaParse, Docling, MegaParser • LangChain loaders, Unstructured.io, Trieve 🧠 Use smart chunking + metadata tagging for better recall. 5. Model Access – Run Open LLMs Anywhere Test, deploy, and scale: • HuggingFace, Ollama, Together AI, GroqCloud, Replicate • Inference tools: vLLM, TGI, LMDeploy 🔧 Local models via Ollama = privacy-first RAG. 6. Embeddings – The Core of Retrieval Turn text into searchable vectors: • OpenAI (text-embedding-3-small), Cohere • BGE (BAAI), T5-Sentence, Nomic embed-text, Voyage AI 🚀 Use domain-tuned embeddings for legal, medical, etc. 7. Evaluation & Monitoring – Ensure Quality Track faithfulness, relevance & accuracy: • Ragas – End-to-end RAG evaluation • TruLens – Pipeline monitoring & tracing • Vellum, Giskard, Zeno, PromptLayer – Prompt testing 📊 Track: hallucination, groundedness, precision@k. 🔥 RAG in 2025 = Static Bots → Agentic AI Today’s agents can: • Remember long-term • Connect to APIs • Take actions, not just respond • Learn & personalize at scale • Adapt to user context in real time 🎯 Final Thoughts Whether you're building an AI copilot, enterprise search, or expert agent, this RAG stack is your foundation for smart, scalable, and responsible AI. 👋 I'm Muhammad Ghulam Jillani, Principal AI Data Scientist at @ Jillani SofTech. I help organizations design agents with memory, API access & real-world impact. 📂 Portfolio: https://lnkd.in/dv5tCb92 📞 Book a call: https://lnkd.in/emns3fF8 #ragstack #llmops #generativeai #langchain #vectorsearch #chatbotdevelopment #rag #jillanisoftech #ai #genai

578

2 Comments

Mythology meets machine learning: India's first case study in AI-powered storytelling at scale. There's been legitimate skepticism about AI in entertainment—can technology truly capture the emotional weight of something as sacred as the Mahabharat? What Collective Artist Network & JioHotstar have executed with Mahabharat: Ek Dharmayudh offers a compelling answer. This is production infrastructure, not just production assistance: ✅ 100 episodes with cinema-grade VFX ✅AI-driven character modeling for expressive consistency across the series ✅Workflows that compress multi-year timelines into months ✅Visual ambition that would've been cost-prohibitive a decade ago Today's AI pipelines enable higher visual standards (as compared to the ones we have grown up with) within scalable budgets—turning what was once a financial barrier into competitive advantage. This marks India's evolution from AI as a tool → AI as core infrastructure for entertainment. 💡The real question: If AI can industrialize the Mahabharat while maintaining cultural depth, what's the next frontier? Original Indian epics designed for global audiences? I would suggest to embrace rather than fighting it, change can be scary but it the only constant #AIInnovation #CulturalTech #ThoughtLeadership #StreamingStrategy #Mahabharat #AI

91

19 Comments

Every week: "AGI is just around the corner!" The research says otherwise. Here's what the data reveals. 6 fundamental barriers researchers have identified: - No persistent memory - Rigid task boundaries - Pattern recognition ≠ understanding - Zero common sense (70-year-old unsolved problem) - Massive training costs ($100M+ for GPT-4) - No scientific consensus on intelligence itself Interesting market observation: While headlines promise AGI by 2025, leading AI researchers are surprisingly candid about these limitations. Yann LeCun: "AI systems still lack the general common sense of a cat." Recent papers from Apple, Salesforce, and Anthropic all highlight fundamental reasoning gaps. What we're seeing in practice: - Companies finding success focus on narrow applications rather than waiting for general intelligence. - The 80/20 pattern emerges consistently across implementations. - The research suggests AGI timelines remain speculative at best. - Most predictions appear to be marketing rather than scientific consensus. What patterns are you observing in AI implementation? Are the limitations becoming more apparent? 🤔

72

45 Comments

***** Algorithm of Thought (AoT) ***** Most of us have tried clever prompts to get better answers from large language models. But there is a new way of thinking called Algorithm of Thought (AoT). Instead of only giving instructions and hoping the model figures it out, AoT teaches the model how to explore a problem space. It does not settle for the first answer; it searches, tests, and refines, similar to how a person reasons through a tough question. Why this matters: More accurate and reliable results Handles complex, multi-step problems better Makes LLMs feel smarter and more useful in real work This feels like the shift from guessing to thinking. The prompting may not be about writing the perfect question but about guiding the model’s reasoning itself. #AI #PromptEngineering #LLM #AlgorithmOfThought #MachineLearning

28

8 Comments