Coalesce and Snowflake Cortex Analyst demo: model data for AI and analytics

Moving BI from dashboards → to conversational analytics! It would be interesting to see AI + LLMs handling large scale queries, generate SQL, visualise insights, and even understand voice & images all while maintaining latency. #AI #GenAI #RAG #LLMOps #VectorDB #DuckDB #Plotly #Vosk #LLaVA #Phoenix #Langfuse #BI #DataAnalytics #PromptEngineering

🚀 Reimagining Business Intelligence with AI + LLMs After years of working with traditional BI tools, I’ve been exploring along with Sachin Jain how Generative AI, RAG, and multimodal inputs can transform data analysis into a truly conversational and intelligent experience. Here’s the architecture for a next-gen BI assistant we’re building: 🔹 Natural Language Queries → SQL Generation - User query (text/voice) + schema + sample data → LLM generates optimized - SQL - Executed on DuckDB for fast in-memory analytics 🔹 Data → Graphs & Insights - Clean DataFrame passed to LLM → predicts graph metadata (chart type, X/Y axes, labels) - Visualized dynamically with Plotly 🔹 RAG + VectorDB (Chroma) - Query + dataset embeddings stored in VectorDB - Retrieves most relevant datasets to enrich insights 🔹 Multi-Modal Inputs - Vosk LLM for speech-to-text - LLaVA/Ollama for image-based Q&A 🔹 LLM-as-a-Judge & Evaluation - Google Gemini as Judge to refine prompts and improve query accuracy - Automated evaluation with RAGAs, benchmark datasets, and Langfuse/Arize AI Phoenix for tracing & monitoring This prototype blends ETL + LLMOps + GenAI into a seamless pipeline where users can ask questions naturally, and the system handles SQL, joins, graphs, and insights automatically. ✨ Moving from dashboards → to Conversational Analytics. #AI #GenAI #RAG #LLMOps #VectorDB #DuckDB #Plotly #Vosk #LLaVA #Phoenix #Langfuse #BI #DataAnalytics #PromptEngineering

SQL + AI = 🚀 Future-Proof Skills I just completed the "SQL USING AI" workshop by #Be10x 🙌 — and my data workflow got a serious upgrade. 💡 Key takeaways: 🤖 Claude for generating & optimizing complex SQL queries. 📚 SQLBolt to keep fundamentals razor-sharp. 🛠️ AI debugging tools that save hours of trial & error. 📝  Specialized AI tools like BlazeSQL and AI2SQL for debugging SQL code are a game-changer—saving hours of head-scratching frustration 👉 How are you integrating AI into your SQL workflow? 👉 What’s one AI tool that’s been a game-changer for you? #SQL #AI #DataAnalytics #Be10x #TechSkills #FutureOfData #ClaudeAI #DataScience #Upskilling

✨ From SQL Queries to Text-to-SQL — The Future of Analytics? ✨ When I first started with SQL, I remember spending hours perfecting queries to pull the right data. Today, AI is making that process faster — with Text-to-SQL, you can literally type: 👉 “Show me the top 5 products by sales in 2024” and get the SQL query written for you. This doesn’t mean SQL is going away. In fact, it highlights why knowing SQL is more important than ever: 🔹 To validate what the AI generates 🔹 To optimize queries for performance 🔹 To ensure accuracy when the stakes are high I see Text-to-SQL as an assistant, not a replacement — freeing analysts to focus on insights over syntax. 💬 Have you tried Text-to-SQL yet? Do you see it as a game-changer or just a trend? #SQL #DataAnalytics #TextToSQL #AI #FutureOfWork #DataScience

We keep on hearing that AI won’t replace data analysts, but data analysts who use AI will replace those who don’t. Here are the 5 things AI can do much faster today than I could back in 2022: 1️⃣ Query generation → What used to take 30 minutes in SQL now takes 30 seconds. AI drafts, analysts refine. 2️⃣ Data cleaning → No more endless hours fixing messy spreadsheets. AI detects errors and fills gaps. 3️⃣ Dashboards on demand → Charts and visuals built instantly, so analysts can focus on interpretation. 4️⃣ Smarter insights → AI catches anomalies and correlations we might miss, surfacing trends faster. 5️⃣ Time for strategy → With the grunt work reduced, analysts shift to storytelling, business impact, and influencing decisions. The skill gap is widening: Analysts who master AI are moving ahead. Those who don’t… are stuck doing yesterday’s work. 👉 If you’re a data analyst today, how much of your workflow already includes AI? #AI #Data #SQL #Python #Analytics

Bringing AI to Data Solutions: Snowflake Generative AI Professional Certified! As a Data Solutions Engineer, I’ve always been the bridge between data and business, answering queries and delivering insights. One recurring challenge has been the turnaround time—even small queries often required code changes, testing, and moving updates to production. This is exactly where AI can transform the way we work. This course was a hands-on deep dive into how AI can enhance data solutions engineering, especially through Text-to-SQL generative apps, which allow natural language querying of structured data. Key learnings from the program include: Building applications for AI tasks like summarization, translation, sentiment analysis, and text classification Performing prompt engineering and inference with foundation model families like Llama, Mistral, and Anthropic Fine-tuning foundation models for desired behaviors or distilling capabilities from larger models Asking questions of structured data using natural language (Text-to-SQL) Building and evaluating RAG applications to extract insights from unstructured data Through lab exercises and applied projects, I gained practical experience in model fine-tuning, batch analysis of unstructured text, text classification, and implementing retrieval-augmented generation applications. This is just the beginning of how AI can revolutionize data solutions engineering, making insights faster, more accessible, and actionable. Excited to bring these skills into real-world projects and continue exploring the future of AI in data! #GenerativeAI #Snowflake #TextToSQL #DataEngineering #Analytics #AIinData #RAG #ProfessionalCertificate

🚀 From Data to Decisions: The Power of Data Analysis & Data Science.... AI/ ML Vs Data Science 👇 Nowadays everyone talks about LLM and Different - Different Models like Gemini, Meta, GPT , Claude ,Deep Seek and etc.. In today’s digital world, data is the new oil – but only if we know how to analyze and use it effectively. 🔹 Data Analysis helps us understand trends, patterns, and insights. 🔹 Data Science takes it further with machine learning, AI, and predictive modeling. 👉 Together, they drive smarter decision-making, innovation, and business growth. 💡 Whether it’s finance, healthcare, retail, or technology – data skills are shaping the future. 🔥 Join Groups for the latest Update and Notes:- https://lnkd.in/dYh-u4wP 🎯 Test Your SQL Skills – Free Quiz! https://lnkd.in/gH_M7vSm 🌈Join my YouTube channel for in-depth discussions https://lnkd.in/gr4FGKtW 🔗It is helpful please report and follow Roshan Jha Top 10 Machine Learning questions:- 🌈 https://lnkd.in/gcewTQdC Please ping your questions or query 🔥 #DataAnalysis #DataScience #MachineLearning #AI #CareerGrowth #ML #CareerOpportunity #JroshanCode #CodeJroshan

🚀 Prompt Engineering for Smarter Data Analysis! 📊🤖 As I explore the intersection of AI and data, I’ve found that Prompt Engineering is a powerful tool to make LLMs work like intelligent assistants for data tasks! 💡 Here’s how different prompting techniques can help — plus examples you can try: 🔹 Zero-Shot Prompting 🧠 No examples, just instructions. 📌 Useful for quick tasks. Example: "Summarize the key trends in this sales data from January to June." 🔹 Few-Shot Prompting 📚 Provide a few examples to guide the model. ✅ Improves consistency and accuracy. Example: "Here’s how I want the insights formatted: Highlight top-performing regions Mention any anomalies Now do the same for this new dataset." 🔹 Chain-of-Thought Prompting 🧵 Encourage step-by-step reasoning. 🔍 Ideal for complex analysis. Example: "First, calculate the monthly average revenue. Then, identify months with above-average growth. Finally, suggest possible reasons for the spikes." 🔹 Chain Prompting 🔗 Break down tasks into smaller prompts. 🎯 Great for modular workflows. Example: 1️⃣ "Clean the dataset by removing null values." 2️⃣ "Analyze customer churn rate over the last 6 months." 3️⃣ "Generate a summary of churn drivers." 🎥 Want to learn more? This YouTube video explains it beautifully: https://lnkd.in/g8Pant5q 👉 Prompt Engineering Explained 💬 Have you tried using LLMs for data analysis yet? What kind of prompts worked best for you? #PromptEngineering #DataAnalysis #AI #LLM #ZeroShot #FewShot #ChainOfThought #TechWithPronoti #LearningJourney #LinkedInLearning #MCAJourney

𝗔𝗜 + 𝗗𝗮𝘁𝗮 𝗔𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝘀: 𝗧𝗵𝗲 𝗙𝘂𝘁𝘂𝗿𝗲 𝗶𝘀 𝗛𝗲𝗿𝗲 Generative AI isn’t just a buzzword anymore—it’s transforming how we work with data every single day. 🔹 Natural Language Queries – Tools like Power BI Copilot let business users ask questions in plain English and get instant visuals. 🔹 Automated Insights – LLMs can scan millions of records, highlight anomalies, and draft summaries in seconds. 🔹 Faster Decisions – Real-time integration of AI models into analytics pipelines means leaders act on insights immediately. For data analysts, this isn’t a replacement—it’s an upgrade. Our role shifts from data preparation to strategic storytelling, where we guide AI and ensure data quality, privacy, and context. I’ve started experimenting with GenAI-driven dashboards, and the productivity boost is incredible. 👉 How are you using AI to accelerate analytics in your work? #AI #GenerativeAI #DataAnalytics #BusinessIntelligence #PowerBI #SQL #Python #MachineLearning #DeepLearning #DataEngineering #DataVisualization #AnalyticsCommunity #FutureOfWork #TechTrends #CloudComputing #BigData #RealTimeAnalytics #DataScience #DataDriven #Innovation #DigitalTransformation #DataGovernance #ArtificialIntelligence #DataOps #AIAnalytics #AdvancedAnalytics #DataStrategy #AifiniteLearning

🚀 What is AI Query in Databricks? Let’s break it down simply! 🧠✨ Imagine you have a magical assistant who can instantly read heaps of information, understand it, and then give you quick answers or summaries—without you having to dig through all that data yourself. That’s exactly what AI Query in Databricks does! The ai_query function provides a simple way to apply AI directly on your data within Databricks. It supports querying powerful AI models from different sources: the Databricks foundation model endpoint, external model endpoints, and even your own custom model endpoints using Databricks Model Serving. How to use AI Query? Here’s the basic syntax: #sql ai_query(endpoint, request) endpoint: The name of the AI model endpoint you want to query. request: The question or command you want to ask the AI about your data. For example, to summarize customer reviews, you might write: #sql SELECT ai_query('databricks-meta-llama-3-3-70b-instruct', 'Summarize the key points of these reviews') AS summary FROM customer_reviews; With AI Query, you can: Summarize content Extract insights Detect fraud Forecast trends ... all with a simple query. And you don’t need to be a tech expert! Whether it’s summarizing feedback, translating text, or predicting sales, AI Query lets you unlock AI insights directly where your data lives—easily and efficiently. Imagine telling your data, "Give me a quick summary of these reviews," and getting an instant, clear answer – right inside Databricks. No jargon, no complexity, just actionable insights. This is a game changer for businesses wanting to benefit from AI without the tech headache. Ready to simplify your data with AI? 🔥 #AI #Databricks #DataScience #BusinessInsights #EasyAI #DataMagic