Havish Garimella

It has been fun putting together the Data Engineering track for Fifth Elephant Conference this year along with Shashwat Agarwal and Pramod Biligiri #DataManagement, #MachineLearning, #AI & #Data We have assembled a diverse set of talks.   Even if you are not a hard-core data engineer, you will find something of interest A few talks to highlight 1. Vishnu Vasanth from e6data will talk on the Lakehouse Compute engine they have built. 2. Ruturaj Bhokre from Dream11 will talk on the Evolution of their data platform 3. Mohd. Shadab S. (CISO at Hotstar) will explain Design patterns in Data security 4. Niraj Mishra from Atlassian will talk on Ephemeral data pipelines You may know of API contracts but have you heard of Data Contracts ? Bichitra Kumar Sahoo, Rahul Madan and Shikhar Vaish from Atlan will be conducting a workshop on Data contracts and OpenLineage. There is a separate "LLM and GenAI" track as well, if that suits your interest more. The Fifth Elephant 2024 Conference is on: 📅 13 July 2024 (Saturday)  ⏰ 9 AM to 6 PM  📌 BIC, Indiranagar, Bangalore + Hybrid Access Check out the schedule here & go grab your early elephant tickets today at: http://has.gy/Xz_w P.S. Tag anyone in your networks who is working in the space of #AI #DataScience & #LLMs

29

TGIF, folks! Fridays are hands down my favorite day—a perfect mix of weekend anticipation and a well-deserved breather from the weekly hustle (which I also love, haha). So here's the latest, I've finally caved and set up a Topmate profile! 😅 Why? Because so many of you folks have been reaching out for 1-1 help with: 1. Navigating the wild world of data science and analytics careers 2. Prepping for those nerve-wracking interviews I’ve decided to dedicate few hours of my weekend to offering personalized support for these requests. I've opened up a few 1-on-1 slots on my Topmate profile for those interested. If you're looking for guidance or interview prep, feel free to check it out and book a session! Looking forward to helping you on your data science journey. 😊 https://lnkd.in/gy-fMC6Q #CareerGuidance #DataScience #Analytics #InterviewPrep #TopmateProfile

38

1 Comment

The AI & LLM Revolution Boon or Bane for Society? 🤖 🌍   As we witness the rapid evolution of AI and Large Language Models (LLMs) in recent times, with Meta recently making Llama 3 open source and Vinod Khosla's insane predictions about AI, it's time to pause and reflect on the implications of these advancements on various aspects of our lives.. 🌐   1. Personal Finance 💰: AI and LLMs have the potential to revolutionize personal finance management, making it more accessible and efficient. However, they could also lead to job losses in the financial sector, affecting the livelihoods of many - economic instability?   2. Education 🎓: LLMs can revolutionize education by providing personalized learning experiences, but could they also widen the digital divide?   3. Jobs 🏭: As AI and LLMs infiltrate various industries, how will non-IT and non-engineering professionals adapt to these changes? How can we ensure a smooth transition for affected workforce?   4. Social Life 🤝: Will AI & LLM enhance our social interactions or lead to increased isolation and dependence on technology? AI-powered social media platforms could enhance our online interactions, but they might also contribute to the erosion of privacy and the spread of misinformation.   5. Agriculture 🌾: AI-driven precision farming could boost productivity, but will it also lead to ecological and environmental concerns?   6. Basic Needs 🍲: Can AI help address food security and access to clean water, or will it exacerbate existing inequalities?   7. Work-Life Balance ⚖️: AI can automate mundane tasks, but will it also blur the lines between work and personal life?   8. Health 🏥: AI can revolutionize healthcare, but will it also lead to over-reliance on technology and loss of human touch in patient care? AI-driven healthcare solutions could revolutionize diagnostics and treatment, but they might also raise ethical concerns and exacerbate existing healthcare disparities.   9. Environment, and Ecology 🌳 - AI-driven innovations can help us address pressing global challenges such as climate change and disease outbreaks. However, will they consume vast amounts of energy and resources?   10. Security & Safety 🛡️: AI can improve security measures, but will it also lead to increased surveillance and potential misuse of personal data?   11. Politics & Power 🏛️: AI can help streamline governance, leading to more informed decision-making, will they be exploited for political gains?   Are we on the cusp of a transformative era? As we ponder these questions, it's crucial to remember that responsible AI governance could be the ultimate solution to ensure these technologies benefit society. 🤖   What are your thoughts on this? 🤔 #AI #LLM #ArtificialIntelligence #LargeLanguageModels #Society #Impact #FutureOfWork #Education #PersonalFinance #Environment #Healthcare #Security #Politics #BoonOrBane #BubbleOrRevolution #ResponsibleAI #Governance

3

Hello all, I and my friend Aditya Sahu have been working lately on Automatic Redaction / Replacement tool for PDFs (scanned PDF & text-readable) and for Images which uses large language models (LLMs) in the backend. Different Formats / templates of PDFs cause a major problem in the extraction process. *What it does: 1. It removes the editing panel for your redaction / replacement work and instead you can just explain what you need to redact / replace in normal keywords or plain sentences in a comma separated fashion. 2. It uses LLMs in the background - you can use your own privately deployed model like llama 3 70b fine-tuned version or you can also use models like GPT-4o, Claude etc. which are commercially available. It can be configured based on your requirement. 3. It uses OCR for Image / Scanned Image case, which can be configured to any Cloud Server OCRs as well as open-source OCRs. 4. Can ingest multiple images and PDFs and work sync. 5. You can run multiple iterations on the same file to make many small small changes that can be possible in the PDF. Note: The process is not fully 100% accurate but it is well in range of 85-90+ , the accuracy can vary based on the choice of LLM model with good context length and choice of OCR as well as the quality of image. [*imp] *PDFs are quite complex for handling the formatting issues, so this tool does have limitations on what length of words can be replaced because it might lead to formatting issues in the provided PDF. There would be HIL [human in the loop] for evaluation. You can go through the Demo once; it has 2 parts in it - one for scanned PDF and one for text readable pdf (built using Python) 😀. Right now, it is just a Streamlit demo but parallelly in the backend work is going on... Please DM to me Mohit Singh Pawar or Aditya Sahu for more details or clarification related to its availability. Audio credits: ElevenLabs free credits. I guess will have to upload part 1 here and part 2 in a separate post. part 2 : https://lnkd.in/gEi-DUzb #redact #llm #replace #pdf #genai #generativeai

56

5 Comments

Why do attention models require positional encoding while RNN or CNNs do not? How does it work? I have provided a detailed explanation in my recent blog. #LLMs #AttentionModels #GenaI #PositionalEncodings https://lnkd.in/dHzQfDsi

19

📍 💡 Need some visual inspiration? #Recommendations to foster new ideas and explore the world. #Recsperts Episode No. 22 with Prabhat Agarwal and Aayush Mudgal from Pinterest is out now! Prabhat is a Senior ML Engineer and Aayush is a Staff ML Engineer. Prabhat works on #recommendations and #search systems at Pinterest, leading representation learning efforts. Aayush is responsible for #ads #ranking and privacy-aware conversion modeling. In our interview, Prabhat takes us on the journey of #personalizing the Pinterest Homefeed. We discuss how to capture users' short- and long-term preferences through multiple #embeddings and the role of candidate generators for content diversification. Aayush dives into the specifics of ads ranking at Pinterest and helps us to better understand how multifaceted ads can be. He also shares some insights about #exploration and corresponding randomization in the context of ads and how user behavior is very different between different kinds of ads. Both highlight the role of #counterfactual evaluation and its impact for faster #experimentation. ✅ Subscribe on your favorite podcast player ⭐ Leave a rating or review ✍ Share your thoughts on Pinterest Homefeed Personalization and Ads Ranking Listen to this new episode of #Recsperts - Recommender Systems Experts! 🎧 Website: https://lnkd.in/gVP5Ar_B 🎧 Spotify: https://lnkd.in/gPyguxY3 🎧 Apple: https://lnkd.in/gDCJjFzw

48

5 Comments

Exciting update from Harini Gopalakrishnan, the Field CTO of Life Sciences at Snowflake! She has shared a new section on Drug Discovery using Snowflake. Highlights include: - Training amino acid sequence files within Snowflake using the protT5 model. - Displaying the top three 3D structures based on vector similarity search from amino acid sequences. Here’s why Snowflake is the ideal platform for drug discovery: 🔒 Security and Governance: Interaction with Snowflake data and container services is single-tenant. Data remains within the platform for computation, enabling complex workflows like drug discovery without external data transfer. 📊 Centralized Research Data: Integrate all scientific data (proteomics, screening results, etc.) into a centralized data storage and analysis system. Combining business metadata stores with multi-omics in a Streamlit UI creates FAIR data products. 🤝 Ease of Data Sharing: Enable seamless data collaboration with research partners. 🤖 Managed LLMs: Cortex AI offers a managed vector store using NVIDIA-accelerated compute, available 24/7 for complex tasks like semantic search. ⚡ Warm Compute Pools: Snowpark Container Services allows rapid instantiation of warm compute pools. Harini also mentioned future plans to enhance informatics analysis for drug discovery with ligand docking and small molecule screening and property prediction using Diffusion models. Exciting times ahead! Watch the full presentation here: https://lnkd.in/gm66N3pn #DrugDiscovery #LifeSciences #Snowflake #AI #MachineLearning #DataScience #Biotech #Proteomics #BigData #CortexAI #SnowflakeSquad

19

Just submitted my creation, Arctic Analytics (https://lnkd.in/gVehD56b) to The Future of AI is Open hackathon conducted by #Snowflake and #Streamlit, and what a ride it's been! 🏁💥 Arctic Analytics a Streamlit app based on Snowflake's Arctic AI model, represents a leap toward bridging data privacy and analytics accessibility. It's not merely a tool but a statement - ethical AI use can empower anyone to unleash their data's potential, all the while maintaining stringent data privacy. Imagine drawing powerful insights and visuals without the AI ever peeking into your data, coupled with unmatched transparency about the data shared with the AI. 🛡️🤖 I am proud to have navigated this venture, merging technology with values. And this is merely the start. As submissions close and I await results on June 6, Arctic Analytics stands as a testament to what we can achieve at the intersection of privacy, accessibility, and innovative technology. 🔥🌐 Ready to usher in the future of AI with open arms and secure data? Join me in pushing tomorrow's boundaries today! 🌈⏳ #Hackathon #AI #Innovation #DataPrivacy #TheFutureOfAIIsOpen #SnowflakeArctic #ArcticAnalytics

73

2 Comments

Many of ML practitioners might have heard the term "Extending context length" for LLMs. In case if you want to dive deeper into this topic along with its code implementation, give this blog a read. I have described about Position Interpolation, NTK aware and Dynamic NTK method, which are widely used for extending context length.

68

TensorFlow vs. PyTorch: Finding the best Deep Learning framework for your AI journey 🚀 Which framework will boost your career goals? Whether you’re excited about diving into cutting-edge research with PyTorch or eager to create scalable AI models with TensorFlow, each option has its own perks! From how easy they are to use and the support you can get from the community to their flexibility and scalability, understanding these differences can really set you up for success in the fast-paced world of AI. I think Juliette Carreiro's article for @ironhack is a fantastic resource for anyone starting their journey in Data Science and Machine Learning! On another note, I’m still looking for a German-speaking Data Manager to join a leading company on an exciting automotive project in Frankfurt. If this sounds like a good fit for you or someone you know, please reach out here or at [email protected]. Happy to share more details! #DeepLearning #AI #DataScience #MachineLearning #TensorFlow #PyTorch #CareerInTech #Hiring #ironhack #redsofa #datamanager

12

1 Comment

Attended an incredibly insightful webinar hosted by Ai Palette on "The Next Chapter of CPG Innovation: One Year with Generative AI: Hype vs. Reality." The session featured thought leaders like Srikanth Sridhar, Jerome Linder, and Malay Shah, who shared their expertise on the transformative impact of Generative AI in the CPG industry. Key takeaways: - Jerome highlighted how we are on the cusp of becoming "supersmart & super quick" with the latest LLM based Gen AI advancements. - Srikanth emphasized a bullish outlook, noting how generative AI is rapidly influencing various sectors and the ways of working. Some of the EBIDTA projections that he shared blew my mind! - Malay pointed out the exciting times ahead for operationalizing & scaling up these solutions, and now the time has come to discuss about ROIs and EBIDTA figures. A significant focus was on the reality of AI "hallucinations" and the importance of using medium-sized, focused LLMs to mitigate these issues. Practical insights included the need for strong observability, guardrails, and strategies for rehearsal and remediation to overcome potential challenges. Thank you Ai Palette for this valuable session. I loved it! #CPGInnovation #GenerativeAI #AiPalette #AbhiWrites

19

Gen AI in Identity Verification I'm proud to highlight the continued success of MetaMap‘s Generative AI solution for identity verification, launched in Q1 2024. After months of production use, it has demonstrated remarkable stability and efficiency. Key contributors: 1. Vikram Kalabi : Your robust ML pipeline has proven its resilience, consistently delivering accurate results at scale. 2. Vladislav I. : The human-computer interface you developed has been pivotal, allowing seamless human-in-the-loop feedback and continuous improvement. 3. Alan Garcia : Your operational leadership has ensured smooth integration of human oversight, maintaining high quality standards. This project exemplifies how cutting-edge AI, when thoughtfully implemented, can bring long-term value and reliability to critical processes. Kudos to Vikram, Vladislav, Alan, and the entire team for their ongoing commitment to excellence. #GenerativeAI #IdentityVerification #SustainedInnovation

76

5 Comments

Check out this highly recommended course for those interested in optimizing their models: - Introduction to Quantization - Symmetric and Asymmetric Quantization Modes - Hands-on Implementation from Scratch using PyTorch - covering Per Tensor, Per Channel (Axis), and Per Group techniques - Weights Packing: Exploring 2 or 4 Bits Quantization Methods https://lnkd.in/gMAuWXHm

43

❝ How do you taste your Wine? With the right Glass, served from the right Bottle. How do you utilize your LLM? With the right Task, served from the right Compute environment. ❞ If the quote above caught your interest, check out my blog post that was featured on the Toyota Connected India Medium channel last week: Leveraging LLMs in Cloud - 🔗 https://lnkd.in/gfHsdevH --- I hope this blog adds a bit of amusement for the seasoned AI/ML engineers 🧠👨‍💻 with the carefully crafted images and perhaps even the silly wine analogies 😉. Whether you're a cloud engineer ☁️ 👨‍💻, a product owner of cloud-based apps, or someone new to Generative AI in the cloud, this blog offers a detailed, beginner-friendly look into the selection and deployment of LLMs in cloud environments. --- A heartfelt thanks 🙏 to my colleagues at Toyota Connected India for taking the time to review, shape this piece and even share a creative writeup like below in the original post 🫡 👇 🤔 Curious to dive in? Click the link below to explore the blog on Medium! 🌐 🔗 https://lnkd.in/gfHsdevH

18

Summarizing my experience working with Vertex AI (Google Cloud) over the last 2-3 weeks! A single offering in Vertex AI is called by many names, just like Indian gods! Unlike gods who will respond by whatever name you call them, Vertex AI offerings don't, no matter which name you use. 😅 The documentation is all over the place but doesn't do anything useful, just like Cred ads! Creating a vector DB for the first time and indexing 5 documents takes 1 hour! A minute in the outside vector DB cloud world is an hour in the Google cloud, reminding me of Interstellar memes. :) And just to make life more complex, someone named a product in Google Cloud as LlamaIndex, similar to the open-source library LlamaIndex? #llms #googlecloud #generativeai #artificialintelligence

159

28 Comments

Join me and our team from Tredence Inc., along with our partner Databricks (Sumit Saraswat & Michael Riley), for a talk on 'Unlocking Financial Insights with LLMs'. The use of #GenerativeAI in finance accelerates insights generation, resulting in cost savings, faster processes, and increased outreach for BFSI firms. By leveraging large language models (#LLMs), private equity, investment, and portfolio management firms can streamline strategies, optimize portfolio performance, and uncover market opportunities, driving greater value for investors and stakeholders. We will explore the future of financial analytics and discover how LLMs are revolutionizing the industry. Register now to secure your spot: Unlocking Financial Insights with LLMs In our session, we will cover: - AI-driven summarization for financial reports in due diligence and investment strategies - Integration with top AI models like OpenAI's GPT, Mistral AI's Mistral, Meta's Llama, and Databricks's DBRX. - Exploring Databricks’ AI capabilities, including governance, vector search, and curated open-source LLMs #FinancialInsights #LLMs #Tredence #Databricks #AI #MachineLearning #DataScience #BFSI #GenerativeAI Arpan Dasgupta Unmesh Kulkarni lakshmikant G. Ashwini Agrawal Zohra Ladha Indranil Bhattacharya Ravindra Patil, Ph.D. Aravind Chandramouli Sagar Balan

70

1 Comment

Very common rookie mistake candidates do while trying to get a job in the data science industry. Having the following 3 projects from #Kaggle in your resume: House Price Prediction Telco Churn Prediction Titanic Problem No, you will not get your resume selected with these projects. I get it. YouTube tutorials suggested doing these projects so you are wondering, “Why aren’t my resume getting picked after I’ve completed them?” Well think about it. As a hiring manager, how do they know you didn’t just copy an existing notebook? You might say, “But they can at least give me a chance to prove my skills!” Again think from their perspectives - What if they do give a chance but you don’t perform up to the mark, that’s valuable time wasted. Now imagine giving that time to all candidates. To really get noticed, work on projects that will show that you’re not just another candidate. And there are ways. Many ways. We will discuss some during https://lnkd.in/gMNckgRi on 14th October, 9pm. #DataScience #DataAnalytics #HiringTips #CareerAdvice #DataJobs #Kaggle #ResumeTips #StandOut #DataProjects #JobSearch #Job

9