Hello Everyone, my name is Anirudh & I lead Revenue at Lyzr.ai We help enterprises build Gen AI Apps in minutes using our tech privately on their cloud. Would love to connect with folks who are developing interesting use cases using AI in their industry. We are hosting a webinar on "The Enterprise Gen AI Stack" It's on Jan 24th, Wed at 8:30 PM IST (10 AM EST) & it's on Linkedin live. We'll cover ---> 1) How to sell to Gen AI to Enterprises (Who to speak to) 2) What they care about (Privacy, Data, AI safety standards, time taken) 3) What does implementation look like 4) The Tech stack (LLMs, Vector DBs, Cloud, Data sources) If anyone is interested, please sign up. https://lnkd.in/g4HM8giv The session won't be recorded & it would be for 30-40 minutes. #GenAIstack #Enterprise

Hey folks! Wrote about building enterprise data pipelines with Hamilton — its a pretty in-depth post. Hoping it gives you some inspiration! https://blog.dagworks.io/p/enterprise-ready-data-pipelines-with

Anyone want a lighter-weight experiment tracker than MLFlow and Weights & Biases that you can host yourself? Well we’ve got one — written by a Master’s student to more easily track code and results and it’s using FastAPI and FastUI. https://blog.dagworks.io/p/building-a-lightweight-experiment?r=2cg5z1&utm_campaign=post&utm_medium=slack

Here’s my 2¢ about AI impact on society and what we can do about it:

Are you a platform person? Do you know what a Jupyter Magic is? Did you know you could push your MLOps and LLMOps concerns inside one and improve the experience of a notebook user? Have a piqued you interest? I have a blog post for you! https://blog.dagworks.io/p/using-ipython-jupyter-magic-commands?r=2cg5z1&utm_campaign=post&utm_medium=web

What is it: A Cloud Platform for GPU & CPU & Storage Who is it for: Machine learning engineers, AI engineers, Data engineers Why is it relevant: Easy to use interface, Cuts AI operational costs by 50%, uses powerful RTX 4080 + 4090, and speeds up inference time. Link: https://nodeshift.com/

Attention Data Scientists, ML Engineers, Data Engineers and Data architects! 📣 We're writing an O'Reilly ebook on how to build ML systems with a feature store and are proud to share access to the first chapter. The first chapter gives you an unfiltered introduction to ML systems where you will: • Learn how to build 3 types of ML systems in a unified architecture: Batch, Real-TIme, and LLMs. • Learn about real-world applications in batch, real-time and LLM machine learning systems. Access the chapter below ⬇️ https://bit.ly/49Tz0cO

Hi all, Serverless Toronto is hosting a unique online event with Jerry Liu (creator of LlamaIndex) and Mark Ryan (Google AI Lead) to dive deep into advanced RAG pipelines and the LLM landscape. It's an ideal opportunity for IT professionals aiming to pivot their careers towards Generative AI. Expect interactive Q&A to enrich your understanding. You're warmly invited: https://www.meetup.com/serverless-toronto/events/299524579/ 🤓

Are you processing documents for RAG? How happy are you with your code and that system? If you aren’t happy, or want to see another take then I wrote a blog post on how to write one with Hamilton (it’s easy) and then scale it onto Ray, Dask, or PySpark. https://blog.dagworks.io/p/rag-ingestion-and-chunking-using?r=2cg5z1&utm_campaign=post&utm_medium=web

Hey everyone! Would love to share about the product we are building at QueryPal. It’s an AI assistant on Slack that can help you handle your fragmented knowledge across tools like Notion, confluence, GoogleDrive and Jira. We aim to help you never answer the same question again by searching across all your tools. You can try it out at https://www.querypal.com/. Install it and let me know if you have any questions or comments.

Are you thinking about building apps with LLMs inside? We’ve got a new framework for you! Introducing Burr - https://blog.dagworks.io/p/burr-develop-stateful-ai-applications It’s an OS white-box framework with an open source telemetry UI to help you build, debug, and ship faster. Would love you to bookmark the repo too!

I’m looking for contributors! https://github.com/shure-dev/Awesome-LLM-related-Papers-Comprehensive-Topics

Want a fun example of using GenAI to create some cool images? Checkout our write up about playing Telephone with GenAI. Links to code and images included! 😄 https://blog.dagworks.io/p/playing-telephone-with-chatgpt-and?r=2cg5z1&utm_campaign=post&utm_medium=web

Anyone here have to inherit Data Science work? Do you enjoy it? (Probably not 😉 ) Why not send this blog post to them that can help both of you. https://blog.dagworks.io/p/structuring-your-data-analysis-with?r=2cg5z1&utm_campaign=post&utm_medium=web

@channel Call for papers at International Workshop on LLM+KG: Data Management Opportunities in Unifying Large Language Models + Knowledge Graphs (https://seucoin.github.io/workshop/llmkg/) In conjunction with the VLDB 2024, the 50th International Conference on Very Large Databases, Guangzhou, China, August 25, 2024 Overview: --------- Large Language Models (LLMs), e.g., ChatGPT and LLaMA are revolutionizing the fields of artificial intelligence and natural language processing (NLP). Recent LLMs browse Web knowledge and learn from external sources, warranting the coupling of knowledge graphs (KGs) and LLMs. The possibility of bridging KGs with LLMs has attracted increasing interest in the area of knowledge engineering. On one hand, LLMs can be enhanced with KGs to provide answers with more contextualized facts. On the other hand, downstream tasks, e.g., KG curation, embedding, and search can also benefit by adopting LLMs. It remains an interesting direction to explore effective interactions between LLMs and KGs, where many recent advances come from deep learning, information retrieval, NLP, and computer vision domains. The workshop, titled “LLM+KG: Data Management Opportunities in Unifying Large Language Models + Knowledge Graphs”, is targeted for data management researchers, aiming to discuss interesting opportunities such as data cleaning, modeling, designing of algorithms and systems, scalability, fairness, privacy, usability, explainability, and etc. We solicit unpublished papers discussing issues and successes under the broad category of LLM-enhanced KGs, KG-enhanced LLMs, and unifying LLMs + KGs in the following areas (and beyond): - KG-enhanced Pre-training of LLMs - KG-enhanced Fine-tuning of LLMs - KG-enhanced Inference of LLMs - KG-enhanced Validation and Explainability of LLMs - LLM-enhanced KG Creation - LLM-enhanced KG Completion - LLM-enhanced KG Embedding - LLM-enhanced KG Querying - LLM-enhanced KG Analytics - LLM-enhanced Domain-specific KG Applications Additionally, the paper must have a clear data management focus, e.g., discussing data management solution(s) such as (but not limited to): - Data and Input Modeling for LLMs+KGs - Data Cleaning, Integration, and Augmentation with LLMs+KGs - Multi-modal Data Management with LLMs+KGs - KG-enhanced Validation and Explainability of LLMs - Vector Data Management for LLMs+KGs - Accuracy and Consistency of LLMs+KGs - Efficiency and Scalability of LLMs+KGs - Bias and Fairness with LLMs+KGs - Explainability and Provenance of LLMs+KGs - Usability of LLMs+KGs - Security and Privacy for LLMs+KGs - Optimizing KG Databases and Systems with LLMs - Empirical Benchmark and Ground Truth in Emerging Applications with LLMs+KGs Paper Format, Submission, and Reviewing --------------------------------------- We solicit three types of papers. Survey Papers/Tutorials: these papers survey the related work in specific sub-areas and lay out the agenda for future work. New/ Late-breaking Results: these papers report the newest preliminary results about the most promising problems in the field. Vision Papers: these papers are devoted to discussing problems that we face currently and anticipate for the future. We welcome the papers that fall under short papers of at most 9 pages and long papers up to 18 pages, including bibliography. Submissions must adhere to CEUR-WS formatting guidelines with 1-column style available at: http://ceur-ws.org/Vol-XXX/CEURART.zip . An Overleaf page for LaTeX users is available as template at https://www.overleaf.com/read/xztwvxtwbzrn#ac9ca2 . All submissions must be submitted in PDF through: https://cmt3.research.microsoft.com/LLMKG2024/. Submissions will be reviewed in a single-blind manner, and all author names and affiliations should be included. Papers that do not follow the guidelines or are not within the scope of relevant topics will be desk rejected. We also expect that publications from DB venues, e.g., SIGMOD/VLDB/ICDE/EDBT etc. are cited. Submissions will be reviewed by at least three members of the Program Committee. All accepted papers will be published online via CEUR-WS https://ceur-ws.org/ . The workshop will be in-person and at least one author of each accepted paper is required to register. Best papers will be invited to submit extensional versions to the special issue: Neuro-Symbolic Intelligence: Large Language Model Enabled Knowledge Engineering in the World Wide Web Journal ( https://link.springer.com/journal/11280/updates/26763530 ). Dates ----- Submissions must be received by the deadline below. - Paper submission deadline: May 15, 2024 (11:59 PST) - Notification of acceptance: June 20, 2024 - Camera-ready version due: July 20, 2024 - Workshops at VLDB 2024: August 25, 2024 Workshop Co-Chairs: ------------------- - Arijit Khan, Aalborg University (Denmark) ( https://homes.cs.aau.dk/~Arijit ) arijitk@cs.aau.dk - Tianxing Wu, Southeast University (China) ( https://tianxing-wu.github.io/ ) tianxingwu@seu.edu.cn - Xi Chen, Tencent (China) ( https://hualichenxi.github.io/ ) jasonxchen@tencent.com

Hello, Good Noon Team, 👋 Do you need to be a coding genius to use AI tools? Not at all! 👇 Check out this list of AI tools that will help you be the super-human 🦸‍♂️🦸‍♀️ https://www.linkedin.com/pulse/best-ai-tools-developers-2024-toolplate-glpvc?utm_source=share&utm_medium=member_android&utm_campaign=share_via Show your love with Likes, Comments, and Shares! 👍

Hello Good Noon, Team 👋 🚀 Curious about starting your own software company with minimal risk? Dive into the world of Micro SaaS. Start learning today and turn your vision into reality! 👇 https://medium.com/@toolplate.ai/jumpstart-your-startup-with-these-cool-micro-saas-ideas-409928719d10 Show your love with Likes, Comments, and Shares! 👍

Hey all. We just open sourced a UI to help with introspection & management of python based pipelines! Are you looking for MLOps/LLMOps solutions that cover one or more of the following: • versioning • lineage & provenance • a catalog to display: feature, data set, model, general artifacts, etc • execution observability: how long things took by function, what data was produced so you can compare/debug, pinpointing errors quickly… Then we have a solution that has it all! Read our blog or watch our .

Hello Good Noon, Everyone 👋 Struggling to find the perfect free AI art tools to unleash your creativity? But don’t worry! Check out some excellent free AI art tools that are user-friendly, capable of producing stunning artwork, and best of all, completely free. 👇 https://medium.com/@toolplate.ai/7-best-free-ai-art-generators-you-can-use-right-now-f52e6916b5cb Show your love with Likes, Comments, and Shares!

Hello Good morning, Team 👋 Do you know? According to a recent survey, 70% of GenZ and 82% of Millenials said that AI tools can actually help them in their career growth. Let’s explore top AI tools and discover how AI can unlock new opportunities, supercharge your skills, and move your career to new heights! 👇 https://www.linkedin.com/pulse/unlocking-success-best-10-ai-tools-career-toolplate-lld4c?utm_source=share&utm_medium=member_android&utm_campaign=share_via Show your love with Likes, Comments, and Shares👍

Hello Good Morning, Team! 🌞 Did you know? Most of teachers believe that AI tools not only streamline their workload but also enhance the learning experience for their students. Dive into our latest blog post to uncover the top AI tools every teacher should know about! Discover how these tools can revolutionize your teaching methods, save time, and help you provide a more engaging learning environment for your students! 📚🤖 Elevate your teaching with AI—start today! 👇 https://medium.com/@toolplate.ai/teaching-made-easy-top-10-ai-tools-every-teacher-needs-to-know-6d88955731a7 Show your support with Likes, Comments, and Shares! Let's empower more educators together! 💬👍🏽

Hello Good morning, Team 👋 Data, data everywhere, but not a drop of insight? In this digital world where data isn't just part of the business; it's the core of every strategic decision. Explore the top AI tools that are essential for data analysts in today’s world, offering you a pathway to utilize the full potential of your data. 👇 https://www.linkedin.com/pulse/best-ai-tools-data-analysts-essential-guide-toolplate-o1g9c Show your love with Likes, Comments, and Shares! 👍

Want to see how you can build most of a RAG system using entirely open source projects? Then I have a google collab notebook and blog post for you! It’s on building an NER powered semantic search pipeline using HuggingFace data & models, Hamilton, and LanceDB, i.e. the part that you’d query for context to put into a prompt for RAG. What’s shown here is generally applicable to any search using text and vector embeddings.

check out brieflyai.com/success

Do you use Kedro? Would you like to track and see a lot more about the project? Well now you can use Hamilton to run it and plug it into the self-populating catalog, observability, and lineage that comes with the Hamilton UI. Best part: this is all open source!

hello there! 👋 check out my blog on guided LLM generation techniques it covers regular expressions, JSON schemas, context-free grammars, templates, entities, and structured data generation would love to hear your thoughts!

Doing RAG but curious about GraphDBs? Have I got a post for you! In it I explain: • what a graphdb is — using FalkorDB as an example ◦ go over the cypher query language that’s required to query it. • then talk about how you can build a full RAG system that you could take to production going over ingestion through to inference with an agent; Hamilton for ingestion, Burr for the agent.