Articles for category: AI Tools

March 13, 2025

ikayaniaamirshahzad@gmail.com

How to Build a RAG System Using LangChain, Ragas, and Neptune

LangChain provides composable building blocks to create LLM-powered applications, making it an ideal framework for building RAG systems. Developers can integrate components and APIs of different vendors into coherent applications. Evaluating a RAG system’s performance is crucial to ensure high-quality responses and robustness. The Ragas framework offers a large number of RAG-specific metrics as well as capabilities for generating dedicated evaluation datasets. neptune.ai makes it easy for RAG developers to track evaluation metrics and metadata, enabling them to analyze and compare different system configurations. The experiment tracker can handle large amounts of data, making it well-suited for quick iteration and

March 12, 2025

ikayaniaamirshahzad@gmail.com

Unlocking the Power of Customer Feedback Analysis in Retail with Databricks AI Functions

In today’s dynamic retail environment, staying connected to customer sentiments is more crucial than ever. With shoppers sharing their experiences across countless platforms, retailers are inundated with feedback that holds the key to enhancing products, services, and overall customer satisfaction. But sorting through this tidal wave of unstructured data can feel like searching for a needle in a haystack. That’s where Databricks AI functions come in. This cutting-edge solution equips retailers with the tools to transform raw customer feedback into actionable insights. By harnessing the power of advanced language models and SQL-based functions, Databricks streamlines the process of analyzing reviews,

March 12, 2025

ikayaniaamirshahzad@gmail.com

NVIDIA L40S GPUs are here

Today we added NVIDIA L40S GPUs to our supported hardware types. These new GPUs are around 40% faster than A40 GPUs. We’re also going to be removing support for A40 GPUs. We will begin migrating all existing models and deployments from A40 GPUs to L40S GPUs over the coming weeks. You’ll continue to pay the same price for your private models and deployments, but you might pay more if you’re using public models or training models on A40 GPUs. You can now run L40S GPUs for any new models, existing models, or deployments. To learn how to change the hardware

March 12, 2025

ikayaniaamirshahzad@gmail.com

CODEGEN: A Transformative Open-Source Language Model for Versatile Program Synthesis

With the rise of large language models (LLMs), we are thinking and approaching things differently for many tasks, from natural language processing and text generation to programming. From OpenAI’s GPT-3 and GPT-4 to Anthropic Claude, Google’s PaLM, and Apple’s Certainly, we are in a post-LLM era. One of the most exciting tools is an open-source LLM for program synthesis that’s democratized everyone’s access to coding. It’s called CODEGEN. CODEGEN has been created by the Salesforce Research team. in this article, we will explore its capabilities and implications for the future of programming. To understand the concepts in this article, familiarity

March 12, 2025

ikayaniaamirshahzad@gmail.com

LangMem SDK for agent long-term memory

Today we’re releasing the LangMem SDK, a library that helps your agents learn and improve through long-term memory. It provides tooling to extract information from conversations, optimize agent behavior through prompt updates, and maintain long-term memory about behaviors, facts, and events. You can use its core API with any storage system and within any Agent framework, and it integrates natively with LangGraph’s long-term memory layer. We are also launching a managed service that provides additional long-term memory results for free – sign up here if you are interested in using it in production. Our goal is to make it easier

March 12, 2025

ikayaniaamirshahzad@gmail.com

We Tried OpenAI’s New Agent—Here’s What We Found

Sponsored By: Learn how to do the best writing of your life—with AI How to Write With AI is a course taught by Every lead writer Evan Armstrong. You’ll learn how to use AI tools like ChatGPT, Claude, Spiral, and Lex to transform blank pages into powerful content that resonates across the internet. The four-week cohort-based class runs from Feb. 13 through Mar. 6 and includes: Live lectures and hands-on workshops A writing group overseen by an Every-trained editor Interviews with successful internet writers including Every CEO and cofounder Dan Shipper 30 days of quick writing exercises Your own customized LLM prompt for improving

March 12, 2025

ikayaniaamirshahzad@gmail.com

America Is Missing The New Labor Economy – Robotics Part 1 – SemiAnalysis

SemiAnalysis is hosting an Nvidia Blackwell GPU Hackathon on Sunday March 16th. It is the ultimate playground for Blackwell PTX tech enthusiasts, offering hands-on exploration of Blackwell & PTX infrastructure while collaborating on open-source projects. Speakers will include Philippe Tillet of OpenAI, Tri Dao of TogetherAI, Horace He of Thinking Machines, and more. Sponsored by: Together, Lambda, Google Cloud, Nvidia, GPU Mode, Thinking Machines, OpenAI, PyTorch, Coreweave, Nebius. Apply to be part of the fun. This is a Call for Action for the United States of America and the West. We are in the early precipice of a nonlinear transformation in

March 12, 2025

ikayaniaamirshahzad@gmail.com

OpenAI Agents SDK

OpenAI Agents SDK. OpenAI’s other big announcement today (see also) – a Python library (openai-agents) for building “agents”, which is a replacement for their previous swarm research project. In this project, an “agent” is a class that configures an LLM with a system prompt an access to specific tools. An interesting concept in this one is the concept of handoffs, where one agent can chose to hand execution over to a different system-prompt-plus-tools agent treating it almost like a tool itself. This code example illustrates the idea: from agents import Agent, handoff billing_agent = Agent( name="Billing agent" ) refund_agent =

March 12, 2025

ikayaniaamirshahzad@gmail.com

Get started with our Crash Course

Deephaven is a full-stack live data framework that Wall Street analysts, machine learning engineers, data scientists, and many other professionals rely on for data analysis and transformation. Whether you’re creating Bollinger bands to analyze financial instruments, conducting research that requires transforming large amounts of data, or building a machine learning model, Deephaven can streamline and empower your workflow. Deephaven is fast, efficient, versatile, and easy to use – and with the release of our new Crash Course and demo notebooks, it’s never been easier to learn than now. Deephaven’s new Crash Course is available for both Python and Groovy users.