What is Knowledge Augmented Generation (KAG)?
Knowledge-Augmented Generation (KAG) is a framework that integrates the structured reasoning of knowledge graphs with the flexible language capabilities of LLMs.
More issues
LLMs in Prod 2025: Insights from 2 Trillion+ Tokens
Real-world analysis of 2Trillion+ production tokens across 90+ regions on Portkey's AI Gateway. Get the full LLMs in Prod'25 report today.
What are AI agents?
AI agents are software programs designed to sense their environment, make decisions, and take actions independently. They can operate and adapt in various settings - from physical spaces to digital environments. Unlike AI models that simply process inputs to generate outputs, agents continuously interact with their surroundings through an ongoing
Jamming on Event-Driven Architecture and MCP for Multi-Agentic Systems
Insights from Portkey's AI Practitioners Meetup on building scalable multi-agent systems. Learn about Event-Driven Architecture patterns, Model Context Protocol implementation, and real-world experiences building multi-agents system.
Reducing AI hallucinations with guardrails
Your chatbot just told a user that Einstein published his Theory of Relativity in 1920. Sounds plausible, right? Except it happened in 1915. This isn't a rare glitch -
A recent study revealed 46% of users regularly catch their AI systems making up facts like these, even with
What are AI guardrails?
Learn how to implement AI guardrails to protect your enterprise systems. Explore key safety measures, real-world applications, and practical steps for responsible AI deployment.
The real cost of building an LLM gateway
When your AI apps start to scale, managing multiple LLM integrations can get messy fast. That's when teams usually realize they need an LLM gateway. Many developers jump straight to building their own solution, often without seeing the full picture of what's involved.
Drawing from what
LLM observability vs monitoring
Your team just launched a customer service AI that handles thousands of support tickets daily. Everything seems fine until you start getting reports that the AI occasionally provides customers with outdated policy information. The dashboard shows the model is running smoothly - good latency, no errors, high uptime - yet
Multi-LLM Text Summarization
The paper introduces a novel framework called Multi-LLM for text summarization, which leverages multiple large language models (LLMs) to generate better summaries, especially for long documents. This framework is designed to overcome the limitations of using a single LLM, which might fail to captur
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference - Summary
<p>The research paper introduces <strong>ModernBERT</strong>, an updated version of the original BERT model, which is an encoder-only transformer designed to improve retrieval and classification tasks. Despite the original BERT's widespread use, until now, there have been limited improvements in te