An exploration of the cyclical nature of AI development, tracing the rise and fall of new technologies within the field, and how this pattern has repeated throughout history.

A grand unified theory of the AI hype cycle

Discover how managed LLMOps platforms like Dify streamline the development of AI-powered internal tools. Learn about the challenges of integrating LLMs, the benefits of managed solutions, and real-world examples of efficient AI tool creation. Perfect for businesses looking to enhance productivity with AI without extensive technical expertise.

Streamlining internal tool development with managed LLMOps: A Dify case study

Caching is a vital technique that boosts performance by storing frequently accessed information. Let's see how it works with RAG. In this article, we will know how cache could be implement in RAG system.

Evaluating caching in RAG systems

This article explores chunking strategies to handle context limitations in Large Language Models (LLMs) like GPT. It covers preprocessing data, selecting chunk sizes, and how to maintain coherence in various content types such as unstructured, Markdown, and LaTeX.

Chunking strategies to overcome context limitation in LLM

An overview of how to implement long-term memory in a ChatGPT-based chatbot using a Vector Database (VectorDB) to store conversation history and retrieve the most relevant past interactions.

Storing long-term memory in ChatGPT using VectorDB

Generative AI overview and the different stages of building an LLM-powered feature

Developing rapidly with generative AI

When building a chatbot agent, it's important to evaluate its performance and user satisfaction. One effective method is user simulation, which involves creating virtual users to interact with the chatbot and assess its responses. This approach allows for a more realistic evaluation of the chatbot's capabilities and user experience.

Evaluate chatbot agent by user simulation

This guide offers a structured approach to evaluating and optimizing the integration of third-party Large Language Models (LLMs) into applications, ensuring alignment with business goals and user needs through detailed checklists and evaluation metrics.

Evaluation guidelines for LLM applications

Improving AI models requires collecting accurate user feedback,which can be difficult. The article explores more into the importance of collecting human feedback and discusses the need for creating an organized database to effectively store and use this valuable input. We hope to continuously improve our large language models, ensuring they deliver greater performance and match user expectations more effectively.

Design feedback mechanism for LLM applications

An overview of foundation models, their versatility in generative AI tasks, and their impact across various domains like NLP, image generation, and scientific research. The article highlights the benefits, challenges, and future potential of these models.

Foundation models: the latest advancement in AI

Function calling is a critical component in the architecture of AI agents, facilitating the integration of external functionalities and resources. This note explores how function calling is implemented in AI architectures and its role in enhancing agent capabilities

Function calling in AI agents

An introduction to Generative UI (genUI), a user interface that generates interactive elements in response to user needs using AI, enhancing UX in chat applications. The article explores examples, benefits, and popular solutions like the Vercel AI SDK for implementing generative UI.

What is Generative UI?

In baseline Retrieval Augmented Generation (RAG), sometimes the result might not be accurate as expected since the query itself have multiple layers of reasoning or the answer requires traversing disparate pieces of information through their shared attributes in order to provide new synthesized insights. In this post, we will explore a new approach called GraphRAG which combines the strengths of knowledge graphs and large language models to improve the accuracy of RAG systems

GraphRAG - building a knowledge graph for RAG system

Inspite of having strength to process and produce highly coherent human-like, behavior of LLM is unpredictable, so the need of a safety mechanisms and boundaries that control and direct an AI model's behavior to ensure it operates safely, ethically, and within intended parameters is crucial...

Guardrails in llm

When Large Language Models (LLMs) becomes popular and an essential tool for growing businesses, it signals a transition toward more complex and efficient data processing. Instead of outputting raw text, the models may now generate structured data in formats such as JSON or XML. This allowed the information to be directly integrated into company databases, removing the need for human processing. Businesses can use structured outputs to streamline their data workflows, decrease processing time, and improve the accuracy and reliability of their analytics.

History of structured outputs for LLMs

This post presents technique to improve the your output when prompting ChatGPT.

How to talk to ChatGPT effectively

Hybrid search comes to solving problems in vector search and full-text search. Let's see how it works. In this article, we will know how hybrid search approach and how to evaluate each search method through metrics in information retrieval.

Evaluating search engine in RAG systems

User intent classification is a crucial aspect of conversational AI, start with machine learning models, but now advanced language models (LLMs) are being explored for this task. Unlike the old methods which is need to labeled datasets exhaustively, LLMs can understand what users mean without all that preparation. This memo explores the application of LLMs in intent classification, highlighting their potential to streamline the process and overcome traditional NLU limitations.

Intent classification by LLM

With the robust growth of LLM models currently, there is a new method is used to evaluate the performance of large language models (LLMs): LLM-as-a-Judge, also known as LLM-evaluators. This approach take adavantages of other advanced language models to assess the quality and effectiveness of responses generated by other LLMs.

LLM as a judge

An exploration of query caching in Large Language Models (LLMs), focusing on how semantic vector databases can drastically improve efficiency and reduce computational costs by reusing cached answers for semantically similar queries.

Query caching for large language models

Understanding LLM Tracing - Principles, Techniques, and Applications in building LLM-powered AI systems.

LLM tracing in AI system

Logs are like the footprints of your LLM, tracking every move it makes. We will look at how logging can help you see beneath the top layer of a system, which can help you troubleshoot problems and better understand the system behavior.

Logging

Metrics give you the rundown on how your LLM’s performing. We will show how to use these metrics to identify issues, increase efficiency, and make changes for improved outcomes.

Metrics

Learn how to choose the right AI model for your needs. Explore key factors like accuracy, privacy, and cost. Compare commercial vs open-source options and API vs self-hosting approaches.

Model selection

In AI integrated systems, instead of put all workload on a single agent, we can apply divide and conquer strategy to distribute workload to multiple agents. This approach can enhance task completion by leveraging the unique skills and capabilities of each agent.This approach allows for more complex and nuanced problem-solving, as well as increased efficiency and scalability. By coordinating and communicating effectively, agents can work together to achieve common goals, divide labor, and overcome challenges that a single agent might face alone

Multi-agent collaboration for task completion

In spite of having taken the world by storm, Large Language Models(LLM) still has some limitations such as limited context window and a knowledge cutoff date. Retrieval-Augmented Generation(RAG) steps in to bridge this gap by allowing LLMs to access and utilize external knowledge sources beyond their training data. However, data is not text based only, it also can be image, audio, table in docs,...

Multimodal: in rag

Observability in AI is all about understanding what’s going on inside complex systems. It gives you the tools - logs, metrics, and traces - to monitor, troubleshoot, and optimize how AI models and services run.

Observability in AI platforms

Nowadays, Large Language Models (LLMs) have become integral to various applications. However, with great power comes great responsibility, and the rise of LLMs has introduced new security challenges. One such challenge is prompt injection attacks, a sophisticated technique that can manipulate AI systems to perform unintended actions. In this article, we'll dive deep into the world of prompt injection, understand its implications, and explore strategies to prevent these attacks.

Prevent prompt injection

Proximal policy optimization (PPO) is an algorithm that aims to improve the stability of training by avoiding overly large policy updates. It is a popular and effective method used for training [ reinforcement learning]() models in complex environments. To achieve this, PPO uses a ratio that indicates the difference between the current policy and the old policy and clips this ratio within a specific range, ensuring that the policy updates are not too large and the training process is more stable...

Proximal policy optimization

An introduction to Q-learning, a model-free reinforcement learning algorithm used to learn optimal policies in Markov Decision Processes.

Q learning

As large language models (LLMs) continue to evolve, their parameter counts grow exponentially, with some models reaching trillions of parameters. This exponential growth presents significant challenges for deployment on edge devices and in resource-constrained environments due to extensive memory and computational requirements. Quantization emerges as a crucial technique to reduce model footprint while preserving acceptable performance.

Quantization for large language models

An overview of RAPTOR, a novel approach for improving retrieval-augmented language models for long documents using hierarchical tree summaries.

RAPTOR: Tree-based retrieval for language models

Re-ranking is a crucial step in Retrieval-Augmented Generation (RAG) systems that addresses the challenge of retrieving heterogeneous and potentially irrelevant information. By evaluating and re-ordering retrieved documents, re-ranking ensures that only the most relevant and useful information is passed to the generation model. This process significantly improves the coherence, accuracy, and relevance of the generated text, ultimately enhancing the reliability and effectiveness of RAG systems.

Re-ranking in RAG

Working with Large Language Models (LLMs) may seem straightforward at first glance. Initially, we might think that simply prompting the AI model with a task is sufficient for it to assist us. However, when faced with more complex tasks, we need to break down the problem into smaller sub-tasks and guide the AI model to solve them sequentially. This is where the ReAct approach comes into play.

ReAct(reason + act) in LLM

An introduction to Reinforcement Learning (RL), a machine learning method where an agent learns to make decisions by interacting with an environment. This article covers the basics of RL, including how it works, common algorithms, and its application in training models with Large Language Models (LLMs).

Introduction to reinforcement learning and its application with LLMs

A Reward model is a critical component in Reinforcement Learning for Large Language Models (LLMs), designed to evaluate and score the quality of generated responses. It plays a key role in aligning LLMs with human values and improving their output through iterative refinement.

Reward model

In the process of improving Large Language Model (LLM) performance, many techniques have been proposed. The Augmented Language Model (ALM) approach boosted LLM accuracy by enabling the attachment of external sources to enhance the model's knowledge. However, ALMs still had limitations in terms of time consumption and token resources. To address these issues, ReWOO was developed as a more efficient solution.

ReWOO: Reasoning without observation - a deeper look

An overview of vector databases and their application in LLM systems. This article covers the history and core concepts of vector databases, their use cases, implementation considerations with LLMs, and a comparison of popular vector database options.

Select vector database for LLM

A comprehensive guide outlining the journey for engineers developing applications on top of Large Language Models (LLMs), covering key stages from understanding AI basics to fine-tuning models.

Story map for LLMs

In the rapidly evolving field of artificial intelligence, the concept of agent supervisors has emerged as a powerful approach to orchestrating multiple AI agents for complex tasks. This article explores how building agent supervisors can lead to generating valuable insights, with a focus on a practical implementation in a Discord bot.

Building agent supervisors to generate insights

An exploration of natural language to database query systems using MongoDB, examining system prompts and implications for data engineering and agentic workflows.

Natural language to database queries: Text-to-MongoDB

Discover how the rapid surge in artificial intelligence, led by models like ChatGPT, Claude, and Gemini, is reshaping industries and democratizing AI development. This article explores the rise of model-as-a-service, the economic impact of AI, and how accessible APIs are transforming productivity, creativity, and innovation across sectors.

The rise of AI applications with LLM

The article talks about how important human feedback is for making large language models better, especially using thumbs up and down. It explains the Pearson correlation coefficient, which measures how variables are related. The thumbs system is an easy way for users to show if responses are helpful or not, which encourages more feedback and keeps users engaged. This feedback helps improve training data and makes the models more accurate. The article includes examples in sentiment analysis for reviews and content moderation, showing how this feedback helps understand user opinions and filter out bad content on sites like YouTube and Twitter.

Thumbs up and thumbs down pattern

Tracing is like following your LLM’s journey, step by step. We will explain how tracing makes it easy to identify and address problems by allowing you to track the entire process.

Tracing

Explore the diverse applications of large language models (LLMs) and AI in both enterprise and consumer sectors. Learn about key use cases across data analysis, content creation, healthcare, education, and more.

Topics > LLM

2024

November (3 posts)

October (12 posts)

September (5 posts)

August (3 posts)

July (8 posts)

June (4 posts)

May (1 posts)

2023

August (1 posts)

July (2 posts)

June (4 posts)

May (2 posts)