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

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

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 article shares a workflow for making slide decks with Overleaf and ChatGPT. It solves issues like slow content creation using ChatGPT and formats with Overleaf’s themes. It includes examples, tips, and a Dify automation for engineers.

Create slides with Overleaf and ChatGPT

Discover how our two-week MVP harnesses AI-driven, real-time voice processing to streamline interviews, reduce bias, and accelerate hiring success

Building MVP for AI-driven interview platform

Explore Anthropic's Model Context Protocol (MCP) - a groundbreaking approach to enhancing AI assistants. Learn how MCP integrates with local and remote resources, enabling smarter interactions with tools and databases.

Intro to Model Context Protocol

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

Stay updated on the latest in AI tools for developers with this week’s digest, new command Aider, OpenHands, Qwen2.5 Coder 32B

AI digest #2 New command Aider, OpenHands, Qwen2.5 Coder 32B, Predicted Output

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

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

Salesforce is taking AI to the next level with large language models that make customer service smoother, sales more strategic, and insights faster. By automating routine tasks, these tools free up teams to focus on real connections with customers. The result? Happier customers, smarter sales, and big wins for businesses.

Salesforce use cases

Stay updated on the latest in AI tools for developers with this week’s digest, featuring Cline's v2.0.0 update, OpenAI’s Realtime API, and Aider’s Architect/Editor split for enhanced coding workflows.

AI digest #1 Aider reasoning, OpenAI Realtime API, Cline - pre Claude-dev 

In an age where Large Language Models like ChatGPT offer instant access to a universe of information, it raises the question, does our own personal knowledge base still hold any value, and is building a personal knowledge base still a legitimate thing to do?

Build your knowledge base

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

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

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

Yelp already had a machine learning platform before the big push for large language models (LLMs). Now, they’re using LLMs to level up their search and recommendation systems, making it easier for moderators and businesses to track down users. Let’s dive into how Yelp is making it work.

Yelp use cases

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

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

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

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

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

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.

Use cases for LLM applications

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

A scathing look at Go's compiler internals and the vector search gold rush, exposing the industry's obsession with speed over substance

#13 Compiler Quests and Vector Vexations

Go Commentary #13: Compiler Quests and Vector Vexations

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

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

A critical examination of Go's resurgence in CLI tool development, exploring recent projects in Kubernetes log viewing, REST API interaction, and terminal-based readers, while questioning the industry's shift back to command-line interfaces.

#12 CLI Tools for K8s, REST, and Terminals

Go Commentary #12: CLI Renaissance with Kubernetes, REST, and Terminal Readers in the Age of Complexity

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 map of content (MoC) outlines the critical components required to design and build a large language model (LLM) system, focusing on architecture, model customization, safeguarding, performance evaluation, and more.

§ Building LLM system

Journey of Thought Prompting is an innovative technique that leverages AI to craft more effective prompts for large language models. This approach uses the analytical capabilities of AI assistants to help users create detailed system prompts, fill in missing details, and iteratively refine their prompt engineering skills. It represents a shift towards collaborative AI interaction, enhancing problem-solving capabilities for businesses and engineers.

Journey of Thought Prompting: Harnessing AI to Craft Better Prompts

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

LLM tracing in AI system

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

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

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?

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

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

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

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

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 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

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

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

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

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

Developing rapidly with Generative AI

An overview of Open Assistant, an open-source chat-based AI assistant, and its implementation of Reinforcement Learning from Human Feedback (RLHF). This article covers the three-step process of RLHF, system requirements, and detailed setup instructions for training the model using Supervised Fine-Tuning, Reward Modeling, and Reinforcement Learning.

RLHF with Open Assistant

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

An overview of adversarial prompting in prompt engineering, focusing on understanding risks associated with Large Language Models (LLMs) and strategies for mitigating them.

Adversarial Prompting in Prompt Engineering

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 self-refinement, a technique where Large Language Models (LLMs) evaluate and improve their own output without the need for supervised data or reinforcement learning.

LLM's Accuracy - Self Refinement

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

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

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

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 guide on how to build a personal AI chatbot using open-source Large Language Models (LLMs) like Alpaca and GPT4All on your personal computer.

Build your chatbot with open source Large Language Models

This article explores strategies to overcome OpenAI's token limit using Langchain, including stuffing, map-reduce, refining, and map-rerank methods. It discusses the advantages and drawbacks of each approach in handling large documents or prompts while working within the constraints of OpenAI's API.

Workaround with OpenAI's token limit with Langchain

This article explores Langchain document loaders, explaining their role in overcoming token limits, integrating with vector databases, and demonstrating how to build a question-answering system using CSV data and an AI agent.

#LLM

A

B

C

D

E

F

G

H

I

J

L

M

N

O

P

Q

R

S

T

U

W

Y

§