This article explains how to construct a Retrieval‑Augmented Generation pipeline in Rust, covering knowledge‑base creation with Qdrant, model loading and embedding generation using candle, and integrating a Rust‑based inference service to answer queries with up‑to‑date external data.
This article provides a comprehensive, experience‑driven guide to supervised fine‑tuning (SFT) of large language models, covering special tokens, latency considerations, data diversity and production, training frameworks and hyper‑parameters, over‑/under‑fitting diagnostics, and evaluation metrics such as helpfulness, honesty, and harmlessness.
The author speculates on OpenAI’s o1 architecture, proposing that it relies on reinforcement learning guided by a generalizable, process‑supervised reward model, and outlines data collection, multi‑model generation, and training tweaks needed to realize such a system.
The author reviews Google NotebookLM, describing how it aids deep paper reading, boosts chat willingness with guided prompts, maintains conversation coherence through self‑play insights, highlights the audio‑overview feature, and reflects on AI concepts such as the "bitter lesson" and the limits of self‑play in open scenarios.
Using an LLM-powered IDE, the author built a full‑stack weekend project without writing a single line of code, discovering faster development cycles, new debugging habits, and the strengths and limits of AI assistants compared to traditional Google searches.
This article explains how to set up a lightweight local AI Q&A system using Java, LangChain (and LangChain4J), Ollama for LLM inference, embedding techniques, and a vector database (ChromaDB), covering core concepts, environment preparation, Maven dependencies, and sample code.
This article walks through building a local AI question‑answer system using Java, Ollama, LangChain4J, embeddings, and a Chroma vector database, covering LLM fundamentals, embedding techniques, RAG architecture, setup steps, Maven dependencies, and sample code to retrieve and answer queries.
This article provides a detailed technical analysis of OpenAI’s o1 model, exploring its enhanced logical reasoning, the likely use of reinforcement learning with hidden chain‑of‑thought generation, multi‑model architecture, training data pipelines, reward modeling, and how these innovations could reshape AI safety and scaling strategies.
This article details Huolala's exploration of large‑language‑model (LLM) based AI assistants across multiple business scenarios, describing their architecture, implementation challenges, prompt engineering techniques, and the progressive stages from professional assistants to multi‑agent systems that drive efficiency and innovation in logistics.
This article analytically reconstructs OpenAI o1’s architecture, training pipeline, and inference workflow, exploring its reinforcement‑learning‑enhanced hidden chain‑of‑thought, multi‑model composition, scaling laws, reward modeling, and potential implications for future AI safety and small‑model strategies.
This article explains how the Volcano Engine DataLeap team leveraged large‑language models to build the “Find Data Assistant”, detailing its design, challenges, embedding‑and‑reranker enhancements, LLM‑driven semantic search, mixing architecture, and practical lessons for improving data asset management and retrieval.
This article explains how to extend large language models with domain‑specific knowledge using Retrieval‑Augmented Generation (RAG) in LangChain4j, covering the concepts of RAG, its indexing and retrieval stages, simple RAG setup, detailed API usage, and advanced customization options such as query transformers and content injectors.
This article presents a comprehensive technical analysis of using large language models to build a task‑oriented multi‑turn dialogue system for intelligent marketing, detailing architecture, intent detection, slot extraction, prompt design, dialogue management, practical experience, and future research directions.
This article analyzes recent post‑training trends in large language models, comparing DPO and PPO, examining the scarcity of open‑source preference data, the iterative training process, the rise of synthetic data pipelines, and emerging methods for improving math and reasoning capabilities.
This article details an engineering‑focused practice that uses large language models, RAG, prompt engineering, and reranking to automatically generate, review, and refine Aviator scripts for decision‑center policies without any model pre‑training, offering practical insights and code examples for developers.
This article explains the different low‑level LLM API types in LangChain4j, including LanguageModel, ChatLanguageModel, and other model interfaces, and shows how to create and combine ChatMessage objects for multi‑turn conversations.
This article details how the DataLeap team applied large language model technology to build the "Find Data Assistant" platform, addressing the challenges of locating and using massive data assets through a hybrid retrieval architecture, enhanced embedding, reranking, mixed ranking, and answer summarization, while sharing practical lessons and future directions.
The article compares traditional rule‑engine architectures with AI‑driven models, explains their differing characteristics, outlines when deterministic rule matching is preferable over flexible AI inference, and recommends practical technologies such as Drools for rule‑based solutions and LLM‑based RAG/Agent frameworks for AI‑centric scenarios.
LangChain4j streamlines the integration of large language models into Java applications by offering a standardized API, extensive support for over a dozen LLM providers and vector stores, a rich toolbox for RAG, chat memory, and tool calling, plus two abstraction layers that cater to both low‑level control and high‑level convenience.
This article describes how KooJiaLe, a leading 3D design company, built an AI‑powered platform that uses large language models to automate test case generation, detailing its workflow, generation modes, editing features, export options, optimization efforts, results, and remaining challenges.
The article outlines fifteen advanced Retrieval‑Augmented Generation (RAG) techniques—from hierarchical indexing and context caching to multimodal alignment and microservice orchestration—explaining how they help transform AI prototypes into scalable, reliable production systems while highlighting common pitfalls and a concluding call to action.
This article introduces LangChain.js, explains its origins, core concepts such as chats, templates, tools, and chains, demonstrates practical JavaScript code examples, and explores the LangChain Execution Language (LCEL) for building flexible, conditional AI workflows.
This article explains the core concepts of Retrieval‑Augmented Generation (RAG), walks through its implementation steps with LangChain.js—including text chunking, embedding, storage, retrieval, and generation—and showcases practical use cases, challenges, and best practices for building reliable AI‑powered applications.
This article reviews MetaGPT, an open‑source multi‑agent framework that integrates human‑engineered SOPs into LLM‑based agents to improve software generation, data interpretation, and simulation tasks, highlighting its rapid community growth, experimental successes, tool integration strategies, and future research directions.
Learn step‑by‑step how to integrate OpenSearch LLM’s intelligent Q&A edition with the Dify large‑model platform to create a robust Retrieval‑Augmented Generation (RAG) system, covering architecture, workflow setup, API authentication, result parsing, and practical code examples.
This article analyzes the emerging AI Gateway market, compares major products such as Kong, Gloo, Higress, Portkey, and OneAPI, and provides a detailed technical review of Cloudflare AI Gateway’s architecture, capabilities, advantages, limitations, and practical usage for LLM integration.
This article reviews the ACL 2024 paper that investigates how large language model‑generated text influences retrieval‑augmented generation pipelines, revealing short‑term retrieval gains but a long‑term “spiral of silence” that marginalizes human‑generated content and homogenizes open‑domain QA results.
This article introduces LangChain.js, its core concepts such as chats, templates, tools, and chains, demonstrates how to use LCEL for flexible workflow composition, and shows practical JavaScript code examples for building AI-powered applications with large language models.
This article explains Prompt Engineering, introduces the AI Gateway concept, and demonstrates how to integrate a Geo‑IP plugin with an AI prompt‑modifying plugin in Higress using Go and Wasm, providing configuration examples, implementation details, and sample request‑response scenarios.
This article examines the typical business and technical architectures for large language model applications, covering AI Embedded, Copilot, and Agent modes, single‑ and multi‑agent systems, core frameworks, and guidance on selecting appropriate technical routes.
LangChain is a modular framework that streamlines integration of large language models by providing unified model interfaces, prompt optimization, memory handling, indexing, chains, and agents, enabling developers to quickly build and deploy sophisticated NLP applications such as text generation, information extraction, and dynamic tool‑driven workflows across various industries.
This guide walks you through deploying NVIDIA NIM for LLM inference on Alibaba Cloud ACK, integrating the Cloud Native AI Suite, configuring KServe, setting up Prometheus and Grafana monitoring, and implementing custom autoscaling based on request queue metrics.
This article introduces Kotaemon, an open‑source Retrieval‑Augmented Generation platform that lets users chat with their documents, offering a self‑hosted web UI, support for local and API LLMs, hybrid retrieval, multimodal question answering, GraphRAG indexing, and advanced reasoning capabilities, along with step‑by‑step installation via App or Docker.
This article compares GraphRAG with traditional RAG across seven dimensions—suitable scenarios, knowledge representation, retrieval, comprehensive queries, hidden‑relationship understanding, scalability, and performance‑cost trade‑offs—explains how they can be fused, and offers guidance on selecting the right approach for complex data‑driven applications.
This article explains why generic large language models struggle with domain‑specific data, introduces Retrieval‑Augmented Generation (RAG) as a solution, compares Word and PDF formats, outlines document‑parsing pipelines, reviews open‑source PDF tools, and presents Alibaba Cloud's rule‑based parsing architecture with performance results.
This article provides a comprehensive overview of large language models, covering their fundamental concepts, historical milestones, parameter scaling, prompt engineering techniques, retrieval‑augmented generation, autonomous agents, and multimodal model applications, illustrating how these technologies reshape AI capabilities across domains.
This guide explains how to reduce the computational cost of large language models by preparing instruction data, optionally augmenting or refining it, deploying teacher and student models on PAI, and performing distillation training with detailed hyper‑parameter settings and sample Python scripts.
This article details Tencent Game's end‑to‑end approach to building intelligent NPCs, covering the opportunities brought by AI, the practical implementation of multimodal LLM‑driven dialogue, knowledge‑augmented retrieval, long‑context handling, safety measures, multimodal expression (voice and facial animation), and system‑level performance optimizations for real‑time deployment.
The author shares a candid account of recent large‑model experiments, highlighting why most labs struggle to exceed 100 B parameters, how data and hardware constraints shape model iteration, and the practical engineering, safety, and multimodal challenges that dictate real‑world LLM deployment.
The author reflects on two years of LLM work, describing how large language models shattered old NLP expertise, reshaped daily engineering tasks, leveled the playing field for newcomers, sparked a golden era of AI productivity, and why concerns about a bubble are largely irrelevant for programmers.
This article explains what AI agents are, why they matter, the essential soft and hard skills needed, and provides a detailed step‑by‑step roadmap for anyone aspiring to become an AI agent developer in the emerging AI‑driven software landscape.
This article shares engineering insights from Hema’s AI smart customer service deployment, detailing key stability factors for AI agents—including hallucination mitigation, memory integration, RAG enhancement, exception handling, and comprehensive monitoring—to improve reliability and performance in real‑world e‑commerce chatbot scenarios.
LangGraph Studio is a new visual IDE that simplifies the development, debugging, and interactive iteration of complex LLM‑based agent applications, offering features such as graph visualization, real‑time state inspection, code‑aware debugging, and seamless integration with LangSmith, with step‑by‑step guidance for desktop users.
This article explains what large language models (LLMs) are, how they are trained, their diverse applications across industries, the challenges they face, and provides a practical Python example using Replicate to run Meta's Llama 3‑70b‑instruct model.
This article details Meituan Waimai's feed advertising system, covering business characteristics, the evolution of estimation models, and practical implementations such as decision‑path modeling, ultra‑long/wide user modeling, full‑reconstruction techniques, and the integration of large language models for CTR prediction.
This article explains how large language models (LLMs) can launch data democratization by constructing a metric platform that combines LLM agents, semantic layers, NL2SQL/NL2API pipelines, warehouse‑internal and external semantics, and showcases SwiftAgent/SwiftMetrics innovations, real‑world case studies, and future directions.
This article explains the fundamentals of large language models, covering tokenization, probability prediction, Markov chain basics, training data limitations, context windows, and the transition to neural network architectures like Transformers, while providing Python examples and insights into model scaling and the illusion of intelligence.
This article explains how generative AI models work by demystifying tokens, tokenization with tools like tiktoken, simple Markov‑chain training, the limitations of small context windows, and how modern LLMs use neural networks, transformers and attention mechanisms to predict the next token.
This article reviews cutting‑edge research on integrating large language models with graph‑based recommendation systems, detailing four key strategies—LLM node embeddings, deep graph‑LLM fusion, model‑driven graph data training, and text‑modal enhancements—while analyzing representation learning, InfoNCE optimization, explainable recommendations, and extensive experimental validation.
This article introduces LangGraph, a Python library for creating stateful, multi‑agent LLM workflows, explains its loop, persistence, and human‑in‑the‑loop features, shows how to install it, and provides a complete code example that builds, runs, and reuses a searchable AI agent with thread‑level state saving.
The article examines DARPA's TRACTOR project, which aims to use large‑language‑model AI to automatically translate legacy C and C++ code into safe Rust, discusses the memory‑safety motivations, technical challenges, community reactions, and the broader push by US agencies to abandon unsafe languages.
The article presents a practical method for evaluating 1‑million‑token LLMs by inserting structured medal data into a classic Chinese novel, provides a full Python script for the test, shares results on GLM‑4‑long, and discusses training techniques and open‑source resources for long‑context models.
This article reviews four ACL 2024 papers authored by Meituan’s research team—covering training cost reduction, speculative decoding, code generation optimization, and instruction fine‑tuning—while also announcing a live sharing session at the conference.
The article breaks down multiple practical approaches for data preparation, training code handling, and experiment analysis in large‑language‑model fine‑tuning, showing how deeper engagement in each step can boost personal expertise even when final model performance appears similar.
MegaParse is an open‑source document parser that transforms PDFs, Word, PPT, Excel and CSV files into LLM‑friendly formats, preserving full information, boosting processing efficiency, and enabling deeper semantic analysis, with quick‑start installation steps and a roadmap for future features.
The article surveys the rapid emergence of large AI models and AIGC, explains core concepts like AI, AGI, and LLMs, details prompt‑engineering techniques such as chain‑of‑thought, outlines a seven‑layer AIGC stack, discusses technical and ethical challenges, and highlights future multimodal and industry‑specific applications.
This article analyses the shortcomings of current large language model training methods such as SFT, RLHF and DPO, explains why they incur high data and compute costs, and introduces Intuitive Fine‑Tuning (IFT) with temporal residual connections as a cheaper yet effective alternative that better aligns training objectives with real generation tasks.
This article introduces an AI‑driven Smart Report Assistant Bot that automatically converts uploaded Excel files into recommended charts, allows users to customize reports, and details the underlying workflow—including Excel parsing, LLM‑generated SQL, dynamic table creation, chart rendering with ECharts, and image‑merging plugins.
This article introduces STORM, a Stanford‑developed large‑language‑model‑based knowledge‑management platform that automates topic research, outline generation, citation‑rich article writing, and iterative refinement through perspective‑guided questioning and simulated conversations, dramatically improving technical investigation efficiency.
This article introduces STORM, a Stanford‑developed LLM‑based knowledge‑management system that automates topic research, outline creation, content generation with citations, and optimization through perspective‑guided questioning and simulated dialogue, dramatically improving technical investigation efficiency.
This guide walks through creating a full‑featured AI‑native API gateway using Higress, covering architecture setup, AI agent integration, observability, content security, token rate limiting, caching, retrieval‑augmented generation, prompt templates, and intelligent request/response transformation with concrete configuration examples.
This article explains the fundamentals of large language models, artificial general intelligence, AI-generated content, AI agents, retrieval‑augmented generation, knowledge bases, multimodal processing, fine‑tuning, alignment, tokens, vectors, and related tools, highlighting their capabilities, limitations, and practical considerations.
This report presents a continual pre‑training approach that significantly enhances Llama‑3 (8B)’s Chinese language proficiency and scientific reasoning by using a carefully mixed corpus of existing and synthetic data, detailing the bilingual adaptation and synthetic‑enhancement stages, data‑mixing and curriculum strategies, and demonstrating strong results across multilingual and scientific benchmarks without sacrificing original capabilities.
This article reviews the state‑of‑the‑art applications of large language models in recommendation systems, summarizing background knowledge, recent advances such as LLM4Rec, various tuning strategies, agent‑based approaches, open research problems, and future directions for generative recommendation.
This article surveys the design of autonomous large‑language‑model agents, detailing their modular architecture—including profiling, memory, planning, and execution—while also reviewing common profiling methods, memory structures, planning techniques, action strategies, and various learning approaches such as exemplar, human‑in‑the‑loop, and environment‑feedback training.
This article explains how to use the Shire language to create reliable coding agents by defining custom RAG workflows, leveraging IDE APIs, code verification functions, and vector‑based search, with detailed examples, configuration snippets, and a roadmap for future enhancements.
This article explains the challenges of deploying large language model (LLM) applications, outlines the need for end‑to‑end observability, and details Alibaba Cloud ARMS' LLM‑specific tracing, metrics, and Python agent solutions for monitoring, debugging, and performance optimization.
This article reviews the emerging field of large language model‑based AI agents, outlining their overall architecture, key challenges such as role‑playing, memory, planning, and multi‑agent collaboration, and discusses future research directions and practical examples in user behavior simulation and software development.
This article explores how large language model‑powered coding assistants boost developer productivity, shift the role of engineers toward higher‑level design and problem‑solving, and raise new responsibilities for code safety, performance, and ethical use in the evolving software development paradigm.
This article walks through the author’s experience creating a custom AI agent using LangChain and OpenAI APIs, explains the concepts of AI agents and the ReAct reasoning framework, provides step‑by‑step code, discusses required libraries and APIs, and shares practical tips and challenges encountered.
This talk explores how 360's advertising recommendation system leverages language models—from BERT to large‑scale LLMs—to improve user interest modeling, feature extraction, and conversion‑rate prediction, detailing practical challenges, engineering solutions, experimental results, and future research directions.
This article presents Task‑aware Decoding (TaD), a plug‑and‑play technique introduced by JD Tech and Tsinghua University and accepted at IJCAI 2024, which reduces intrinsic hallucinations in large language models by comparing pre‑ and post‑fine‑tuning outputs, and demonstrates its effectiveness combined with Retrieval‑Augmented Generation across various tasks.
This article provides a comprehensive overview of large language models (LLMs), covering their basic concepts, relationship with NLP, development history, parameter scaling, offline deployment, practical applications, prompt‑engineering frameworks, retrieval‑augmented generation, LangChain integration, agents, workflow orchestration, and future directions toward multimodal AI and AGI.
This article reviews JetBrains AI, an LLM‑powered assistant for JetBrains IDEs, exploring its code‑completion, code‑explanation, unit‑test generation, and refactoring capabilities through real C# examples and discussing its impact on developer workflows.
The talk by Huawei Noah's Ark Lab researcher Wang Yichao presents a comprehensive exploration of large language models (LLMs) for recommendation systems, covering background challenges, the KAR and Uni-CTR projects, experimental results, and future directions for open‑world, generative recommendation pipelines.
Mem0 is an open‑source memory‑management middleware for large language models that provides dynamic, context‑aware, and adaptive memory, outperforming traditional Retrieval‑Augmented Generation (RAG) and enabling personalized AI assistants, travel planners, and support agents with concrete Python APIs and examples.
This article walks through deploying the open‑source LLM serving tool Ollama and the Open‑WebUI interface on a Kubernetes cluster using Helm, covering GPU considerations, configuration files, service exposure, and model management with practical code examples.
This article surveys the rapid rise of AI agents powered by large language models, explaining their core perception‑planning‑action loop, memory architectures, tool‑use mechanisms, self‑reflection techniques, and real‑world case studies while highlighting current challenges and future prospects for autonomous intelligent systems.
Exploring Large Language Models, this article surveys their core concepts, evolution through Transformers, GPT and BERT, generation challenges, diverse applications such as QA, multimodal creation, summarization and retrieval‑augmented generation, prompt‑engineering frameworks and tools, LangChain‑based pipelines, AI‑driven agents, and future prospects toward domain‑specific use, multimodality, and AGI.
This article reviews the emerging field of large‑language‑model (LLM) based AI agents, outlining their overall architecture, core modules such as profiling, memory, planning and action, discussing current challenges, presenting concrete use‑cases, and highlighting promising research directions.
This article explains how Alibaba Cloud designed and deployed large‑language‑model agents for its service domain, covering background, ideal LLM deployment, the shift from explanation to problem solving, the agent framework, practical implementation, automation trade‑offs, training, evaluation, and real‑world impact.
Recent tests reveal that popular large language models—including GPT‑4o, Gemini Advanced, and Claude 3.5—often claim 9.11 is larger than 9.9 because their tokenizers split the numbers, but rephrasing, zero‑shot chain‑of‑thought prompts, or treating the values as floating‑point numbers can correct the mistake, a pattern also seen variably in Chinese models.
TaD, a task‑aware decoding technique jointly developed by JD.com and Tsinghua University and presented at IJCAI 2024, leverages differences between pre‑ and post‑fine‑tuned LLM outputs to construct knowledge vectors, significantly reducing hallucinations across various models, tasks, and data‑scarce scenarios, especially when combined with RAG.
This article reviews the hallucination problem in large language models, analyzes its data, training, and inference sources, and presents Task‑aware Decoding (TaD) and Retrieval‑Augmented Generation (RAG) as effective, plug‑and‑play solutions demonstrated through extensive experiments.
The article examines how AI-era large language model (LLM) applications impose new traffic, security, and scalability requirements on gateways, and explains how the Envoy‑based open‑source Higress gateway addresses these challenges with hot configuration updates, token‑based rate limiting, streaming support, and multi‑tenant capabilities.
This article explains how to use Alibaba Service Mesh (ASM) to register large language model (LLM) providers, configure LLMProvider and LLMRoute resources, and implement traffic routing, observability, and security for LLM services through step‑by‑step Kubernetes manifests and curl tests.
This article reviews the IJCAI 2024‑presented Task‑aware Decoding (TaD) technique, explains how it mitigates large‑language‑model hallucinations when combined with Retrieval‑augmented Generation, and details experimental results, practical deployments, and future research directions.
This guide explains how to deploy the open‑source LLM serving tool Ollama and the Open‑WebUI front‑end on a Kubernetes cluster using Helm charts, covering GPU configuration, persistent storage, service exposure, and model selection for large language models.
This guide compiles open‑source repositories, research papers, and practical tricks for training miniature large‑language models under 1 billion parameters, helping readers learn by reproducing models like nanoGPT, tinyLlama, Phi‑1.5, and more.
This article provides a comprehensive, step‑by‑step guide for developing large‑language‑model (LLM) applications, covering prompt design techniques, n‑shot and chain‑of‑thought strategies, retrieval‑augmented generation, structured I/O, workflow optimization, evaluation pipelines, operational best practices, and team organization to create reliable, scalable AI products.
This article presents a practical Python benchmark that measures token‑per‑second generation speed of various large language models—including GPT‑4o, glm‑4‑airx, and moonshot‑v1‑32k—by timing text generation on a Colab environment and summarizing the results in detailed tables and visual charts.
This guide explains how to enhance large language model outputs by constructing a GraphRAG pipeline that transforms relational data into a Neo4j knowledge graph, creates nodes and relationships via Python, and leverages LangChain's GraphCypherQAChain for accurate, context‑aware retrieval and generation.
The article presents Ant Group's research on integrating large language models into recommendation pipelines, covering background challenges, knowledge extraction, teacher‑model distillation, efficient deployment, experimental results, and future directions to improve accuracy and reduce bias.
This article provides a step‑by‑step guide for Java engineers on building a Retrieval‑Augmented Generation (RAG) application using the LangChain4j framework, covering RAG fundamentals, environment setup, Maven integration, document loading, splitting, embedding with OpenAI, vector store management with Chroma, and prompt‑based LLM interaction.
This article reviews the Kuaishou paper on adapting large language models for recommendation, detailing the LEARN framework's dual‑tower architecture, embedding generation, loss functions, and experimental results that address cold‑start and long‑tail challenges in modern recommender systems.
This tutorial walks you through creating a privacy‑preserving, locally hosted large language model chatbot using Ollama, Python 3, and ChromaDB, covering RAG fundamentals, GPU selection, environment setup, and full source code for a Flask‑based application.
This guide walks through the concepts, workflow, and practical steps for creating a high‑quality knowledge base in FastGPT using vector search, QA pair structuring, prompt engineering, and parameter tuning to improve LLM‑driven question answering.
genai is a Rust library that unifies the APIs of major large language models, offering a lightweight, native solution with simple chat‑focused examples, demonstrated through a dual‑model Rust program, and outlines future expansions such as additional model support, multimodal capabilities, and performance optimizations.
This article surveys how large language models reshape recommendation systems, presents a generative RS framework tailored for JD Alliance advertising, details material representation, model input, training and inference pipelines, and reports extensive offline and online experiments demonstrating its effectiveness on sparse user data.
This article explores the role of hyperparameters in large language models, explains each key hyperparameter, and guides readers through manual and automated tuning methods such as random search, grid search, and Bayesian optimization to achieve optimal model performance.
