Tagged articles
LLM integration
83 articles · Page 1 of 1
This guide walks through configuring OpenAI's Codex CLI to use DeepSeek models, covering CLI updates, API key setup, model catalog configuration, config.toml edits, smoke testing with a small task, and troubleshooting common errors like authentication failures and tool compatibility issues.
CLI configurationCodexDeepSeek
0 likes · 5 min read

This analysis of Agent Zero examines its 1.8M Docker pulls versus 19.8k stars, detailing its real Linux desktop environment for AI agents, native DOM browser interaction, installation methods, key features like project isolation and time-travel snapshots, and critical caveats around licensing, contributor concentration, and default anti-detection components.
AI agentsAgent ZeroDocker
0 likes · 12 min read

This tutorial demonstrates how LiteFlow v2.16+ integrates AI agents as native components, enabling developers to orchestrate LLMs like DeepSeek, Qwen, and OpenAI models using familiar LiteFlow operators (THEN, WHEN, IF) within Spring Boot applications.
AI AgentAgent orchestrationJava framework
0 likes · 14 min read

Jev is a 'System One' model that returns structured judgments with probabilities instead of free text, enabling reliable integration into software workflows for high-frequency classification tasks where LLMs' unstructured output creates parsing overhead and instability.
AI ArchitectureJSON alternativeJev
0 likes · 18 min read

This tutorial demonstrates building a graph-based workflow for AI agents using Spring AI Alibaba, covering state management, node implementation, conditional edges, and a practical excuse-upgrade example with LLM-driven nodes and dynamic routing based on believability scores.
Agent DevelopmentConditional EdgesGraph Workflow
0 likes · 14 min read


java1234Sep 24, 2026 · Backend Development
This article details the design of an AI-powered OA system built with Spring Boot 4, Vue 3, and Spring AI 2.0, covering three AI capabilities (smart leave forms, approval tracking, RAG policy QA), a four-role permission model, two-level approval engine, database schema, API endpoints, and vector retrieval configuration using Redis Stack and Alibaba Qwen models.
LLM integrationOA SystemRAG
0 likes · 37 min read

This guide categorizes six major Java AI frameworks into infrastructure and orchestration layers, detailing Spring AI 2.0's Advisor chain, LangChain4j's model breadth, Solon AI's Java 8 compatibility, Spring AI Alibaba's workflow engine, AgentScope's production-grade harness, and Embabel's deterministic GOAP planning to match frameworks to project constraints and scenarios.
AI FrameworksAgent orchestrationAgentScope
0 likes · 30 min read

WeKnora is an MIT-licensed enterprise knowledge management framework from Tencent's WeChat team that goes beyond traditional RAG by integrating hybrid retrieval, ReAct agents with skill sandboxes, automatic Wiki generation from raw documents, knowledge graphs, and multi-channel distribution including WeChat ecosystem integration.
Auto WikiDocker deploymentEnterprise Knowledge Management
0 likes · 15 min read

LangChain4j provides a Java-native framework for integrating 20+ LLM providers and 30+ vector stores via a unified API, declarative AiServices, RAG pipelines, tool calling, and MCP support, enabling Spring Boot teams to add AI capabilities without Python dependencies.
AI servicesJavaLLM integration
0 likes · 9 min read

This article demonstrates how to integrate Grok with Pi Agent and configure context window and compaction settings to trigger automatic context compression before hitting the 200K token threshold where Grok's pricing doubles, preserving task quality while maximizing weekly quota efficiency.
Context ManagementGrokLLM integration
0 likes · 6 min read

This article dissects Palantir's Ontology, a semantic operational layer integrating data, logic, actions, and security, explaining its three core primitives (Objects, Links, Actions), layered architecture, differences from knowledge graphs, and demonstrating via Airbus Skywise case how LLMs use OSDK to query and execute actions safely.
AIPAirbus SkywiseData Decision Platform
0 likes · 13 min read

This tutorial introduces 10 practical DeepSeek Harness (DSH) plugins that extend the AI agent platform with capabilities like prompt optimization, cost tracking, plugin marketplace, web UI aggregation, Codex/Claude/Grok subscription integration, conversation mapping, office document automation, multi-agent team collaboration, and context visualization — each with installation commands and usage walkthroughs.
AI agentsAgent WorkbenchContext Visualization
0 likes · 17 min read

The article explains what an ontology platform is, why enterprises need it to close the semantic gap between data and business, evaluates core technical capabilities, reviews the market landscape, and offers a step‑by‑step selection guide for building a robust Data+AI semantic infrastructure.
Data+AILLM integrationenterprise architecture
0 likes · 17 min read

The article examines whether code agent frameworks (Harness) are tightly coupled to specific LLMs, analyzing differences in training alignment, attention mechanisms, safety guardrails, and chat format protocols that require model-specific adaptations, and explores architectural abstraction strategies using OpenCode as a reference.
Agent Framework DesignChat Format AlignmentCode Agents
0 likes · 8 min read

This article explains what an AI harness is, compares ready‑made and DIY options, categorises three main harness types, and provides an eight‑point checklist—including context management, memory, protocol support, standards, model flexibility, remote access, debugging, and hackability—to help both engineers and non‑technical users select the most suitable solution.
AI HarnessLLM integrationautomation
0 likes · 14 min read

The article explains how to replace Codex’s underlying model with DeepSeek‑V4‑Flash, provides benchmark results showing it outperforms DeepSeek‑V4‑Pro‑Preview and ranks 7th in Frontend Code Arena, highlights its low token price, and walks through installation, configuration, and sample prompts using official scripts.
AI pricingChatGPTCodex
0 likes · 7 min read

Claude Code only understands Anthropic‑format endpoints, but by adjusting three environment variables you can route it to domestic models such as Kimi K3 or Alibaba Qwen, with detailed step‑by‑step instructions for direct env‑var changes, settings‑file configuration, and GUI or CLI tools, plus known limitations.
Anthropic APIClaude CodeKimi
0 likes · 12 min read

The article explains that while many teams focus on model accuracy, the real challenges of an AI‑powered tagging system are write spikes, timeouts, duplicate tagging, cost overruns and state inconsistency, and it proposes a five‑layer architecture, async fallback, governance and validation practices to reliably achieve a 100 k QPS target.
AI taggingKafkaLLM integration
0 likes · 30 min read

This tutorial explains the Model Context Protocol (MCP) introduced by Anthropic, showing how its three‑layer Host/Client/Server architecture and six primitives turn Harness into a standardized, USB‑like interface for connecting any data source or tool to large language models, with concrete examples, transport choices, and step‑by‑step implementation guidance.
HarnessLLM integrationMCP
0 likes · 23 min read


21CTOJun 30, 2026 · Artificial Intelligence
The article argues that, despite Python’s dominance in AI research, PHP’s ubiquitous production‑grade web stack, built‑in authentication, database access, and recent language features make it a pragmatic choice for building AI agents that call LLM APIs via simple REST requests, without extra runtimes or orchestration tools.
AI agentsBackendLLM integration
0 likes · 14 min read

Firecrawl is a 139K‑star open‑source web‑scraping API that handles dynamic JavaScript pages, full‑site crawling, search, and interactive browsing, offers built‑in proxy rotation and LLM‑ready Markdown/JSON output, and provides detailed code samples and deployment guides that outperform traditional tools like Scrapy and Selenium.
AI agentsFirecrawlLLM integration
0 likes · 12 min read

This article compares Spring AI 2.0 and LangChain4j for integrating large language models into Java enterprise applications, examining their positioning, version alignment, programming models, RAG capabilities, tooling, observability, learning curves, and suitability for different team stacks to help you make an informed selection.
AI FrameworksJavaLLM integration
0 likes · 12 min read

The article provides a side‑by‑side analysis of Spring AI 2.0 and LangChain4j, comparing their goals, version alignment, programming models, RAG and agent capabilities, ecosystem integration, learning curve, and operational considerations to help Java teams decide which library best fits their project constraints.
AI agentsJavaLLM integration
0 likes · 11 min read


java1234Apr 24, 2026 · Artificial Intelligence
This article compares Spring AI 2.0 and LangChain4j, examining their positioning, version alignment, architecture, programming model, RAG support, observability, learning curve, and ecosystem integration to help Java teams decide which library best fits their AI project constraints.
AI librariesJavaLLM integration
0 likes · 13 min read


Geek LabsApr 13, 2026 · Artificial Intelligence
Hermes Agent, an open‑source AI framework released by Nous Research, introduces a built‑in self‑evolution loop, a three‑layer memory system, and multi‑platform support; the article reviews its core features, compares it with Claude Code/OpenClaw, and highlights two companion projects—the Orange Book guide and a Web UI monitoring dashboard.
AI AgentHermes AgentLLM integration
0 likes · 15 min read

This article curates ten free, open‑source AI‑focused projects—from web‑crawlers and browser automation to audio transcription, video downloading, and persistent memory—explaining their core capabilities, typical use cases, and how they can be integrated into developer workflows to boost productivity.
AI toolsDeveloper ProductivityLLM integration
0 likes · 11 min read

Goose is an open‑source, on‑machine AI agent written in Rust that can autonomously handle end‑to‑end development workflows—from project scaffolding and API coding to testing and debugging—by orchestrating multiple LLMs via a Model Context Protocol, offering a full‑stack engineering partner for developers and teams.
AI AgentLLM integrationRust
0 likes · 8 min read

Academic‑Search is an open‑source AI‑powered literature retrieval skill that unifies multi‑platform search, deduplication, citation tracking, BibTeX export, PDF download, and code completion, dramatically accelerating research workflows by up to ten times while integrating smoothly with agents like AutoGPT and LangChain.
AI literature searchLLM integrationPython
0 likes · 10 min read


大转转FEMar 30, 2026 · Industry Insights
This newsletter curates five in‑depth industry analyses covering Claude‑driven AICoding engineering, large‑model integration in e‑commerce data warehouses, AI agent identity‑permission governance, a step‑by‑step AI agent construction guide, and Tair‑based short‑term memory architecture for millisecond‑level response.
AI agentsAI codingLLM integration
0 likes · 6 min read

LiteLLM provides a single Python SDK and proxy server that let developers call more than 100 large‑language‑model APIs with a uniform OpenAI‑style interface, handling cost tracking, load balancing, rate limiting, and detailed logging to simplify multi‑model experimentation and production deployments.
AI gatewayLLM integrationLiteLLM
0 likes · 6 min read


AI WakaMar 26, 2026 · Artificial Intelligence
This article analyzes the trade‑offs between Model Context Protocol (MCP) and Skills for Claude‑based AI workflows, offering a three‑question test, real‑world examples, and architectural diagrams to help engineers choose the most efficient approach for their tasks.
AI workflowClaudeDecision Framework
0 likes · 10 min read


AI WakaMar 25, 2026 · Artificial Intelligence
OpenClaw is an open‑source, OS‑level autonomous agent runtime that combines dynamic system prompts, powerful tool access, file‑based memory, and sub‑agent generation, offering a secure, extensible architecture that runs on a single Node.js process and integrates with any LLM provider.
Agent RuntimeLLM integrationOpenClaw
0 likes · 19 min read

This article provides a comprehensive technical analysis of OpenClaw, an open‑source autonomous‑agent framework that integrates large language models with local system operations through a four‑layer architecture, detailed message‑processing steps, ReAct reasoning loops, security mechanisms, performance optimizations, and real‑world application scenarios.
AI agentsLLM integrationOpenClaw
0 likes · 13 min read

AstrBot is an open‑source, highly modular Python platform that unifies IM adapters, LLM abstraction, and a plugin marketplace, enabling developers to deploy cross‑platform AI assistants with a single backend, as demonstrated by a quick Docker setup and support for dozens of chat services.
AI chatbotAstrBotDocker deployment
0 likes · 7 min read

Pi-mono is a four‑tool, four‑layer AI coding assistant built by Mario Zechner that replaces bloated agents with a minimalist design, supports dozens of LLM providers, offers a terminal UI, extensible TypeScript plugins, and demonstrates superior benchmark performance in Terminal‑Bench.
AI coding assistantLLM integrationagent framework
0 likes · 13 min read

This guide walks you through installing Claude Code and Ollama, pulling and configuring various open‑source models, setting environment variables, and running Claude Code with both local and cloud‑hosted models, while covering context length, performance considerations, and tool‑calling examples.
Claude CodeLLM integrationOllama
0 likes · 14 min read

PicoClaw is a Go‑rewritten, 99% smaller version of OpenClaw that fits under 10 MB, boots in under a second on a 0.6 GHz CPU, runs on $10‑$100 single‑board computers, offers full‑stack engineer mode, task scheduling, sandbox security, and multi‑platform chat integration, with detailed installation guides and a balanced list of strengths and current limitations.
AI AgentGoLLM integration
0 likes · 11 min read


TonyBaiFeb 15, 2026 · Artificial Intelligence
The article examines how the Pi engine, the core of OpenClaw’s AI coding agent, was built with a minimalist, opinionated design, detailing its modular components, handling of multi‑model context, lightweight TUI, security philosophy, and benchmark results that show it rivals heavier competitors.
AI coding agentLLM integrationMinimalist Design
0 likes · 14 min read

OpenClaw, a 2026 open‑source AI agent, combines a protocol‑agnostic gateway, a four‑layer memory system, and an extensible Agent Skills framework to enable real‑time cross‑platform interaction, long‑term learning, and seamless integration with Chinese large language models and popular chat applications.
AI AgentChat Tool IntegrationFour-Layer Memory
0 likes · 11 min read


AI WakaJan 24, 2026 · Artificial Intelligence
This comprehensive 2026 roadmap outlines the essential programming foundations, core agent architectures, LLM and API integrations, tool usage, memory management, RAG systems, deployment strategies, monitoring, and security practices needed to design, develop, and operate autonomous AI agents.
AI roadmapAgentic AILLM integration
0 likes · 10 min read

This guide walks you through installing and configuring OpenCode—a free, open‑source AI programming assistant supporting 75+ LLM providers—and its Oh My OpenCode plugin suite that adds specialized parallel agents, automatic model switching, and rich CLI commands, showing how they transform real‑world development workflows.
AI coding assistantCLI toolsLLM integration
0 likes · 15 min read

This article introduces next‑ai‑draw‑io, an open‑source AI extension for Draw.io that lets developers generate and edit architecture diagrams through natural‑language prompts, supports image‑to‑diagram conversion, multiple LLM providers, and offers easy installation via Next.js or Vercel.
AI diagram generationDraw.ioLLM integration
0 likes · 6 min read

The article explains how a well‑designed enterprise ontology—an explicit business‑level semantic and constraint model—turns large language models from risky, hallucination‑prone tools into safe, auditable AI agents that can act across systems, enforce policies, and become a lasting digital asset.
AI governanceLLM integrationenterprise AI
0 likes · 15 min read

This guide shows how to replace Claude Code's default model with the Chinese Doubao‑Seed‑Code programming model by creating a wrapper script, configuring environment variables, and running a few shell commands, then demonstrates the setup by generating a functional Space Invaders web game.
AI coding modelClaude CodeDoubao-Seed-Code
0 likes · 8 min read

The article explains how Amazon Bedrock AgentCore Memory transforms AI agents from short‑term responders into continuously learning entities by extracting valuable insights, integrating them intelligently, handling edge cases, supporting custom strategies, and delivering high compression rates and low latency for large‑scale deployments.
AI agentsAgentCore MemoryAmazon Bedrock
0 likes · 17 min read

The article analyzes the evolution from a single‑agent LLM pipeline to a six‑agent architecture that separates intent recognition, tool filtering, reasoning, and summarization, enabling precise handling of complex user queries, efficient tool selection from thousands, and faster, more reliable AI‑driven data generation.
AI agentsLLM integrationPrompt engineering
0 likes · 25 min read

This article explains how BaikalDB leverages the Model Context Protocol to let large language models query and analyze its distributed database without writing any code, detailing the protocol’s principles, server components, transport methods, tool capabilities, use cases, configuration, and future challenges.
BaikalDBDatabase AILLM integration
0 likes · 11 min read

MCP, a protocol from Anbhropic, standardizes how large language models communicate with external tools, databases, and APIs through a client‑server architecture, offering three communication modes (Stdio, HTTP with SSE, Streamable HTTP) and enabling use cases such as intelligent analytics, knowledge hubs, AI chatbots, BPM, API integration, automated testing, and programming assistance.
AI protocolLLM integrationMCP
0 likes · 9 min read

This article introduces the rapidly popular Gemini CLI, compares it with Claude Code, explains its core features, demonstrates coding, multimodal, and MCP use cases, and details the author’s Easy LLM CLI fork that enables custom model integration, flexible configuration, and direct code embedding for developers.
AI AgentGemini CLILLM integration
0 likes · 15 min read

This article introduces Byte's open‑source Coze Loop and Coze Studio platforms, detailing their Apache‑2.0‑licensed architectures, full lifecycle management for AI agents, core features such as prompt engineering, evaluation, observation, and a low‑code visual development environment built with Golang, React, and TypeScript.
AI AgentCoze LoopCoze Studio
0 likes · 6 min read

This article examines the Cursor coding‑assistant by dissecting its backend architecture, running three practical experiments (a Go hello‑world program, a CUDA flash‑attention code search, and a single‑page to‑do web app), and analyzing why the tool succeeds or fails in real development scenarios.
Coding AgentCursorLLM integration
0 likes · 9 min read

This article introduces three emerging standards—MCP, A2A, and AG‑UI—that simplify connecting large language models to external tools, other agents, and user interfaces, explaining their origins, architectures, development workflows, key features, and how they complement each other in AI application development.
A2AAG-UIAI Protocols
0 likes · 14 min read

The article provides a detailed walkthrough of OpenManus, an open‑source AI agent framework built with Python 3.12, covering its modular architecture, agent and tool hierarchies, a step‑by‑step usage example for generating a Beijing travel plan, and a deployment guide on Alibaba Cloud.
AI agentsAlibaba Cloud deploymentLLM integration
0 likes · 10 min read

This guide introduces the Model Context Protocol (MCP), explains its purpose as a standardized USB‑C‑like interface for LLMs, and provides step‑by‑step Python code to set up SSE‑based MCP servers and a client, plus essential installation details and execution commands.
AI protocolLLM integrationMCP
0 likes · 11 min read

This guide shows how to install Gradio with MCP support, write a few lines of Python to expose a function as an MCP tool, launch the server, and integrate it with large language model clients such as Claude Desktop or Hugging Face Spaces.
APIGradioLLM integration
0 likes · 8 min read

Google’s newly released Agent2Agent (A2A) protocol and Anthropic’s Model Context Protocol (MCP) are examined side‑by‑side, outlining their purposes, complementary features, potential competition, and how they together shape the future of multi‑agent systems, security, task management, and integration with legacy data sources.
A2AAI ProtocolsAgentic Systems
0 likes · 17 min read

MCP (Model Context Protocol) is an emerging open‑standard that lets large language models interact with tools, data sources, and services through a unified JSON‑RPC or gRPC interface, addressing fragmentation, data silos, and low development efficiency while offering a flexible, community‑driven ecosystem with clear advantages and current limitations.
AI Tool CallingJSON-RPCLLM integration
0 likes · 14 min read

This guide walks developers through creating a reusable MCP (Model Context Protocol) tool for Cursor AI—encapsulating the SDK, configuring files, implementing PSD‑slicing logic, defining JSON schemas, adding utilities and build scripts, and deploying it as a command‑type server while avoiding common integration pitfalls.
Cursor AILLM integrationMCP
0 likes · 7 min read

The Model Context Protocol (MCP) is an open, USB‑like standard that lets large language models securely connect to external data sources, tools, and services through a client‑server architecture, enabling developers to integrate diverse resources with standardized SDKs, fostering rapid, scalable AI‑enhanced applications across many domains.
AI standardsLLM integrationMCP
0 likes · 18 min read

This article explains the agents.json specification, its OpenAPI foundation, how it differs from MCP and Google A2A, and demonstrates how AI agents can load, interpret, and execute multi‑step API flows using code examples and schema illustrations.
AI agentsAPI flowsLLM integration
0 likes · 16 min read

This article introduces Anthropic’s open Model Context Protocol (MCP), explaining its basic concepts, motivations, core architecture, components, and workflow, and shows how it standardizes and secures LLM interactions with external data sources, tools, and services.
AI ArchitectureAnthropicLLM integration
0 likes · 7 min read

This article explains what Model Context Protocol (MCP) is, demonstrates a simple e‑commerce example, and provides a step‑by‑step guide to create, configure, build, and debug an MCP service using APISIX Admin API, Node.js, TypeScript, and Zod, enabling natural‑language interaction with backend APIs.
API automationAPISIXLLM integration
0 likes · 15 min read


ArchitectApr 2, 2025 · Artificial Intelligence
This article explains the open‑source Model Context Protocol (MCP) created by Anthropic, describes its client‑server architecture for safely linking LLMs with external data sources and tools, and provides a complete step‑by‑step Python tutorial—including environment setup, server and client code—to demonstrate MCP in action.
AI agentsLLM integrationLangChain
0 likes · 9 min read


ArchitectMar 27, 2025 · Artificial Intelligence
This article explains Anthropic’s open‑source Model Context Protocol (MCP), its client‑server architecture, resource and tool definitions, sampling workflow, and provides step‑by‑step Python examples for building a PoE2 hot‑fix fetcher and a simple chatbot that leverages MCP to connect large language models with external data sources and functions.
AI toolsLLM integrationMCP
0 likes · 14 min read

The article presents Anthropic’s open‑source Model Context Protocol (MCP) – a client‑server framework that standardizes how large language models securely access resources, prompts, and tools (the “HTTP of AI”) – and demonstrates its use through a hot‑fix scraper and a dynamic chatbot that discovers and invokes tools via JSON‑formatted calls.
AI ProtocolsLLM integrationMCP
0 likes · 15 min read

The article details how the author discovered a bug in Cursor’s closed‑source IDE where correctly registered MCP services, such as a weather query tool, are omitted from the LLM’s tool list, preventing calls, and explains the debugging steps that compared Cursor with the open‑source Cline implementation to pinpoint the registration flaw.
AI debuggingCursorLLM integration
0 likes · 12 min read

The article explains how the Model Context Protocol (MCP) addresses the difficulty of connecting large language models to external data, tools, and APIs by providing an open, standardized interface that enables AI agents to access real‑time information, act autonomously, and do so securely and modularly.
AI agentsAI tool interoperabilityLLM integration
0 likes · 7 min read

The Model Context Protocol (MCP), announced by Anthropic, standardizes how AI applications provide context to LLMs, offering a client‑server architecture that simplifies data and tool integration, and is compared with function calling, highlighting its benefits, workflow, controversies, and future prospects.
AI ArchitectureAnthropicFunction Calling
0 likes · 9 min read

Learn how to deploy the new QwQ‑32B inference model alongside DeepSeek‑R1 using the Higress AI gateway, covering environment setup, model configuration, routing, token‑level rate limiting, content safety, semantic caching, and advanced features like automatic fallback and internet‑search integration.
DeepSeekHigressLLM integration
0 likes · 16 min read

This tutorial explains how to use Anthropic's open‑source Model Context Protocol (MCP) to connect large language models with external data sources by building both MCP servers and clients in Node.js/TypeScript, covering architecture, transport options, SDK usage, and practical code examples.
Function CallingLLM integrationMCP
0 likes · 16 min read

This step‑by‑step guide shows how to obtain a DeepSeek API key, set up an Alibaba Cloud ECS instance, configure the WeChat public platform, clone the open‑source COW project, edit its JSON configuration, and run the service so that a WeChat public account can interact with the DeepSeek large language model.
API keyBackend tutorialDeepSeek
0 likes · 12 min read

Facing inconsistent metrics and low reuse in siloed data services, the team built a unified metric service using a headless BI semantic layer and virtual data models, enabling consistent metric definitions, reusable data models, AI-friendly queries, and faster, scalable reporting across the organization.
Data ModelingHeadless BILLM integration
0 likes · 17 min read

This guide shows how to create a Cursor‑style AI‑native IDE by forking the open‑source CodeFuse project built on the extensible OpenSumi framework, configuring a large‑language model, and packaging an Electron app, while explaining Cursor’s advantages over plugin‑based tools and the strategic benefits of a fully integrated AI development environment.
AI IDECodeFuseCursor
0 likes · 17 min read

GPT‑4o’s speech multimodal system discretizes audio into semantic and acoustic tokens, integrates these tokens with large language models through multi‑stage instruction tuning, and employs hierarchical zero‑shot text‑to‑speech decoding, enabling low‑latency, streaming, and prompt‑driven voice synthesis for applications like gaming.
AudioLMGPT-4oLLM integration
0 likes · 33 min read

With the rise of LLMs, vector search and vector databases have become essential for extending model memory, and this article explains the principles, algorithms, design choices, implementation details, and performance results of ByteHouse’s cloud‑native vector retrieval engine.
ANNByteHouseKNN
0 likes · 14 min read

This article outlines three practical approaches—direct prompting, retrieval‑augmented generation (RAG), and fine‑tuning—to connect enterprise applications to large language models, explains key prompt‑engineering techniques, details RAG workflow and vector‑database integration, and provides step‑by‑step guidance for fine‑tuning on the KubeAI platform.
AI for businessKubeAILLM integration
0 likes · 20 min read

This article explains the fundamentals of vector databases, how high‑dimensional vector data is generated and stored, reviews common ANN search algorithms such as Flat, k‑means and LSH, discusses benchmarking and product selection, and demonstrates practical integration of vector stores with LLMs using LangChain and Python code.
ANNLLM integrationPython
0 likes · 17 min read

This article explores the rise of generative AI, outlines popular models like ChatGPT, DALL‑E, and Google Bard, examines their limitations, and then delves into Elasticsearch’s Relevance Engine and vector capabilities, demonstrating how to store, index, and query dense embeddings with practical code examples.
ElasticsearchGenerative AILLM integration
0 likes · 17 min read


DevOpsJan 4, 2024 · Artificial Intelligence
This article explains Microsoft’s open‑source Semantic Kernel SDK, describing its purpose, core components, workflow (Ask, Planner, Skills, Memory, Connectors, Pipeline), practical examples, and the advantages it brings to developers building Copilot‑style AI applications.
AI SDKAI pluginsLLM integration
0 likes · 13 min read

Douyin tackled vector‑retrieval challenges by optimizing HNSW and creating a high‑performance IVF algorithm, implementing custom scalar quantization, SIMD acceleration, and a DSL‑driven engine that merges filtering with search, then built a cloud‑native, storage‑compute‑separated vector database (VikingDB) delivering sub‑10 ms latency, real‑time updates, multi‑tenant support, and secure, scalable retrieval for LLM‑driven applications.
ANNLLM integrationStorage-Compute Separation
0 likes · 18 min read


phodalJul 23, 2023 · Artificial Intelligence
AutoDev is an AI‑assisted JetBrains IDE plugin that connects to issue trackers, automates prompt generation, enforces code standards, supports multiple languages and LLM providers, and offers smart prompt strategies, aiming to reduce developer interaction costs while improving generated code quality.
AI codingAutoDevLLM integration
0 likes · 9 min read


21CTOJul 11, 2023 · Artificial Intelligence
Microsoft’s newly released Semantic Kernel (SK) is an open‑source SDK that blends large language models with traditional programming languages, offering features like prompt chaining, recursive reasoning, memory management, and planner integration, while outlining a roadmap that includes vector database support and Azure Cognitive Search.
AI SDKLLM integrationai-development
0 likes · 5 min read


ByteFEApr 3, 2023 · Artificial Intelligence
This comprehensive tutorial demonstrates how to leverage the official ChatGPT API and advanced prompt engineering techniques to develop a command-line tool that translates natural language instructions into precise shell commands, covering iterative prompt design, constraint implementation, and Node.js integration.
AI toolsCLI DevelopmentChatGPT API
0 likes · 15 min read
