Focused on deep research and development of large-model applications. Authors of "RAG Application Development and Optimization Based on Large Models" and "MCP Principles Unveiled and Development Guide". Primarily B2B, with B2C as a supplement.
This article explains why GUI agents are needed, defines their multimodal capabilities, walks through a high‑level automation scenario, details the architecture of large‑model‑driven GUI agents, highlights recent open‑source projects, and compares them with traditional RPA solutions.
This article introduces CrewAI, a high‑level Python framework for constructing multi‑agent systems, explains its core concepts such as Crew, Agent, Tool, Task and Process, walks through a complete demo with code, evaluates its strengths and limitations, and showcases the new Flows feature for more flexible workflow orchestration.
This article explains the hallucination problem of large language models, introduces Retrieval‑Augmented Generation (RAG) as a solution, compares RAG with model fine‑tuning, and outlines basic RAG architecture and workflow for practical applications.
This article explores how compact multimodal models like OmniVision-968M enable efficient generative AI on edge devices, detailing their architectural advantages, benchmark superiority over larger models, and step‑by‑step instructions for local installation and visual inference using NexaSDK.
This article walks through implementing a multi‑agent workflow using LangGraph, comparing it with the lightweight Swam framework, and detailing the code for defining models, tools, agents, graph structures, testing, and evaluating the framework's strengths, limitations, and suitable use cases.
This article introduces the concept of multi‑agent systems, compares five popular orchestration frameworks, and provides a step‑by‑step tutorial for building and testing a simple supervision‑based workflow using OpenAI's experimental Swam library, complete with code snippets and performance observations.
This guide explains how to overcome the limitations of text‑only embeddings for enterprise AI search by using a multimodal embedding model to index and retrieve both text and images, detailing the full workflow, code examples, and performance benefits.
Incremental knowledge updates in Retrieval‑Augmented Generation (RAG) systems can be achieved by using document‑level or chunk‑level strategies, leveraging hash fingerprints, record managers, and framework‑specific APIs such as LangChain’s index() with cleanup modes or LlamaIndex’s ingestion pipeline, reducing redundant computation and cost.
This tutorial explains why AI agents need durable, personalized long‑term memory, introduces the open‑source Mem0 solution, shows how Mem0 works with LLMs and vector stores, and provides step‑by‑step code to integrate Mem0 into a LangGraph workflow for adaptive, user‑specific interactions.
This guide walks through setting up the open‑source Kotaemon framework, configuring Azure Document Intelligence and a visual large model, and implementing code to extract and caption images and tables from PDFs for end‑to‑end multimodal RAG applications.
