LangChain
30 articles tagged with this topic
AI Engineers' Real Barrier Isn't LangChain—This Project Lays Bare the Stack
calmrocks' zero-framework Colab tutorials went viral on GitHub. We're watching the deeper signal: the AI engineer role is stratifying by who truly und
AI Agent Instability Isn't the LLM's Fault — It's the Harness Engineering
Open-source MyCodeAgent teardown: AI Agent reliability hinges on Harness engineering, not the LLM. Three key choices and four overlooked risks.
AI Assistants' 'Amnesia' Is Now a Business — DSH-Style Frameworks Step In
DSH is an open-source context framework for AI Agents. We dissect why AI assistants forget and the engineering behind it—for users and enterprise IT.
Alibaba Cloud, 3 Agent Frameworks: Industry Shifts from 'Build' to 'Maintain'
Alibaba Cloud + AgentScope, LangChain, Dify tour BJ/SZ/SH. Theme shifts from 'build' to 'evaluate'—from can we build to can we reliably run.
AI Agent Tool Selection: Don't Dump Everything In — An AI Pharma Paper's Fix
Three tool-filtering modes for AI Agents — LLM, embedding, all-in. An AI pharma paper exposes real cost-vs-accuracy tradeoffs in enterprise rollouts.
LangChain Lowers Agent Engineering Barrier with Six Execution Checkpoints
LangChain turns permissions, retries, and monitoring into pluggable middleware via six execution points. Enterprise competition shifts from model answ
Agent Learning's Real Threshold: Reciting Concepts ≠ Using Them Correctly
After Agent basics, a developer's 6 Q&As: Chatbot vs Agent, streaming Tool Calling, Loop stopping, context trade-offs. Demo proves chain, not producti
Long-Task Agents 'Lose Their Memory'—The Real Problem Is Unmanaged Context
Context ledgers assign each item a source, utility, expiry, risk, and eviction policy, keeping long-task agents reliable without ever-larger windows.
DeepSeek Makes Agent Dev Lego-Like — Can LangChain Stay on Top?
DeepSeek open-sources Harness and Cordis (MIT license), turning Agent dev into protocol assembly. LangChain's moat meets its first serious Chinese cha
14,000 Lines of Python Expose AI Code Agent's Black Box
A developer built a 14K-line Python code agent without LangChain, exposing CLI, dependency assembly, and ReAct loop. The black box is opening.
Why Enterprise AI Gets It Wrong: It's Not the Model, It's Document Splitting
Deep-dive on RAG's most overlooked step: document splitting. When AI misreads your docs, the chunker — not the LLM — is usually to blame.
Enterprise AI Knowledge Bases Miss the Mark: 80% of Work Is Document Loading
Enterprise RAG projects fail because documents aren't AI-ready. LangChain's Document abstraction solves this hidden 'first mile.'
LangChain Has Rewritten Its Memory Architecture 8 Times in 3 Years — AI Tool Immaturity Is More
LangChain, the most mainstream AI app framework, has switched memory designs 8 times in three years, archiving the entire legacy system under "classic
Five "Engineering" Terms in Six Months: What's Really Happening in AI Coding
From Prompt to Loop to Graph — five engineering terms in six months. Not marketing fluff, but concrete problems in shipping AI Agents.
LangChain 1.x Makes Agent the Main Line — The Assembly Era of AI Development Is Taking Shape
LangChain, the world's most widely used AI app framework, pivots fully to Agent: Model + Harness as the standard formula. Building AI apps is becoming
Build a Local AI Knowledge Base: LangChain + Ollama Make PDF Q&A Simple
A hands-on guide using LangChain with Qwen2 and bge-m3 to build an offline RAG knowledge base that answers PDF questions on your own machine.
Enterprise RAG in Practice: The Bottleneck Is Docs and Retrieval, Not Models
A real enterprise deployment shows RAG succeeds or fails less on model size than on document parsing, chunking, retrieval, and citations.
Chunking Isn’t a Minor Tweak—it Determines Whether RAG Really Works
RAG often fails not because of the model, but because document chunking breaks retrieval, cost, and answer quality.
LangChain: AI Agents Load Skills On-Demand — Modular Dev Is the New Agent Paradigm
LangChain DeepAgent: AI agents load skill modules on-demand like humans, shifting Agent development from monolithic to pluggable composition for custo
LangChain DeepAgents v2 Streams Progress — Opaque Agents Have No Commercial Value
LangChain updates DeepAgents streaming, solving multi-agent black-screen waits. We judge: real-time AI transparency is make-or-break for user retentio
LangChain's Context Engineering: Cramming AI With Data Makes It Dumber
More data makes LLMs dumber. LangChain's Context Engineering systematically manages AI's "field of view," marking a shift from parameter rivalry to en
agui Exposes AI Chat Flaw: Streaming Fails, Tool Calling Needs Unified UI Protocol
agui unifies text, tool calls, and errors into one stream. It fixes UX collapse during AI tool use, evolving frontends from typewriters to true protoc
RAG's Five Stages: LLMs Embrace Open-Book Exams as Enterprise Standard
RAG is the enterprise LLM standard, enabling "open-book exams" via knowledge retrieval. But accuracy, engineering complexity, and data cleaning remain
LangChain Dismantles Omnipotent AI: Multi-Agent Becomes Pragmatic Enterprise Choice
LangChain replaces omnipotent AI with specialized multi-agent collaboration. This cures tool-selection errors, shifting AI from tech demos to true bus
900K-Token RAG Test: Simplest Line Split Wins; Enterprise KBs Stop Overpaying
Most enterprise RAG projects fail at chunking. Latest 900K-token benchmark: simplest line splitting is most accurate. Chunking strategy > model choice
LangChain Breaks AI Into 4 Components: Orchestration Layer, Not Just Framework
LangChain splits AI into Chain, Agent, Memory, Tool. It's an orchestration layer shifting LLMs from "talking" to "doing"—crucial for anyone tracking A
AI Interviews Now Ask 'How to Handle Agent Failures'—Engineering Beats Jargon
Interviews now probe failure recovery over definitions. This signals Agent dev is in deep engineering—jargon isn't enough; you need real crash experie
LangChain Agent Teardown: LLM Deployment Demands Control, Not Just Convenience
LangChain dissects Agent graph internals and ReAct reasoning loops. Dev shifts from high-level APIs to graph orchestration—control trumps convenience
LangChain Teaches AI to Take Notes: Memory Is Agent Deployment's Lifeline
LLMs are inherently amnesic. LangChain's two-layer memory scheme solves Agent amnesia, determining if AI apps evolve from toys into tools.
Document Chunking Dictates AI Quality: Get It Wrong, and the Best Model Fails
60% of RAG success hinges on document chunking. Four strategies range from crude to precise; costs match results. This is often the biggest enterprise