#LangChain
172 related articles
Forge: An Open-Source, Self-Hosted Visual Builder for AI Agents
Forge is a MIT-licensed, self-hosted open-source visual AI agent builder. Assemble agents, tools, and RAG on a canvas with built-in observability, JMESPath token trimming, and flexible deployment.
LangChain + Amazon Bedrock: How Agentic Retrieval Tackles Multi-Part Questions
Learn how agentic retrieval with LangChain and Amazon Bedrock Managed Knowledge Bases handles complex multi-part queries that single-shot RAG can't, with trace event comparisons and cost analysis.
CSL-Core: Adding Verifiable Security Policies to LangChain Agent Tool Calls
CSL-Core is an open-source CLI that adds Z3-verified security policies to every LangChain tool call — blocking risky actions without modifying prompts.
LangChain Releases langchain-openai 1.6.5: Enhanced Tool Calling Capabilities
langchain-openai 1.6.5 adds dynamic mid-conversation tool set changes via SystemMessage and new model profile support for OpenAI and Anthropic.
LangChain-Fireworks 1.7.0 Released: Introduces Prompt Caching Middleware
LangChain-Fireworks 1.7.0 is out with a new prompt caching middleware, improved streaming timeout classification, and refreshed model profiles for Fireworks AI users.
LangChain Core 1.6.6 Released: Claude Sonnet 5.5 Support and Documentation Fixes
LangChain Core 1.6.6 is released with Claude Sonnet 5.5 compatibility support and docstring example fixes. A low-risk patch update for LLM app developers.
LangChain-OpenAI 1.6.7 Released: Adds Azure Workload Identity Support
LangChain-OpenAI 1.6.7 adds Azure workload identity auto-discovery, refreshes model configuration data, and removes retired Completions endpoint tests.
LangChain Text Splitters 1.1.3 Released: Dependency Upgrades and Multi-Language Splitting Fixes
LangChain Text Splitters 1.1.3 fixes separators for Kotlin, Rust, C# and more, adds type validation to RecursiveJsonSplitter, restores lazy imports, and upgrades security dependencies.
LangSmith Practical Guide: Building Full LLMOps Workflows with Python
LangSmith is a LangChain LLMOps platform. This guide covers tracing, dataset evaluation, LLM-as-a-judge, Playground, Prompt management, annotation queues, monitoring, and a document extraction case study in Python.
Building an AI Agent from Scratch: A Beginner's Guide to Developing Your Own Intelligent Agent
AI Agents are the next evolution of AI. This guide covers how Agents differ from ChatGPT, enterprise use cases, market growth, and a beginner LangChain-based learning path.
MockAgent: A Tool Mock Gateway Built for Testing LangChain Agents
MockAgent is a lightweight mock and Schema validation gateway for LangChain agents. It uses real-time AJV validation, structured error feedback, and trajectory logging to solve Schema drift, API quota waste, and staging pollution in local Agent testing.
MockAgent: A Tool Mocking and Schema Validation Gateway for LangChain Agents
MockAgent is a lightweight tool mocking and schema validation gateway for LangChain agents, enabling reproducible testing without real external dependencies.
LangChain + MCP in Practice: Understanding Agent Tool Calling from the Ground Up
Learn how LangChain, Agents, and MCP work together. Understand tool calling, conversation history, and multi-turn decision-making in AI agent development.
langgraph-jev: Building Type-Safe Decision Nodes for LangGraph
langgraph-jev wraps TypeSafe's Jev API as typed LangGraph decision nodes, offering typed I/O, confidence scoring, and deterministic routing for reliable AI agent workflows.
How to Solve LangChain Agent Tool Schema Hallucinations with a Mock Gateway
LangChain agents often crash mid-loop due to JSON Schema hallucinations. Learn how a Mock Gateway with AJV validation and structured error feedback enables self-correction.
LangChain Beginner's Guide: What Problems Does It Actually Solve for LLMs?
A beginner's guide to LangChain: learn how this LLM framework solves knowledge cutoffs, external system access, and state persistence — with docs tips included.
The Hidden Problem with AI Agent Tools: Why They Often Can't Tell You If They Succeeded
Agent tools often return output without truly succeeding. This article explores how silent failures compound in chained tasks and offers practical design advice.
Google Custom Search API Deprecation: Migration Guide for LangChain's Search Wrapper
Google is retiring its Custom Search JSON API, breaking LangChain's GoogleSearchAPIWrapper. Learn the temporary client-swap fix and how to migrate to Tavily or Brave Search.
Building Enterprise-Grade Agents from Scratch: A Deep Dive into LangChain 1.0's Core Capabilities
A systematic breakdown of AI Agent concepts, software paradigm evolution, and LangChain 1.0's six major upgrades including the unified create_agent interface — ideal for Agent development beginners.
langchain-halu: Adding an LLM Hallucination Detection Layer to LangChain
langchain-halu is an open-source LangChain integration that embeds LLM hallucination detection into LCEL chains via annotate, gate, and auto-retry strategies, returning calibrated probabilities and error types.