langchain-dependencies

Select and pin correct LangChain, LangGraph, and LangSmith package versions for Python and TypeScript projects.

Updated Jul 16, 2026
One-click install
npx skills add https://github.com/flemx/salesforce-langgraph-agent --skill langchain-dependencies-flemx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: langchain-dependencies
Source: https://github.com/flemx/salesforce-langgraph-agent/tree/main/.agents/skills/langchain-dependencies
Command: npx skills add https://github.com/flemx/salesforce-langgraph-agent --skill langchain-dependencies-flemx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up a LangChain project often leads to version conflicts, deprecated imports, and broken installs because the ecosystem is split across many independently-versioned packages. This Skill provides the exact packages, minimum versions, and pinning strategies needed to avoid incompatibilities. ## Core Features & Use Cases - Package Selection Guidance: Lists required core packages, orchestration options (LangGraph vs Deep Agents), model provider integrations, and tool/retrieval packages for both Python and TypeScript. - Versioning & Upgrade Policy: Explains which packages follow semver, which do not (langchain-community), and how to pin each safely. - Ready-to-Use Templates: Provides minimal requirements.txt and package.json dependency sets for LangGraph, Deep Agents, and tool-equipped projects. - Use Case: When starting a new LangGraph agent project, use this Skill to generate a correct requirements.txt with langchain>=1.0, langgraph, langsmith, and the right model provider package, avoiding legacy 0.3 versions and deprecated community imports. ## Quick Start Ask the agent to set up dependencies for a new LangGraph Python project using Anthropic as the model provider.

Frequently Asked Questions about langchain-dependencies

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up dependencies for a new LangChain project?

Install langchain>=1.0, langchain-core>=1.0, and langsmith>=0.3.0 as the core set, then add langgraph or deepagents for orchestration plus your model provider package such as langchain-openai or langchain-anthropic. Python 3.10+ or Node.js 20+ is required.

LangGraph vs Deep Agents: which should I use?

Use LangGraph when you need fine-grained control over custom graphs, loops, and branching. Use Deep Agents when you want batteries-included planning, memory, and file context out of the box. They are alternatives, not a required stack.

Why does langchain-community break after upgrading?

langchain-community does not follow semantic versioning, so minor releases can contain breaking changes. Pin it to an exact minor series like >=0.4.0,<0.5.0, or switch to a dedicated integration package such as langchain-chroma when one exists.

Can I use LangChain 0.3 for a new project?

No. LangChain 0.3 is legacy maintenance-only until December 2026 and receives no new features. Always start new projects on LangChain 1.0, the current LTS release, using a constraint like langchain>=1.0,<2.0.

Why is @langchain/core missing in my TypeScript monorepo?

@langchain/core is a peer dependency and is not always hoisted automatically in yarn workspaces or monorepos. You must list it explicitly in your package.json dependencies alongside langchain and @langchain/langgraph.