Langchain Dependencies

<overview>

The LangChain ecosystem is split into focused, independently-versioned packages. Understanding which packages you need — and their version constraints — prevents incompatibilities and keeps upgrades predictable.

Key principles:

• LangChain 1.0 is the current LTS release. Always start new projects on 1.0+. LangChain 0.3 is legacy maintenance-only — do not use it for new work.
• langchain-core is the shared foundation: always install it explicitly alongside any other package.
• langchain-community (Python only) does NOT follow semantic versioning; pin it conservatively.
• LangGraph vs Deep Agents: choose one orchestration approach based on your use case — they are alternatives, not a required stack (see Framework Choice below).
• Provider integrations (model, vector store, tools) are installed separately so you only pull in what you use.

</overview>

Environment Requirements

<environment-requirements>

</environment-requirements>

Framework Choice

<framework-choice>

Pick one agent orchestration layer. You do not need both.

Both sit on top of langchain + langchain-core + langsmith.

</framework-choice>

Core Packages

<python-packages>

Python — always required

Python — orchestration (pick one)

Python — model providers (pick the one(s) you use)

Python — common tool & retrieval packages

These packages have tighter compatibility requirements — use the latest available version unless you have a specific reason not to.

langchain-community stability note: This package is NOT on semantic versioning. Minor releases can contain breaking changes. Prefer dedicated integration packages (e.g. langchain-chroma, langchain-tavily) when they exist — they are independently versioned and more stable.

</python-packages>

<typescript-packages>

TypeScript — always required

TypeScript — orchestration (pick one)

TypeScript — model providers (pick the one(s) you use)

TypeScript — common tool & retrieval packages

@langchain/core must be installed explicitly in yarn workspaces and monorepos — it is a peer dependency and will not always be hoisted automatically.

</typescript-packages>

Minimal Project Templates

<ex-langgraph-python>

<python>

Minimal dependency set for a LangGraph project (provider-agnostic).

# requirements.txtlangchain>=1.0,<2.0langchain-core>=1.0,<2.0langgraph>=1.0,<2.0langsmith>=0.3.0
# Add your model provider, e.g.:# langchain-openai# langchain-anthropic# langchain-google-genai

</python>

</ex-langgraph-python>

<ex-langgraph-typescript>

<typescript>

Minimal package.json dependencies for a LangGraph project (provider-agnostic).

{  "dependencies": {    "@langchain/core": "^1.0.0",    "langchain": "^1.0.0",    "@langchain/langgraph": "^1.0.0",    "langsmith": "^0.3.0"  }}

</typescript>

</ex-langgraph-typescript>

<ex-deepagents-python>

<python>

Minimal dependency set for a Deep Agents project (provider-agnostic).

# requirements.txtdeepagents            # bundles langgraph internallylangchain>=1.0,<2.0langchain-core>=1.0,<2.0langsmith>=0.3.0
# Add your model provider, e.g.:# langchain-anthropic# langchain-openai

</python>

</ex-deepagents-python>

<ex-deepagents-typescript>

<typescript>

Minimal package.json dependencies for a Deep Agents project (provider-agnostic).

{  "dependencies": {    "deepagents": "latest",    "@langchain/core": "^1.0.0",    "langchain": "^1.0.0",    "langsmith": "^0.3.0"  }}

</typescript>

</ex-deepagents-typescript>

<ex-with-tools-python>

<python>

Adding Tavily search and a vector store to a LangGraph project.

# requirements.txtlangchain>=1.0,<2.0langchain-core>=1.0,<2.0langgraph>=1.0,<2.0langsmith>=0.3.0
# Web searchlangchain-tavily          # use latest; partner package, semver
# Vector store — pick one:langchain-chroma          # use latest; partner package, semver# langchain-pinecone      # use latest; partner package, semver# langchain-qdrant        # use latest; partner package, semver
# Text processinglangchain-text-splitters  # use latest; semver
# Your model provider:# langchain-openai / langchain-anthropic / etc.

</python>

</ex-with-tools-python>

<ex-with-tools-typescript>

<typescript>

Adding Tavily search and a vector store to a LangGraph project.

{  "dependencies": {    "@langchain/core": "^1.0.0",    "langchain": "^1.0.0",    "@langchain/langgraph": "^1.0.0",    "langsmith": "^0.3.0",    "@langchain/tavily": "latest",    "@langchain/pinecone": "latest"  }}

</typescript>

</ex-with-tools-typescript>

Versioning Policy & Upgrade Strategy

<versioning-policy>

Breaking changes only happen in major versions (1.x → 2.x) for all semver-compliant packages. Deprecated features remain functional across the entire 1.x series with warnings.

Prefer dedicated integration packages over langchain-community. When a dedicated package exists (e.g. langchain-chroma instead of langchain-community's Chroma integration), use it — dedicated packages are independently versioned and better tested.

Community tool packages (Tavily, vector stores, etc.) should be kept at latest unless your project requires a locked environment. These packages frequently release compatibility fixes alongside LangChain/LangGraph updates.

</versioning-policy>

Environment Variables

<environment-variables>

All keys are read from the environment at runtime. Set only the keys for services you actually use.

# LangSmith (always recommended for observability)LANGSMITH_API_KEY=<your-key>LANGSMITH_PROJECT=<project-name>   # optional, defaults to "default"
# Model provider — set the one(s) you useOPENAI_API_KEY=<your-key>ANTHROPIC_API_KEY=<your-key>GOOGLE_API_KEY=<your-key>MISTRAL_API_KEY=<your-key>GROQ_API_KEY=<your-key>COHERE_API_KEY=<your-key>FIREWORKS_API_KEY=<your-key>TOGETHER_API_KEY=<your-key>HUGGINGFACEHUB_API_TOKEN=<your-key>
# Common tool/retrieval servicesTAVILY_API_KEY=<your-key>          # for Tavily searchPINECONE_API_KEY=<your-key>        # for Pinecone

</environment-variables>

Common Mistakes

<fix-legacy-version>

Never start a new project on LangChain 0.3. It is maintenance-only until December 2026.

# WRONG: legacy, no new features, security patches onlylangchain>=0.3,<0.4
# CORRECT: LangChain 1.0 LTSlangchain>=1.0,<2.0

</fix-legacy-version>

<fix-community-unpinned>

langchain-community can break on minor version bumps — it does not follow semver.

# WRONG: allows minor-version updates that may be breakinglangchain-community>=0.4
# CORRECT: pin to exact minor serieslangchain-community>=0.4.0,<0.5.0

Also consider switching to the equivalent dedicated integration package if one exists (e.g. langchain-chroma instead of the community Chroma integration).

</fix-community-unpinned>

<fix-community-tool-outdated>

Community tool packages like langchain-tavily and vector store integrations release compatibility fixes alongside LangChain updates. Using an old pinned version can cause import errors or broken tool schemas.

# RISKY: old pin may be incompatible with LangChain 1.0langchain-tavily==0.0.1
# BETTER: allow latest within the current majorlangchain-tavily>=0.1

</fix-community-tool-outdated>

<fix-community-import-deprecated>

Many tools that used to live in langchain-community now have dedicated packages with updated import paths. Always prefer the dedicated package import.

# WRONG — deprecated community import pathfrom langchain_community.tools.tavily_search import TavilySearchResultsfrom langchain_community.tools import WikipediaQueryRunfrom langchain_community.vectorstores import Chromafrom langchain_community.vectorstores import Pinecone
# CORRECT — use dedicated package importsfrom langchain_tavily import TavilySearch                  # pip: langchain-tavily (TavilySearchResults is deprecated)from langchain_community.tools import WikipediaQueryRun  # no dedicated pkg yetfrom langchain_chroma import Chroma                       # pip: langchain-chromafrom langchain_pinecone import PineconeVectorStore        # pip: langchain-pinecone

To find the current canonical import for any integration, search the integrations directory: https://python.langchain.com/docs/integrations/tools/

Each entry shows the correct package and import path. If a dedicated package exists, use it — the community path may still work but is considered legacy.

</fix-community-import-deprecated>

<fix-core-not-installed>

<typescript>

@langchain/core is a peer dependency — it must be in your package.json, especially in monorepos.

// WRONG: missing @langchain/core (breaks in yarn workspaces / strict hoisting){  "dependencies": {    "@langchain/langgraph": "^1.0.0"  }}
// CORRECT: always list @langchain/core explicitly{  "dependencies": {    "@langchain/core": "^1.0.0",    "@langchain/langgraph": "^1.0.0"  }}

</typescript>

</fix-core-not-installed>

<fix-python-version>

<python>

Python 3.9 and below are not supported by LangChain 1.0.

# Verify before installingimport sysassert sys.version_info >= (3, 10), "Python 3.10+ required for LangChain 1.0"

</python>

</fix-python-version>

<fix-node-version>

<typescript>

Node.js below 20 is not officially supported.

# Verify before installingnode --version   # must be v20.x or higher

</typescript>

</fix-node-version>