langchain

library1.3.17pypypi✓ verified 26d ago

LangChain is an orchestration framework for building LLM-powered applications and agents. It provides abstractions for chaining model calls, tool use, memory, and multi-agent coordination. As of v1.0, LangGraph is the foundational runtime for stateful agent execution.

llm-agents ai-ml

pip install langchain langchain-openai langchain-anthropic

github ↗package ↗homepage ↗docs ↗changelog ↗

INSTALL

IMPORT

SIG · LANGCHAIN

langchain

llm-agentspythonv1.3.17

Install

12.4s avg

Import

5194ms

Disk

130MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.3.17 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

installs and imports cleanly · install 0.0s · import 5.384s · 120.5MB

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 12.4s · import 5.004s · 128MB

130MB installed

● package 130MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

ChatOpenAI

✓ from langchain_openai import ChatOpenAI

✗ from langchain import ChatOpenAI

Moved to partner package in 0.2. Wrong import raises ImportError in 1.0.

ChatAnthropic

✓ from langchain_anthropic import ChatAnthropic

✗ from langchain import ChatAnthropic

Moved to partner package in 0.2. Wrong import raises ImportError in 1.0.

create_agent

✓ from langchain import create_agent

✗ from langgraph.prebuilt import create_react_agent

create_react_agent still works in 1.0 but create_agent is now the idiomatic entry point.

Minimal LLM call using ChatOpenAI in LangChain 1.0.

from langchain_openai import ChatOpenAI llm = ChatOpenAI(model='gpt-4o', temperature=0) response = llm.invoke('What is the capital of France?') print(response.content)

langchain --version

Debug

Known issues

breakingAgentExecutor is removed in v1.0. Use create_agent instead.

fix

Replace AgentExecutor with create_agent from langchain

affects: < 1.0.0

breakingLCEL pipe syntax (prompt | llm | parser) is deprecated. Use explicit chaining.

fix

Use create_agent or direct llm.invoke() calls

affects: < 1.0.0

breakinglangchain-community does not follow semver. Breaking changes can occur in minor releases.

fix

Pin langchain-community version explicitly in requirements.txt

affects: all

gotchapip install langchain alone is insufficient. Provider packages must be installed separately.

fix

Always install langchain-openai or langchain-anthropic alongside langchain

affects: all

deprecatedastream_events(version='v1') uses vulnerable serialization. Use v2.

fix

astream_events(version='v2')

affects: < 1.0.0

gotchaOpenAI API key is missing. Set OPENAI_API_KEY environment variable or pass `api_key` directly to the client.

fix

Set the OPENAI_API_KEY environment variable or pass `openai_api_key='your_api_key'` to `ChatOpenAI`.

affects: all

Upgrade

Version history

1.3.17latest on PyPI · released Aug 25, 2026

Audit

Dependencies

langchain-openairequiredRequired for OpenAI model access. Not included in base langchain package.

langchain-anthropicrequiredRequired for Anthropic/Claude model access. Not included in base langchain package.

langgraphoptionalRequired for stateful multi-agent workflows. Foundational runtime in v1.0.

Agent activity

70 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/langchain-ai/langchain ↗

packagehttps://pypi.org/project/langchain/ ↗

homepagehttps://langchain.com ↗

docshttps://reference.langchain.com/python/langchain/langchain/ ↗

changeloghttps://github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain%3D%3D1%22 ↗