---
id: langchain-google-genai
version: "4.3.4"
license: MIT
license_treatment: permissive
maintenance: active
---

# langchain-google-genai — An integration package connecting Google's genai package and LangChain

License: permissive · Maintenance: active · Downloads: 17.7M/mo

## What it is and what it does

This package bridges Google's Gemini generative AI models into the LangChain framework, allowing developers to use Google's chat, vision, and embedding capabilities as components within LangChain workflows. It wraps the google-genai package and exposes Gemini functionality through LangChain's standard interfaces, enabling code written for other providers to swap in Gemini with minimal changes.

The package depends on langchain-core for base abstractions, pydantic for data validation, google-genai for the underlying API client, and filetype for content type detection. It requires Python 3.10 or later and is actively maintained.

Use it for:

- Build a chatbot using Gemini's chat models within LangChain without rewriting provider-specific code.
- Generate embeddings for semantic search or RAG pipelines using Gemini through LangChain.
- Process images with Gemini's vision capabilities as part of a LangChain agent or chain.
- Prototype multi-model AI applications by swapping between Gemini and other providers via LangChain's API.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates Google's Gemini AI models (chat, vision, embeddings) into LangChain applications through a unified interface.

Yes. Active maintenance, low install friction, permissive MIT license, and no known vulnerabilities make this a solid choice if you need Gemini within LangChain. Verify you have Google API credentials and understand quota constraints before deploying.

## Install

pip install langchain-google-genai
uv add langchain-google-genai
poetry add langchain-google-genai

## Installing langchain-google-genai

Before you install: Low install friction with a pure Python wheel. Actively maintained with a release on 2026-08-14. Depends on langchain-core, google-genai, pydantic, and filetype.

License in practice: MIT license permits commercial and private use with minimal restrictions, suitable for most projects.

Quickstart:

pip install langchain-google-genai

from langchain_google_genai import ChatGoogleGenerativeAI

model = ChatGoogleGenerativeAI(model="gemini-pro")

Google API credentials must be configured (typically via GOOGLE_API_KEY environment variable) before instantiating any model.

Verify before relying:

- Whether Google API credentials or authentication setup is required before use
- Rate limits or quota constraints on Gemini API calls through this integration
- Specific capabilities and models available through each integration point (chat, vision, embeddings)

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 17.7M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

langchain google gemini integration, google genai langchain, gemini chat embeddings langchain, google generative ai langchain, langchain google ai provider, langchain-integration, generative-ai

[View on SkillFed](https://skillfed.io/packages/langchain-google-genai) · [View on PyPI](https://pypi.org/project/langchain-google-genai/)