How to beginner · 3 min read

How to use Gemini API with LangChain

Q: How to use Gemini API with LangChain

Use the gemini-1.5-pro or gemini-2.0-flash model with LangChain by installing langchain_openai, setting your OPENAI_API_KEY environment variable, and creating a ChatOpenAI instance specifying the Gemini model. Then pass this instance to LangChain chains or prompts for chat completions.

Quick answer

Use the gemini-1.5-pro or gemini-2.0-flash model with LangChain by installing langchain_openai, setting your OPENAI_API_KEY environment variable, and creating a ChatOpenAI instance specifying the Gemini model. Then pass this instance to LangChain chains or prompts for chat completions.

PREREQUISITES

Python 3.8+
OpenAI API key (set as OPENAI_API_KEY in environment)
pip install langchain_openai>=0.2.0

Setup

Install the langchain_openai package to access Gemini models via LangChain. Ensure your OPENAI_API_KEY environment variable is set with your Google Gemini API key.

Run this command to install:

bash

pip install langchain_openai>=0.2.0

Step by step

This example shows how to create a LangChain ChatOpenAI client using the Gemini model and generate a chat completion.

python

import os
from langchain_openai import ChatOpenAI

# Initialize the LangChain ChatOpenAI client with Gemini model
chat = ChatOpenAI(model_name="gemini-1.5-pro", temperature=0.7)

# Define a simple chat prompt
messages = [{"role": "user", "content": "Explain LangChain integration with Gemini API."}]

# Generate completion
response = chat(messages)
print(response.content)

output

LangChain integrates with Gemini API by using the ChatOpenAI wrapper, allowing you to call Gemini models seamlessly for chat-based AI tasks.

Common variations

You can switch models by changing model_name to gemini-2.0-flash for faster responses or lower latency. LangChain also supports async calls with await chat.agenerate() in async functions.

Example for async usage:

python

import asyncio
from langchain_openai import ChatOpenAI

async def main():
    chat = ChatOpenAI(model_name="gemini-2.0-flash", temperature=0.5)
    messages = [{"role": "user", "content": "What is LangChain?"}]
    response = await chat.agenerate(messages)
    print(response.generations[0][0].text)

asyncio.run(main())

output

LangChain is a framework that simplifies building applications with language models like Gemini by providing composable chains and prompt management.

Troubleshooting

If you get authentication errors, verify your OPENAI_API_KEY is correctly set in your environment.
For model not found errors, confirm you are using a valid Gemini model name like gemini-1.5-pro or gemini-2.0-flash.
Timeouts may require lowering temperature or using the faster gemini-2.0-flash model.

✅

Key Takeaways

Use ChatOpenAI from langchain_openai to access Gemini models in LangChain.
Set your Gemini API key as OPENAI_API_KEY in the environment for authentication.
Switch between gemini-1.5-pro and gemini-2.0-flash models for different speed and quality trade-offs.

Verified 2026-04 · gemini-1.5-pro, gemini-2.0-flash

Verify ↗