How I Use Google's Gemini Pro with LangChain

Google's Gemini Pro is one of the newest LLMs publicly available, and to the surprise of some its relatively price competitive.

Its effectively free while you're developing, and after you development is complete its relatively cheap, costing around $0.00025 per 1K characters (characters, not tokens like OpenAI), which is slightly more expensive than GPT-3.5-Turbo, and $0.0025 per image, which is effectively the same as OpenAI's GPT-4).

Okay, I get it, how do I use it?

Let's start fresh with a new project. Assuming you're using Python >= 3.10, let's initialize a new virtual environment.

python -m venv env
source env/bin/activate

And let's install LangChain and our dotenv file loader first.

pip install langchain python-dotenv

Once that's done, we can install Gemini Pro's libraries and its LangChain adapter.

pip install google-generativeai langchain-google-genai

Next you need to acquire an API key, which can be done on the Google MakerSuite. In the top left of the page you should see a "Get API Key" button.

Click that button, then click "Create API Key in new project".

Copy the new API Key and save it to a .env file in your project directory.

GOOGLE_API_KEY=new_api_key_here

Now we can create a script that calls Gemini Pro via LangChain.

import os

from dotenv import load_dotenv
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")

llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=GOOGLE_API_KEY)

tweet_prompt = PromptTemplate.from_template("You are a content creator. Write me a tweet about {topic}.")

tweet_chain = LLMChain(llm=llm, prompt=tweet_prompt, verbose=True)

if __name__=="__main__":
    topic = "how ai is really cool"
    resp = tweet_chain.run(topic=topic)
    print(resp)

And that's it! You've now integrated Gemini Pro with LangChain! If you're interested in learning more about LangChain and AI, follow us here on Dev.to as well as on X! I also post a lot of AI and developer stuff on my personal X account! We also have more articles on LangChain an AI on our Dev Page!

Happy coding!