langchain-gradientai

langchain-gradientai

This package contains the LangChain integration with DigitalOcean

Installation

pip install -U langchain-gradientai

And you should configure credentials by setting the DIGITALOCEAN_INFERENCE_KEY environment variable:

• Log in to the DigitalOcean Cloud console
• Go to the GradienAI Platform and navigate to Serverless Inference.
• Click on Create model access key, enter a name, and create the key.
• Use the generated key as your DIGITALOCEAN_INFERENCE_KEY:

Create .env file with your access key:
DIGITALOCEAN_INFERENCE_KEY=your_access_key_here

Chat Models

ChatGradientAI class exposes chat models from langchain-gradientai.

Invoke

import os
from dotenv import load_dotenv
from langchain_gradientai import ChatGradientAI

load_dotenv()

llm = ChatGradientAI(
    model="llama3.3-70b-instruct",
    api_key=os.getenv("DIGITALOCEAN_INFERENCE_KEY")
)

result = llm.invoke("What is the capital of France?.")
print(result)

Stream

import os
from dotenv import load_dotenv
from langchain_gradientai import ChatGradientAI

load_dotenv()

llm = ChatGradientAI(
    model="llama3.3-70b-instruct",
    api_key=os.getenv("DIGITALOCEAN_INFERENCE_KEY")
)

for chunk in llm.stream("Tell me what happened to the Dinosaurs?"):
    print(chunk.content, end="", flush=True)

More features coming soon.