Granite Code on Replicate

This guide demonstrates using inference calls against a model hosted on Replicate. This guide will demonstrate a basic inference call using the replicate package as well as via LangChain. In both cases, you will provide a Replicate API Token. To see how you can use Ollama to host models locally instead, see how to build a VS Code Assistant with Granite.

Granite Code on Replicate

Jupyter notebook showing how to use Granite Code on Replicate

⌘I

Introduction

Granite Language Cookbook

Granite Vision Cookbook

Granite Speech Cookbook

Granite Guardian Cookbook

Granite Time Series Cookbook

Granite Code Cookbook

Agentic AI Cookbook

Model Evaluation Cookbook

Additional Cookbooks

Granite Code on Replicate

Granite Code on Replicate