Google announces Firebase Genkit with Ollama support

2024-05-19 · Source: Ollama Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Novice, quick

Summary

Google announced Firebase Genkit at Google IO 2024, an open-source framework designed for developers to build, deploy, and monitor AI-powered applications. Released on May 20, 2024, Genkit includes native support for Ollama, enabling users to run Google's open-source Gemma model locally on their machines. The framework is compatible with MacOS, Windows, Linux, and Docker environments. Developers can get started by installing Genkit via npm, pulling the Gemma model using Ollama, and then initializing a new Node.js project. This setup allows Genkit to run locally on localhost:4000, providing a development environment for generative AI applications. NVIDIA also offers optimizations for Firebase Genkit on RTX GPUs.

Key takeaway

For AI Architects evaluating new generative AI development tools, Firebase Genkit offers a robust open-source framework with local model execution capabilities via Ollama. You should consider integrating Genkit into your development workflow to streamline the building, deployment, and monitoring of AI-powered applications, especially if local control over models like Gemma is a priority for your projects.

Key insights

Firebase Genkit is an open-source framework for building and deploying AI apps, supporting local model execution via Ollama.

Principles

• Open-source frameworks accelerate AI app development.
• Local model execution enhances developer control.

Method

Install Genkit, pull the Gemma model with Ollama, initialize a Node.js project, and run Genkit locally to develop AI applications.

In practice

• Run Gemma locally on diverse OS with Ollama.
• Monitor AI app performance with Genkit.
• Optimize Genkit apps using NVIDIA RTX GPUs.

Topics

• Firebase Genkit
• Ollama
• Gemma Model
• AI Development Frameworks
• Local LLM Deployment

Code references

• firebase/genkit

Best for: AI Architect, AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• OpenJarvis: a local-first personal AI is now available to run with Ollama — OpenJarvis provides a local-first, open-source framework for personal AI agents, prioritizing efficiency and user control over cloud reliance.
• Ollama's new app — Ollama has launched a new desktop application for macOS and Windows, offering an easier way to interact with local language models.
• Top 10: Open Source AI Platforms — The open-source AI ecosystem offers diverse platforms for efficient model deployment, application development, and community-driven innovation.
• Running AI Models Locally with Ollama Completely Changed My AI Journey — Ollama simplifies running advanced AI models locally, enhancing privacy, speed, and experimentation without cloud dependency.
• How to Implement Tool Calling with Gemma 4 and Python — Gemma 4 and Ollama enable local, privacy-first tool-calling agents for dynamic, real-world interactions.
• I've tested so many desktop AI tools, but Hermes with Ollama is my new favorite - here's why — Hermes, an autonomous AI desktop agent, integrates with Ollama to offer advanced features like memory, skills, and scheduled automations for complex tasks.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Ollama Blog.