At the Google I\/O developer conference on Tuesday<\/a>, Google announced an addition to its Firebase platform<\/a> that aims to make it easier for developers to build AI-powered applications in JavaScript\/TypeScript, with Go support coming soon.<\/p>\n Firebase Genkit is an open source framework, using the Apache 2.0 license, that enables developers to quickly build AI into new and existing applications.<\/p>\n Some of the use cases for Genkit that the company is highlighting Tuesday include many of the standard generative AI use cases: content generation and summarization, text translation and generating images.<\/p>\n \u201cPowerful large language models put AI-powered app features within reach, but building and refining these features beyond a prototype is hard,\u201d Google product manager Chris Gill and developer advocate Peter Friese wrote in Tuesday\u2019s announcement. \u201cMany of us are still figuring out how to deploy these features in production at scale and understand how they are performing so we can quickly iterate and improve on them. Add to this the need to balance safety and stability throughout the process and the problem becomes even harder. Let\u2019s face it, everyone can use some help.\u201d<\/p>\n The Firebase team promises that developers will be able to jump right into using Genkit because it uses the same approaches as the rest of the Firebase toolchain. Using Genkit, they\u2019ll be able to test their new features locally and then deploy their application with the help of Google\u2019s serverless platforms like Cloud Functions for Firebase and Google Cloud Run.<\/p>\n Because it\u2019s open source, developers will be able to extend Genkit as needed, but out of the box, it already supports a number of third-party open source projects. That means that on top of Google\u2019s own Gemini models, for example, developers can use open models via Ollama. Genkit will also support vector databases like Chrome, Pinecone and PostgreSQL\u2019s pgvector, in addition to Google Cloud Firestore.<\/p>\n \u201cGenkit is also designed to be open to any and all models, vector stores, embedders, evaluators, and other components through its plugin system,\u201d the team writes. <\/p>\n Google also notes that Project IDX<\/a>, Google\u2019s next-gen web-based integrated developer environment that is now generally available, will support Genkit\u2019s developer UI out of the box.<\/p>\n In addition to Genkit, the Firebase team also today announced support for SQL databases, powered by Firebase Data Connect, a new service powered by Google\u2019s Cloud SQL Postgres database. <\/p>\n Also new is Firebase App Hosting, which Google describes as \u201cnext generation of serverless web hosting with Google, designed specifically for server-rendered web apps.\u201d Firebase App Hosting is a serverless web hosting solution that will manage everything from building the application to the CDN for distributing content and server-side rendering for developers. <\/p>\n We\u2019re launching an AI newsletter! Sign up here<\/a> to start receiving it in your inboxes on June 5.<\/em><\/p>\n![\"\"](\"https:\/\/techcrunch.com\/wp-content\/uploads\/2024\/05\/295B2CAA-0968-4A9E-89AB-0CA2C3E46C2D.jpg?w=680\")
<\/figure>\n
![\"Read](\"https:\/\/techcrunch.com\/wp-content\/uploads\/2024\/05\/google-io-2024-banner.jpg\")
<\/a><\/p>\n<\/div>\n