Gemini Google

Created

Created

2023 May 10 17:23

Editor

Editor

Creator

Creator

Edited

Edited

2025 Mar 27 21:17

Refs

Refs

dvlab-research • Updated 2024 Dec 22 10:32

Stubbs

A feature where you can create working apps directly in a site with just one prompt

Google plans to integrate the AI technology into products like Chrome DevTools, and Firebase.

Gemini Google Versions

Gemini API Parameters (‣)

logprobs

candidateCount

seed

presencePenalty , frequencyPenalty

Gemini Canvas

Multimodal Canvas

Multimodal Canvas

https://labs.google/multimodal-canvas

Released

Gemini - Google DeepMind

Gemini is built from the ground up for multimodality — reasoning seamlessly across image, video, audio, and code.

Gemini - Google DeepMind

https://deepmind.google/technologies/gemini/#capabilities

Gemini - Google DeepMind

https://arxiv.org/pdf/2312.11805.pdf

emultimodal

Gemini is coming to Makersuite & so are Stubbs

The first ever look at the multimodal Gemini and an extra, secret tool that Google has hidden from everyone, leaked as well.

Gemini is coming to Makersuite & so are Stubbs

https://medium.com/@bedros-p/gemini-is-coming-to-makersuite-so-are-stubbs-32248f3924aa

Gemini is coming to Makersuite & so are Stubbs

Gemini: Google's Latest AI Challenging GPT-4

Google's new AI project, Gemini, is set to redefine the industry with its multimodal capabilities and challange GPT-4. As a network of models under the Generalized Multimodal Intelligence Network, Gemini excels in handling a variety of data types and tasks, from text, images, to audio and video, leveraging a unique architecture that merges a multimodal encoder and decoder. Gemini adjusts easier than other big language systems like GPT-4, making it able to offer new and exciting experiences and solve a wide range of problems. Become a Member of the channel and Supporter of AI Revolution → https://www.youtube.com/channel/UC5l7RouTQ60oUjLjt1Nh-UQ/join #ai #gemini #google

Gemini: Google's Latest AI Challenging GPT-4

https://www.youtube.com/watch?v=gwEuvrI4fx4

Gemini: Google's Latest AI Challenging GPT-4

Enum mode
AI Guardrail

Generate structured output with the Gemini API | Google AI for Developers

Learn how to generate JSON output with the Gemini API

Generate structured output with the Gemini API | Google AI for Developers

https://ai.google.dev/gemini-api/docs/structured-output?lang=python#use-an-enum

Generate structured output with the Gemini API | Google AI for Developers

function calling

Intro to function calling with the Gemini API | Google AI for Developers

Function calling lets you connect models to external tools and APIs. Instead of generating text responses, the model understands when to call specific functions and provides the necessary parameters to execute real-world actions. This allows the model to act as a bridge between natural language and real-world actions and data. Function calling has 3 primary use cases:

Intro to function calling with the Gemini API | Google AI for Developers

https://ai.google.dev/gemini-api/docs/function-calling

Intro to function calling with the Gemini API | Google AI for Developers

Recommendations

///////