Gemini
Gemini is Google's family of multimodal generative AI models and the conversational AI services built around them.
Starting Data Analytics with Generative AI and Python
A family of Google's generative AI models capable of processing and generating text and, in some variants, other modalities.
- How it is used
- Uses Gemini as a chat or API assistant for analytics tasks such as review searches and interpreting delivery patterns.
- How deep it goes
- Shows web access, a configured Vertex AI Python call, and a critique of generated review-filtering code; does not examine model internals.
- Examples
- Tests Portuguese positive-review extraction and uses interstate delivery-time disparities to elicit possible operational explanations.
- What you can do after
- Apply it via Gemini’s web interface or Vertex AI, then inspect generated code and verify analytical suggestions against data.
Read how Starting Data Analytics with Generative AI and Python explains Gemini →
AI for Everyday IT
Gemini is Google's family of generative AI models and assistants for processing and generating multimodal content.
- How it is used
- Deploys multimodal generation, Google Search, coding assistance, and Google Workspace support for everyday information and productivity tasks.
- How deep it goes
- Explains capabilities, account differences, workplace applications, and reliability limits without descending into model internals.
- Examples
- Uses Gmail conversation summaries, action-item extraction, web search, multimodal content, coding, translation, and account-comparison tables.
- What you can do after
- Apply it via Gemini or Gmail to summarize conversations, draft messages, search current information, and create multimodal content while verifying outputs.
WordPress Power Toolkit: Harness AI to build next-level websites
Gemini is Google's generative artificial intelligence service for interacting with and producing content from natural-language prompts.
- How it is used
- Supports information retrieval, cited responses, and assistance across Google products.
- How deep it goes
- Distinguishes large inputs from complex prompts but does not explain Gemini’s internal operation.
- Examples
- Uses supplying an entire blog for audience-appropriate promotion suggestions to illustrate large prompts.
- What you can do after
- Apply it via Gemini to retrieve information and work with large, clearly structured prompts.
Read how WordPress Power Toolkit: Harness AI to build next-level websites explains Gemini →
Generative AI in Action
Gemini is Google's multimodal AI model family for understanding and generating text, images, video, audio, and code.
- How it is used
- Positions Gemini as Google’s multimodal foundation model for reasoning, code generation, and cross-media AI tasks.
- How deep it goes
- Explains capabilities, multimodality, branding, and adaptation options without detailing model internals or implementation mechanics.
- Examples
- Demonstrates text, code, images, video, and audio processing alongside mathematics, physics, reasoning, and programming tasks.
- What you can do after
- Evaluate/understand Gemini’s multimodal scope, adaptation paths, and Google Cloud or AI Studio availability.
Software Testing with Generative AI
Gemini is a family of generative artificial-intelligence models and conversational services.
- How it is used
- Supports experimenting with large language model prompts through Google’s web and cloud platforms.
- How deep it goes
- Lists model versions, access routes, integrations, and performance context without explaining architecture or training internals.
- Examples
- Names Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini 1.0 Pro, and the Gemini web application.
- What you can do after
- Evaluate and experiment with Gemini models through Google’s web application or cloud access.
Read how Software Testing with Generative AI explains Gemini →
Data Analysis with LLMs
Gemini is Google's family of multimodal generative AI models for processing and generating content.
- How it is used
- Uses Gemini as a Google model alternative for asking questions through chat or Python.
- How deep it goes
- Shows chat features and a working Python call, but defers a full overview of the API.
- Examples
- Uses picture questions, inbox searches, and a Python prompt asking about the meaning of life.
- What you can do after
- Apply Gemini through its chat interface or Python library to generate answers to questions.
Build AI-Enhanced Web Apps
A Google Gemini model is a multimodal generative AI model in Google's Gemini model family that can provide embedding or generation capabilities.
- How it is used
- Uses Google Gemini models as the primary external AI provider for generative AI features in JavaScript web applications.
- How deep it goes
- Explains Gemini’s application role, integration stack, API-key setup, and runnable Next.js access, but not model internals.
- Examples
- Demonstrates a Next.js chat client configured with GEMINI_API_KEY, launched through npm, and visited at the root path.
- What you can do after
- Operate/configure a Next.js chat application that uses Gemini through an environment-stored API key.
Related concepts
- language modelkind of · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- ChatGPTalternative to · ChatGPT is OpenAI’s conversational AI service, which lets users interact with generative AI models and related tools through natural-language prompts.
- multimodalkind of · A multimodal model is a model that processes, generates, or relates information represented in two or more data modalities, such as text, images, audio, or video.
- conversational aikind of · Conversational AI is artificial intelligence that enables software systems to interact with users through natural-language dialogue.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.