# google-gemini/cookbook

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/google-gemini-cookbook).**

17,418 stars · 2,670 forks · Jupyter Notebook · Apache-2.0

## Links

- GitHub: https://github.com/google-gemini/cookbook
- Homepage: https://ai.google.dev/gemini-api/docs
- awesome-repositories: https://awesome-repositories.com/repository/google-gemini-cookbook.md

## Topics

`gemini` `gemini-api`

## Description

The Gemini Cookbook is a comprehensive collection of implementation patterns, code samples, and development guides designed for building applications with Google Gemini models. It serves as a central resource for developers to integrate multimodal generative artificial intelligence into their software, providing the necessary frameworks to manage model interactions, stateful workflows, and structured data extraction.

The repository distinguishes itself by offering specialized toolkits for autonomous agent orchestration, enabling the construction of agents that can execute code, browse the web, and perform multi-step tasks in sandboxed environments. It provides deep support for real-time conversational interfaces, including bidirectional streaming for audio, video, and text, as well as advanced capabilities for multimodal content generation and long-context data processing.

Beyond core model integration, the project covers a broad capability surface including retrieval-augmented generation, batch processing for high-throughput workloads, and observability tools for monitoring token usage and debugging API interactions. It also provides guidance on security primitives, such as authentication and content safety, alongside operational strategies for cost optimization and infrastructure management.

The documentation is structured as a series of Jupyter Notebooks, offering interactive examples that demonstrate how to implement these features within production-grade artificial intelligence systems.

## Tags

### Artificial Intelligence & ML

- [Agentic Workflow Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-workflow-orchestration.md) — Provides frameworks for building autonomous systems that use tools and execute multi-step reasoning. ([source](https://ai.google.dev/gemini-api/docs/agents))
- [Autonomous Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-orchestration.md) — Orchestrates stateful agents that execute multi-step tasks and manage tool invocations across reasoning workflows. ([source](https://cdn.jsdelivr.net/gh/google-gemini/cookbook@main/README.md))
- [Gemini Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/gemini-integrations.md) — Provides official software development kits to facilitate communication with generative artificial intelligence models. ([source](https://ai.google.dev/gemini-api/docs/libraries))
- [LLM Application Development](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/llm-application-development.md) — Provides comprehensive implementation patterns and development guides for building production-grade applications with generative AI models.
- [Multimodal Generation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-generation-pipelines.md) — Orchestrates multimodal generation tasks including text, images, video, and audio within automated pipelines. ([source](https://ai.google.dev/gemini-api/docs))
- [Generative AI Integration Patterns](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-integration-patterns.md) — Provides a collection of implementation patterns and code samples for integrating generative AI models.
- [Generative AI Development](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai-development.md) — Provides frameworks and patterns for building multimodal generative AI applications using official SDKs.
- [Grounded Answer Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/grounded-answer-generation.md) — Connects models to real-time web content to provide accurate, up-to-date answers with verifiable citations. ([source](https://ai.google.dev/gemini-api/docs/google-search))
- [Long-Context Models](https://awesome-repositories.com/f/artificial-intelligence-ml/large-language-models/long-context-models.md) — Maintains logical coherence across massive input sequences and extensive codebases using models optimized for million-token context windows. ([source](https://ai.google.dev/gemini-api/docs))
- [Multimodal AI Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-ai-orchestrators.md) — Offers specialized toolkits for orchestrating agentic workflows and real-time multimodal streaming interactions.
- [Stateful Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/stateful-agent-orchestration.md) — Manages autonomous agent state through transition graphs and conditional logic for multi-step reasoning tasks. ([source](https://ai.google.dev/gemini-api/docs/langgraph-example))
- [Autonomous Browser Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/autonomous-browser-agents.md) — Enables intelligent agents to interpret natural language to navigate and interact with web interfaces. ([source](https://ai.google.dev/gemini-api/docs/pricing))
- [Voice Activity Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/voice-activity-detection.md) — Provides automated identification of speech segments within audio streams to manage conversational turn-taking and interruptions. ([source](https://ai.google.dev/gemini-api/docs/live-api/capabilities))
- [Code-Generating Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/code-generating-agents.md) — Utilizes language models to iteratively write and execute code for task completion. ([source](https://ai.google.dev/gemini-api/docs/migrate))
- [Embedding Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/embedding-generators.md) — Transforms text and other content into numerical vector representations for use in semantic search and memory systems. ([source](https://ai.google.dev/gemini-api/docs/migrate))
- [Retrieval Augmented Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/retrieval-augmented-generation.md) — Indexes and retrieves multimodal document content to ground model responses with relevant context. ([source](https://ai.google.dev/gemini-api/docs/file-search))
- [Robotic Task Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/robotic-task-orchestration.md) — Decomposes natural language commands into subtasks for controlling external systems and robotic operations. ([source](https://ai.google.dev/gemini-api/docs/robotics-overview))
- [Structured Data Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-data-extraction.md) — Enforces JSON schema constraints on model outputs to ensure reliable data extraction for downstream pipelines.
- [Structured Output Parsers](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-output-parsers.md) — Enforces schemas on model-generated content to ensure reliable data integration with downstream applications. ([source](https://ai.google.dev/gemini-api/docs/migrate))
- [Agent Response Streamers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-runtimes/streaming-response-processors/agent-response-streamers.md) — Delivers agent output incrementally in real time to provide immediate visibility into long-running tasks. ([source](https://ai.google.dev/gemini-api/docs/managed-agents-quickstart))
- [Document Analysis Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-content-analysis/document-analysis-engines.md) — Interprets text, images, and tables within documents to provide summaries, answer questions, or convert content into structured formats. ([source](https://ai.google.dev/gemini-api/docs/document-processing))
- [Code Execution Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/code-execution-agents.md) — Integrates code interpretation to solve problems through reasoning and execution. ([source](https://ai.google.dev/gemini-api/docs/code-execution))
- [External Tool Integration](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integration.md) — Integrates code execution with search or custom functions to handle multi-step workflows. ([source](https://ai.google.dev/gemini-api/docs/code-execution))
- [Text-to-Image Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-image-generators.md) — Generates high-resolution images from natural language text prompts with configurable output dimensions and safety filters. ([source](https://ai.google.dev/gemini-api/docs/image-generation))
- [Image Editing](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation/image-editing.md) — Modifies existing visual content using generative AI instructions through inpainting and image-to-image transformations. ([source](https://ai.google.dev/gemini-api/docs/image-generation))
- [Document Chunking Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/retrieval-augmented-generation/document-chunking-strategies.md) — Segments source documents into manageable units to optimize retrieval accuracy and token usage. ([source](https://ai.google.dev/gemini-api/docs/file-search))
- [Inference Cost Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/large-scale-training/cost-optimization-strategies/inference-cost-optimizers.md) — Executes requests using lower-cost tiers that accept variable latency for workloads not requiring real-time performance. ([source](https://ai.google.dev/gemini-api/docs/flex-inference))
- [Text-to-Speech](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech.md) — Synthesizes natural human speech from text input with precise control over style, accent, pace, and tone. ([source](https://ai.google.dev/gemini-api/docs/speech-generation))
- [Tool-Calling Schemas](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-calling-schemas.md) — Maps natural language requests to structured tool invocations by defining schemas that models trigger during generation.
- [Reasoning Configuration](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/agent-reasoning-configurations/reasoning-configuration.md) — Enables fine-grained control over model reasoning behavior to balance output quality, latency, and token consumption. ([source](https://ai.google.dev/gemini-api/docs/troubleshooting))
- [Agentic Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-model-integrations.md) — Connects autonomous agents to external language models and cloud services. ([source](https://ai.google.dev/gemini-api/docs))
- [Agentic Web Browsing](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agentic-domains/agentic-web-browsing.md) — Fetches external URL data and performs web searches to incorporate real-time information into model reasoning. ([source](https://ai.google.dev/gemini-api/docs/antigravity-agent))
- [AI Content Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-content-analysis.md) — Processes images to extract information, identify objects, or perform reasoning based on visual content. ([source](https://ai.google.dev/gemini-api/docs/image-understanding))
- [Audio Generation Models](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-generation-models.md) — Creates high-fidelity stereo music from text or image inputs, supporting custom lyrics and multi-language vocal performances. ([source](https://ai.google.dev/gemini-api/docs/music-generation))
- [Audio Transcription](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-transcription.md) — Processes audio files to generate text transcripts, translations, and summaries while extracting metadata like timestamps. ([source](https://ai.google.dev/gemini-api/docs/audio))
- [Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection.md) — Identifies and locates objects within images using bounding boxes and classification. ([source](https://ai.google.dev/gemini-api/docs/image-understanding))
- [Conversation History Management](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-history-management.md) — Maintains state across multiple rounds of prompts and responses to enable coherent multi-turn chat interactions. ([source](https://ai.google.dev/gemini-api/docs/text-generation))
- [Interruption Handlers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-output-formatting/interruption-handlers.md) — Supports barge-in functionality allowing users to interrupt the model during speech for natural conversational flows. ([source](https://ai.google.dev/gemini-api/docs/live-api))
- [Sequential Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/sequential-orchestration.md) — Orchestrates multiple dependent function calls in sequence to fulfill complex requests. ([source](https://ai.google.dev/gemini-api/docs/function-calling))
- [Video Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/video-generation.md) — Creates high-fidelity videos from text prompts or reference images with support for custom aspect ratios and native audio. ([source](https://ai.google.dev/gemini-api/docs/video))
- [Function-to-Tool Converters](https://awesome-repositories.com/f/artificial-intelligence-ml/function-to-tool-converters.md) — Triggers multiple independent functions simultaneously and maps results back to their respective calls. ([source](https://ai.google.dev/gemini-api/docs/function-calling))
- [Generative Music Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-music-agents.md) — Coordinates specialized agents to generate musical compositions through iterative refinement and structural control. ([source](https://ai.google.dev/gemini-api/docs/music-generation))
- [Instruction-Following Models](https://awesome-repositories.com/f/artificial-intelligence-ml/instruction-following-models.md) — Defines system-level instructions to shape the tone, style, and constraints of model output. ([source](https://ai.google.dev/gemini-api/docs/text-generation))
- [Report Generation Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/report-generation-tools.md) — Transforms raw data or research findings into structured, formatted documents using automated content synthesis. ([source](https://ai.google.dev/gemini-api/docs/vercel-ai-sdk-example))

### Networking & Communication

- [Multimodal Conversational Interfaces](https://awesome-repositories.com/f/networking-communication/communication-platforms-services/communication-platforms/real-time-collaboration-suites/real-time-messaging/multimodal-conversational-interfaces.md) — Implements low-latency streaming for audio, video, and text with support for voice activity detection and barge-in capabilities. ([source](https://ai.google.dev/gemini-api/docs/coding-agents))
- [Real-Time Interaction Engines](https://awesome-repositories.com/f/networking-communication/websocket-clients/real-time-interaction-engines.md) — Implements low-latency, bidirectional streaming interfaces for real-time voice and vision interactions.
- [Connection Establishment Protocols](https://awesome-repositories.com/f/networking-communication/communication-protocols-architectures/communication-protocols-standards/network-protocols/connection-establishment-protocols.md) — Connects to models via network streams to enable real-time, low-latency exchange of audio, video, and text data. ([source](https://ai.google.dev/gemini-api/docs/live-api/get-started-websocket))
- [Voice Interaction Engines](https://awesome-repositories.com/f/networking-communication/websocket-clients/real-time-interaction-engines/voice-interaction-engines.md) — Facilitates low-latency, bidirectional voice communication for interactive applications using a dedicated streaming interface. ([source](https://ai.google.dev/gemini-api/docs))
- [Bidirectional Streaming Protocols](https://awesome-repositories.com/f/networking-communication/bidirectional-streaming-protocols.md) — Facilitates low-latency bidirectional communication by interleaving text, audio, and visual data streams over persistent network connections.
- [Real-time Translation](https://awesome-repositories.com/f/networking-communication/real-time-translation.md) — Translates spoken input into different languages on the fly to support multilingual communication. ([source](https://ai.google.dev/gemini-api/docs/live))

### Data & Databases

- [Input Caches](https://awesome-repositories.com/f/data-databases/data-caching/input-caches.md) — Stores frequently used input tokens on the server to reduce latency and operational costs during subsequent requests.
- [Batch Processing](https://awesome-repositories.com/f/data-databases/batch-processing.md) — Handles high-volume asynchronous requests through dedicated queues to optimize throughput and bypass synchronous rate limits.
- [Geographical Grounding](https://awesome-repositories.com/f/data-databases/data-synchronization/real-time/ai-grounding-services/geographical-grounding.md) — Integrates real-time geographical data into model outputs to provide location-aware answers based on current place information. ([source](https://ai.google.dev/gemini-api/docs/maps-grounding))
- [Document Stores](https://awesome-repositories.com/f/data-databases/document-stores.md) — Provides persistent storage containers for document embeddings to maintain data availability. ([source](https://ai.google.dev/gemini-api/docs/file-search))

### Development Tools & Productivity

- [Full-Stack Application Builders](https://awesome-repositories.com/f/development-tools-productivity/full-stack-application-builders.md) — Automates the development and deployment of complete full-stack applications from natural language prompts. ([source](https://ai.google.dev/gemini-api/docs/aistudio-build-mode))
- [Agent-Integrated Functions](https://awesome-repositories.com/f/development-tools-productivity/local-function-execution/agent-integrated-functions.md) — Invokes functions to perform data transformations or external actions during a conversational loop. ([source](https://ai.google.dev/gemini-api/docs/live-api/tools))
- [Application Generators](https://awesome-repositories.com/f/development-tools-productivity/project-scaffolding-config-code-generation/project-scaffolding-configuration/project-scaffolding/application-generators/application-generators.md) — Creates complete native mobile projects using natural language prompts, including automated configuration of build files and UI components. ([source](https://ai.google.dev/gemini-api/docs/aistudio-android))

### Software Engineering & Architecture

- [Sandboxed Execution Environments](https://awesome-repositories.com/f/software-engineering-architecture/sandboxed-execution-environments.md) — Runs generated code and manages agent state within isolated Linux containers to ensure secure and reproducible task processing.
- [Asynchronous Task Execution](https://awesome-repositories.com/f/software-engineering-architecture/concurrency-models/asynchronous-task-execution.md) — Implements mechanisms for executing long-running operations via durable handles, progress polling, and result retrieval. ([source](https://ai.google.dev/gemini-api/docs/live-api/tools))

### DevOps & Infrastructure

- [Code Execution Sandboxes](https://awesome-repositories.com/f/devops-infrastructure/execution-environments/code-execution-runtimes/code-execution-sandboxes.md) — Runs command-line instructions within a secure, isolated Linux environment. ([source](https://ai.google.dev/gemini-api/docs/antigravity-agent))
- [Application Deployment Platforms](https://awesome-repositories.com/f/devops-infrastructure/application-deployment-platforms.md) — Publishes prototype applications to managed production environments for live service deployment. ([source](https://ai.google.dev/gemini-api/docs/aistudio-deploying))
- [API Throttling](https://awesome-repositories.com/f/devops-infrastructure/api-throttling.md) — Enforces usage caps based on request frequency and token volume to ensure service stability and manage resource consumption. ([source](https://ai.google.dev/gemini-api/docs/rate-limits))

### Hardware & IoT

- [Visual Scene Interpreters](https://awesome-repositories.com/f/hardware-iot/embedded-robotics/robotics-autonomous-systems/visual-scene-interpreters.md) — Processes visual scenes to identify objects and spatial relationships for robotic task execution. ([source](https://ai.google.dev/gemini-api/docs/robotics-overview))

### Security & Cryptography

- [Isolated Execution Sandboxes](https://awesome-repositories.com/f/security-cryptography/application-and-system-security/sandbox-and-isolation/isolated-execution-sandboxes.md) — Creates managed Linux environments for executing code and persisting files across interactions. ([source](https://ai.google.dev/gemini-api/docs/agent-environment))
- [Model Safety Filters](https://awesome-repositories.com/f/security-cryptography/model-safety-filters.md) — Provides configurable content moderation settings to manage safety filtering for model inputs and outputs. ([source](https://ai.google.dev/gemini-api/docs/troubleshooting))
- [API Request Authentication](https://awesome-repositories.com/f/security-cryptography/identity-access-management/authentication-strategies/machine-and-protocol-identity/api-machine-authentication/api-request-authentication.md) — Verifies caller identity using standard or service-account-bound keys for secure API access. ([source](https://ai.google.dev/gemini-api/docs/api-key))
- [OAuth Authentication](https://awesome-repositories.com/f/security-cryptography/oauth-authentication.md) — Validates user identity and grants access to API resources using standard OAuth authorization flows. ([source](https://ai.google.dev/gemini-api/docs/oauth))
- [Service Account Management](https://awesome-repositories.com/f/security-cryptography/service-account-management.md) — Uses cloud service accounts to manage identity and access permissions for enterprise-grade generative AI services. ([source](https://ai.google.dev/gemini-api/docs/migrate-to-cloud))
- [Webhook Security](https://awesome-repositories.com/f/security-cryptography/webhook-security.md) — Verifies incoming event notifications using cryptographic signatures to ensure data integrity and authenticity. ([source](https://ai.google.dev/gemini-api/docs/webhooks))

### System Administration & Monitoring

- [AI Cost Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/ai-cost-monitoring.md) — Optimizes operational expenses by managing token usage, context caching, and service tier selection.
- [Model Interaction Monitors](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/model-interaction-monitors.md) — Captures and displays raw request and response pairs to facilitate debugging of model interactions. ([source](https://ai.google.dev/gemini-api/docs/logs-datasets))
- [Token Usage Analytics](https://awesome-repositories.com/f/system-administration-monitoring/usage-monitoring/token-usage-analytics.md) — Calculates and tracks token consumption to manage operational costs effectively. ([source](https://ai.google.dev/gemini-api/docs/migrate))

### Business & Productivity Software

- [Function Calling Controls](https://awesome-repositories.com/f/business-productivity-software/usage-monitoring-tools/function-calling-controls.md) — Manages model behavior regarding tool usage by forcing or disabling function calling to ensure predictable output. ([source](https://ai.google.dev/gemini-api/docs/function-calling))
- [Service Tier Selectors](https://awesome-repositories.com/f/business-productivity-software/billing-and-subscription-management/tiered-capability-scaling/service-tier-selectors.md) — Controls request priority and capacity usage by specifying service tiers to balance performance and cost requirements. ([source](https://ai.google.dev/gemini-api/docs/openai))
- [Workspace Integrations](https://awesome-repositories.com/f/business-productivity-software/workspace-integrations.md) — Integrates directly with user workspace data like emails and calendars for context-aware applications. ([source](https://ai.google.dev/gemini-api/docs/aistudio-fullstack))

### Operating Systems & Systems Programming

- [Real-Time Audio Streaming Buffers](https://awesome-repositories.com/f/operating-systems-systems-programming/kernel-core-internals/process-and-memory-management/memory-management/buffer-and-cache-management/binary-buffer-managers/trace-buffer-managers/audio-buffers/real-time-audio-streaming-buffers.md) — Streams audio in small chunks and resamples input to maintain low-latency, responsive voice interactions. ([source](https://ai.google.dev/gemini-api/docs/live-api/best-practices))

### Programming Languages & Runtimes

- [Asynchronous Extraction Job Management](https://awesome-repositories.com/f/programming-languages-runtimes/language-features-paradigms/concurrency-models/background-task-management/job-batching/asynchronous-extraction-job-management.md) — Manages the lifecycle of asynchronous processing jobs, including status polling and webhook notifications for completion updates. ([source](https://ai.google.dev/gemini-api/docs/batch-api))
- [Direct API Connectivity](https://awesome-repositories.com/f/programming-languages-runtimes/language-interoperability/bi-directional-language-bridging/direct-api-connectivity.md) — Provides direct communication with REST or gRPC endpoints to access platform features and minimize dependency footprints. ([source](https://ai.google.dev/gemini-api/docs/partner-integration))

### Web Development

- [Batch Processing](https://awesome-repositories.com/f/web-development/batch-processing.md) — Handles high-volume, asynchronous tasks with specific capacity limits for concurrent jobs and token counts. ([source](https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview))

### Testing & Quality Assurance

- [UI Automation](https://awesome-repositories.com/f/testing-quality-assurance/automation-interaction-tools/ui-automation.md) — Controls browser and application interfaces by interpreting visual screen data to execute navigation and interaction commands. ([source](https://ai.google.dev/gemini-api/docs/computer-use))

### User Interface & Experience

- [Generated Content Attribution](https://awesome-repositories.com/f/user-interface-experience/source-attribution-interfaces/generated-content-attribution.md) — Maps segments of a generated response to their corresponding web sources using structured metadata for transparent references. ([source](https://ai.google.dev/gemini-api/docs/google-search))