base on Examples and guides for using the Gemini API # Welcome to the Gemini API Cookbook This is a collection of guides and examples for the Gemini API, including [quickstart](https://github.com/google-gemini/cookbook/tree/main/quickstarts) tutorials for writing prompts and using different features of the API, and [examples](https://github.com/google-gemini/cookbook/tree/main/examples) of things you can build. ${\Large \textbf{\color[rgb]{0.12941,0.48235,0.99608}N\color[rgb]{0.57647,0.60392,1}e\color[rgb]{0.91765,0.47843,0.72157}w\color[rgb]{0.93333,0.30196,0.36471}:}}$ Check out the latest Gemini 2.0 capabilities in [the docs](https://ai.google.dev/gemini-api/docs/models/gemini-v2), [Google AI Studio](https://aistudio.google.com/app/live?model=gemini-2.0-flash-exp) and here in the [cookbook](./gemini-2/). ## Get started with the Gemini API The Gemini API gives you access to Gemini [models](https://ai.google.dev/models/gemini) created by [Google DeepMind](https://deepmind.google/technologies/gemini/#introduction). Gemini models are built from the ground up to be multimodal, so you can reason seamlessly across text, images, code, and audio. You can use these to develop a [range of applications](https://ai.google.dev/examples/). ### Start developing 1. Go to [Google AI Studio](https://aistudio.google.com/). 2. Log in with your Google account. 3. [Create](https://aistudio.google.com/app/apikey) an API key. 4. Use a [quickstart](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Prompting.ipynb) for Python, or call the REST API [using curl](https://github.com/google-gemini/cookbook/blob/main/quickstarts/rest/Prompting_REST.ipynb). ## What's New? We're excited to show you the latest additions to the Gemini API, and new notebooks. * [Gemini 2.0](./gemini-2/): Explore the capabilities of the new Gemini 2.0 model, including [multimodal Live API](./gemini-2/live_api_starter.ipynb), [audio streaming applications with tool use](./gemini-2/live_api_tool_use.ipynb) and [Spatial understanding](./gemini-2/spatial_understanding.ipynb). ## Table of contents Learn about the capabilities of the Gemini API by checking out these quickstart tutorials. * [Authentication](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Authentication.ipynb): Start here to learn how you can set up your API key so you can get access to the Gemini API. * [Counting Tokens](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Counting_Tokens.ipynb) Tokens are the basic inputs to the Gemini models. Through this notebook, you will gain a better understanding of tokens through an interactive experience. * [Files](https://github.com/google-gemini/cookbook/blob/main/quickstarts/File_API.ipynb): Use the Gemini API to upload files (text, code, images, audio, video) and write prompts using them. * [Audio](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Audio.ipynb): Learn how to use the Gemini API with audio files. * [JSON mode](https://github.com/google-gemini/cookbook/blob/main/quickstarts/JSON_mode.ipynb): Discover how to use JSON mode. * [Function Calling](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Function_calling.ipynb): The Gemini API works great with code. Use this quickstart to learn how to write prompts to understand and call functions. Then check out the [function calling config](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Function_calling_config.ipynb) tutorial to learn more. * [System Instructions](https://github.com/google-gemini/cookbook/blob/main/quickstarts/System_instructions.ipynb): Give models additional context on how to respond by setting system instructions. * [Embeddings](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Embeddings.ipynb): Create high-quality and task-specific embeddings. * [Tuning](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Tuning.ipynb): Learn how to improve model performance on a specific task through tuning. * [Code execution](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Code_Execution.ipynb): Solve complex tasks by Generating and running Python code based on plain-text instructions. You can find lots more in the [quickstarts folder](https://github.com/google-gemini/cookbook/tree/main/quickstarts), and check out the [examples folder](https://github.com/google-gemini/cookbook/tree/main/examples) for fun examples. We're also maintaining an [Awesome Gemini](Awesome_gemini.md) list of all the cool projects the community is building using Gemini. ## Official SDKs The Gemini API is a REST API. You can call the API using a command line tool like `curl` (and you can find REST examples [here](https://github.com/google-gemini/cookbook/tree/main/quickstarts/rest)), or by using one of our [official SDKs](https://ai.google.dev/gemini-api/docs/downloads): * Python: [Google GenAI SDKs](https://github.com/googleapis/python-genai) will eventually replace the older [Developer SDK](https://github.com/google/generative-ai-python). * [Node.js](https://github.com/google/generative-ai-js) * [Dart (Flutter)](https://github.com/google/generative-ai-dart) * [Android](https://github.com/google/generative-ai-android) * [Swift](https://github.com/google/generative-ai-swift) * [Go](https://github.com/google/generative-ai-go) ## Get help Ask a question on the [Google AI Developer Forum](https://discuss.ai.google.dev/). ## The Gemini API on Google Cloud Vertex AI If you're an enterprise developer looking to build on a fully managed platform, you can also use the Gemini API on Google Cloud. Check out this [repo](https://github.com/GoogleCloudPlatform/generative-ai) for lots of cool examples. ## Contributing Contributions are welcome. See [contributing](https://github.com/google-gemini/cookbook/blob/main/CONTRIBUTING.md) to learn more. Thank you for developing with the Gemini API! We’re excited to see what you create. ", Assign "at most 3 tags" to the expected json: {"id":"9260","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"