v2.1.4

What's Changed

• feat: Implemented Multimodal Live APIs and introduced a new package Google_GenerativeAI.Live
• Added a WPF sample to demostrate Realtime two way audio communication with gemini-2.0-flash-exp
• Remove legacy dependencies from modern .NET targets by @georg-jung in #21
• Add M.E.AI native json support by @georg-jung in #20

Full Changelog: v2.0.14...v2.1.4

v2.0.14

What's Changed

• feat: added Semantic Search Retrieval (RAG 🔎) with Google AQA model 2025-02-20
• Fix typo in json mime type for Google_GenerativeAI.Microsoft by @georg-jung in #19

New Contributors

• @georg-jung made their first contribution in #19

Full Changelog: v2.0.7...v2.0.14

v2.0.7

Added function calling support in Google_GenerativeAI.Microsoft Package

v2.0.4

Some bug fixes

v2.0.0

This new version is a complete rewrite of the previous SDK, designed to improve performance, flexibility, and ease of use. It seamlessly integrates with LangChain.net, providing easy methods for JSON-based interactions and function calling with Google Gemini models.

Highlights of this release include:

1. Complete Rewrite – The SDK has been entirely rebuilt for improved reliability and maintainability.
2. LangChain.net Support – Enables you to directly use this SDK within LangChain.net workflows.
3. Enhanced JSON Mode – Includes straightforward methods to handle Google Gemini’s JSON mode.
4. Function Calling with Code Generator – Simplifies function calling by providing a source generator that creates argument classes and extension methods automatically.
5. Multi-Modal Functionality – Provides methods to easily incorporate text, images, and other data for multimodal operations with Google Gemini.
6. Vertex AI Support – Introducing direct support for Vertex AI, including multiple authentication methods such as OAuth, Service Account, and ADC (Application Default Credentials).
7. New Packages – Modularizes features to help you tailor the SDK to your needs:

Package	Version	Description
GenerativeAI.Tools		Provides function tooling and code generation using tryAgi CSharpToJsonSchema. Ideal for scenarios where you need to define functions and automate their JSON schema generation.
GenerativeAI.Auth		Offers various Google authentication mechanisms, including OAuth, Service Account, and Application Default Credentials (ADC). Streamlines credential management.
GenerativeAI.Microsoft		Implements the IChatClient interface from Microsoft.Extensions.AI, enabling seamless integration with Microsoft’s AI ecosystem and services.
GenerativeAI.Web		Contains extension methods to integrate GenerativeAI into .NET web applications, simplifying setup for web projects that utilize Gemini models.

v1

Merge pull request #14 from stephentoub/updatemeai

Update M.E.AI to 9.1.0-preview.1.25064.3

Version 0.1.14

Added Streaming Support
Added ModelInfoService to get the available generative AI models.
Simplified Gemini Pro Vision Generation with new FileObject class

Version 0.1 (Preview)

Initial Release