Google has announced Genkit for Go, an open source framework for building AI-powered applications and cloud services natively in Go. Google says that it combines Go's performance and concurrency advantages with Genkit's libraries and tools.

Genkit provides open source libraries for Node.js and Go, along with tools for debugging. Suggested uses include intelligent agents that understand user requests and perform tasks autonomously; conversion of unstructured data such as natural language, into structured formats (e.g., objects, SQL queries, tables) for integration into your app or data pipeline; and Retrieval-augmented generation (RAG), creating apps that provide accurate and contextually relevant responses by using your own data sources for the responses, such as chatbots or question answering systems.

The library includes a unified generation API that can be used to generate text, media, structured objects, and tool calls from any generative model. It also has vector database support for use with RAG, providing indexing and retrieval APIs.

The framework can also be use to set up rich prompt templates, model configurations, input/output schemas, and tools within a single, runnable .prompt file.

Genkit organizes app logic into workflows, functions designed for observability, streaming, integration with Genkit devtools, and deployment as API endpoints. It also supports built-in streaming to send content from your Genkit API app to your client app.

Google says Genkit for Go is a lightweight, provider-agnostic framework, and the plan is to offer a growing collection of plugins to integrate with specific models, vector databases, and cloud services from Google and third-party providers.

In this release, Genkit for Go provides several plugins from Google and third parties. The Google plugins include Google AI for Developers plugin that provides access to Google's generative AI APIs, including Gemini and embedding models; and the Google Cloud Vertex AI plugin that can be used to access Gemini and embeddings models from Google Vertex AI. It also supports Google Cloud telemetry plugin for the exporting of  logs, metrics, and traces to Cloud Logging, Cloud Tracing, and Firestore.

Third party plugin support in this version is limited to the Ollama plugin for accessing and running open source models like Gemma, Llama, and Mistral locally through Ollama; and the Pinecone plugin for integrating with Pinecone's vector database for indexing and retrieval operations.

Genkit for Go is available as an alpha version. 

More Information

Genkit For Go On GitHub

Related Articles

Google Releases Vertex AI Agent Builder

Gemini Offers Huge Context Window

Gemini 1.5 Pro Now Available

Golang Back In TIOBE Top 10

Go Developers Still Well Satisfied In 2023

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info