News
Google’s Java Toolkit Opens Access to Third-Party AI Models Through Langchain4j
Google has expanded its Agent Development Kit (ADK) for Java to support a wider range of large language models (LLMs) through integration with the LangChain4j framework, the company said in a blog post on Monday.
The update, included in the ADK’s 0.2.0 release, enables Java developers to connect AI agents not only to Google’s Gemini models and Anthropic’s Claude but also to third-party systems such as OpenAI, GitHub, and Mistral. It also adds compatibility with open-weight models running locally via tools like Ollama and Docker Model Runner.
LangChain4j, a Java implementation of the LangChain framework, allows developers to switch between multiple model providers. With the integration, ADK agents can be configured to use models such as Gemma or Qwen, whether hosted locally or accessed through commercial APIs.
Alongside the LangChain4j support, Google introduced several technical enhancements aimed at improving performance and flexibility:
- Expanded tooling capabilities: Function tools can now be created from object instances as well as static methods, with improved asynchronous support and finer control of agent loops.
- Advanced agent logic and memory: The release adds chained callbacks for model, agent, and tool execution, as well as new memory management options, including an in-memory service for speed and Vertex AI-based retrieval for more advanced applications.
- Development improvements: A parent Maven project object model (POM) and Maven Wrapper were added to simplify the build process and ensure consistency across environments.
Google said these changes are intended to make it easier for developers to build and manage AI agents that interact with different models and data sources. Documentation and release notes are available on GitHub.
About the Author
John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He’s been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he’s written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS. He can be reached at [email protected].
Source: adtmag.com
