Model Configuration and Integration | google/adk-docs | DeepWiki
It explains the model parameter, supported model providers (Gemini, Vertex AI, Anthropic Claude, Ollama, vLLM, LiteLLM, Apigee), and model-specific configuration options including
It explains the model parameter, supported model providers (Gemini, Vertex AI, Anthropic Claude, Ollama, vLLM, LiteLLM, Apigee), and model-specific configuration options including generation parameter...
HOME / Distribution Box ADK Model Parameters - Automation Authority Telecom & Energy Systems
Distribution Box ADK Model Parameters - Automation Authority Telecom & Energy Systems [PDF]
It explains the model parameter, supported model providers (Gemini, Vertex AI, Anthropic Claude, Ollama, vLLM, LiteLLM, Apigee), and model-specific configuration options including
ADK is the open-source agent development framework that lets you build, debug, and deploy reliable AI agents at enterprise scale. Available in Python, TypeScript, Go, and Java.
This page covers model selection, authentication methods, generation parameters, and model-specific features. For information about defining agents that use these models, see LLM Agents.
Learn how to use ADK in Gemini Enterprise Agent Platform.
For scenarios requiring structured data exchange with an LLM Agent, the ADK provides mechanisms to define expected input and desired output formats using schema definitions.
In this tutorial, we''ll explore how to apply prompt engineering principles in ADK — from setup and basics to advanced use cases.
Learn to select and configure different AI models including Gemini variants, optimization strategies, and model-specific configurations.
You instantiate a specific wrapper class (e.g., LiteLlm) and pass this object as the model parameter to your LlmAgent. The following sections guide you through using these methods based on your needs.
Now, let''s talk about the knobs you can turn. The behaviour of an agent comes down to a few key parameters: The model parameter specifies which LLM powers your agent''s reasoning
Shows how to configure an agent to use a specific language model, with custom parameters and settings. Demonstrates how to build a pipeline of agents that pass information between them in