Skip to content

Update ADK doc according to issue #744 - 3 #752

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+34 −2
Open

Update ADK doc according to issue #744 - 3 #752

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 34 additions & 2 deletions docs/agents/models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,7 @@ For deployed applications, a service account is the standard method.

```python
from google.adk.agents import LlmAgent

# --- Example using a stable Gemini Flash model ---
agent_gemini_flash = LlmAgent(
# Use the latest stable Flash model identifier
Expand All @@ -135,7 +135,7 @@ For deployed applications, a service account is the standard method.
instruction="You are a fast and helpful Gemini assistant.",
# ... other agent parameters
)

# --- Example using a powerful Gemini Pro model ---
# Note: Always check the official Gemini documentation for the latest model names,
# including specific preview versions if needed. Preview models might have
Expand Down Expand Up @@ -186,6 +186,38 @@ For deployed applications, a service account is the standard method.
!!!warning "Secure Your Credentials"
Service account credentials or API keys are powerful credentials. Never expose them publicly. Use a secret manager like [Google Secret Manager](https://cloud.google.com/secret-manager) to store and access them securely in production.

## Using Gemma Models

![python_only](https://img.shields.io/badge/Supported_in-Python-blue)

You can use Gemma models in your agents through the `Gemma` wrapper class. This allows you to leverage Gemma's capabilities for various generative tasks.

**Integration Method:** Instantiate the `Gemma` wrapper class with a supported model name and pass it to the `model` parameter of your `LlmAgent`.

**Supported Models:** Currently, only Gemma 3 models are supported. For agentic use cases, `gemma-3-27b-it` and `gemma-3-12b-it` are recommended.

!!! warning "Important Considerations"
* **No System Instructions:** Gemma models do not support system instructions. Any system instructions provided will be automatically converted to user-level instructions.
* **Limited Function Calling:** Gemma's function calling capabilities are limited.
* **No Vertex AI Support:** The current integration does not support the Vertex AI API for Gemma models.

**Example:**

=== "Python"

```python
from google.adk.agents import LlmAgent
from google.adk.models import Gemma

# --- Example Agent using a Gemma model ---
agent_gemma = LlmAgent(
model=Gemma(model="gemma-3-27b-it"),
name="gemma_agent",
instruction="You are a helpful assistant powered by Gemma.",
# ... other agent parameters
)
```

## Using Anthropic models

![java_only](https://img.shields.io/badge/Supported_in-Java-orange){ title="This feature is currently available for Java. Python support for direct Anthropic API (non-Vertex) is via LiteLLM."}
Expand Down