feat: Add Gemma3Ollama model integration and a sample

This change introduces `Gemma3Ollama`, a new LLM model class for running Gemma 3 models locally via Ollama, leveraging LiteLLM. The function calling logic previously in the `Gemma` class has been refactored into a `GemmaFunctionCallingMixin` and is now used by both `Gemma` and `Gemma3Ollama`. A new sample application, `hello_world_gemma3_ollama`, is added to demonstrate using `Gemma3Ollama` with an agent. Unit tests for `Gemma3Ollama` are also included.

Merge: #3120

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839996879

Author: 2 people

contributing/samples/hello_world_gemma3_ollama/__init__.py

@@ -0,0 +1,16 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+from . import agent

contributing/samples/hello_world_gemma3_ollama/agent.py

@@ -0,0 +1,93 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import logging
+import random
+
+from google.adk.agents.llm_agent import Agent
+from google.adk.models import Gemma3Ollama
+
+litellm_logger = logging.getLogger("LiteLLM")
+litellm_logger.setLevel(logging.WARNING)
+
+
+def roll_die(sides: int) -> int:
+  """Roll a die and return the rolled result.
+
+  Args:
+    sides: The integer number of sides the die has.
+
+  Returns:
+    An integer of the result of rolling the die.
+  """
+  return random.randint(1, sides)
+
+
+async def check_prime(nums: list[int]) -> str:
+  """Check if a given list of numbers are prime.
+
+  Args:
+    nums: The list of numbers to check.
+
+  Returns:
+    A str indicating which number is prime.
+  """
+  primes = set()
+  for number in nums:
+    number = int(number)
+    if number <= 1:
+      continue
+    is_prime = True
+    for i in range(2, int(number**0.5) + 1):
+      if number % i == 0:
+        is_prime = False
+        break
+    if is_prime:
+      primes.add(number)
+  return (
+      "No prime numbers found."
+      if not primes
+      else f"{', '.join(str(num) for num in primes)} are prime numbers."
+  )
+
+
+root_agent = Agent(
+    model=Gemma3Ollama(),
+    name="data_processing_agent",
+    description=(
+        "hello world agent that can roll a dice of 8 sides and check prime"
+        " numbers."
+    ),
+    instruction="""
+      You roll dice and answer questions about the outcome of the dice rolls.
+      You can roll dice of different sizes.
+      You can use multiple tools in parallel by calling functions in parallel (in one request and in one round).
+      It is ok to discuss previous dice rolls, and comment on the dice rolls.
+      When you are asked to roll a die, you must call the roll_die tool with the number of sides. Be sure to pass in an integer. Do not pass in a string.
+      You should never roll a die on your own.
+      When checking prime numbers, call the check_prime tool with a list of integers. Be sure to pass in a list of integers. You should never pass in a string.
+      You should not check prime numbers before calling the tool.
+      When you are asked to roll a die and check prime numbers, you should always make the following two function calls:
+      1. You should first call the roll_die tool to get a roll. Wait for the function response before calling the check_prime tool.
+      2. After you get the function response from roll_die tool, you should call the check_prime tool with the roll_die result.
+        2.1 If user asks you to check primes based on previous rolls, make sure you include the previous rolls in the list.
+      3. When you respond, you must include the roll_die result from step 1.
+      You should always perform the previous 3 steps when asking for a roll and checking prime numbers.
+      You should not rely on the previous history on prime results.
+    """,
+    tools=[
+        roll_die,
+        check_prime,
+    ],
+)

contributing/samples/hello_world_gemma3_ollama/main.py

@@ -0,0 +1,77 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+import asyncio
+import time
+
+import agent
+from dotenv import load_dotenv
+from google.adk.artifacts.in_memory_artifact_service import InMemoryArtifactService
+from google.adk.cli.utils import logs
+from google.adk.runners import Runner
+from google.adk.sessions.in_memory_session_service import InMemorySessionService
+from google.adk.sessions.session import Session
+from google.genai import types
+
+load_dotenv(override=True)
+logs.log_to_tmp_folder()
+
+
+async def main():
+
+  app_name = 'my_app'
+  user_id_1 = 'user1'
+  session_service = InMemorySessionService()
+  artifact_service = InMemoryArtifactService()
+  runner = Runner(
+      app_name=app_name,
+      agent=agent.root_agent,
+      artifact_service=artifact_service,
+      session_service=session_service,
+  )
+  session_1 = await session_service.create_session(
+      app_name=app_name, user_id=user_id_1
+  )
+
+  async def run_prompt(session: Session, new_message: str):
+    content = types.Content(
+        role='user', parts=[types.Part.from_text(text=new_message)]
+    )
+    print('** User says:', content.model_dump(exclude_none=True))
+    async for event in runner.run_async(
+        user_id=user_id_1,
+        session_id=session.id,
+        new_message=content,
+    ):
+      if event.content.parts and event.content.parts[0].text:
+        print(f'** {event.author}: {event.content.parts[0].text}')
+
+  start_time = time.time()
+  print('Start time:', start_time)
+  print('------------------------------------')
+  await run_prompt(session_1, 'Hi, introduce yourself.')
+  await run_prompt(
+      session_1, 'Roll a die with 100 sides and check if it is prime'
+  )
+  await run_prompt(session_1, 'Roll it again.')
+  await run_prompt(session_1, 'What numbers did I get?')
+  end_time = time.time()
+  print('------------------------------------')
+  print('End time:', end_time)
+  print('Total time:', end_time - start_time)
+
+
+if __name__ == '__main__':
+  asyncio.run(main())

src/google/adk/models/__init__.py

@@ -53,3 +53,13 @@
 except Exception:
   # LiteLLM support requires: pip install google-adk[extensions]
   pass
+
+# Optionally register Gemma3Ollama if litellm package is installed
+try:
+  from .gemma_llm import Gemma3Ollama
+
+  LLMRegistry.register(Gemma3Ollama)
+  __all__.append('Gemma3Ollama')
+except Exception:
+  # Gemma3Ollama requires LiteLLM: pip install google-adk[extensions]
+  pass