Building Agents with Ollama

pip install -U swarms ollama

ollama pull llama3.2
ollama pull qwen2.5
ollama pull mistral

export OLLAMA_API_BASE="http://your-host:11434"

from swarms import Agent

agent = Agent(
    agent_name="Local-Agent",
    model_name="ollama/llama3.2",
    max_loops=1,
)

print(agent.run("Summarize how diffusion models work in three paragraphs."))

from swarms import Agent

def get_weather(city: str) -> str:
    """Return the current weather for a city."""
    return f"{city}: 21°C, partly cloudy"

agent = Agent(
    agent_name="Local-Assistant",
    model_name="ollama/llama3.2",
    tools=[get_weather],
    max_loops=3,
)

print(agent.run("What's the weather in Tokyo right now?"))

from swarms import Agent

agent = Agent(
    agent_name="Streaming-Ollama",
    model_name="ollama/llama3.2",
    streaming_on=True,
    max_loops=1,
)

agent.run("Walk me through how garbage collection works in modern JVMs.")

from swarms import Agent

medical_agent = Agent(
    agent_name="Local-Medical-Summarizer",
    model_name="ollama/llama3.3",
    system_prompt=(
        "You are a medical document summarizer. Extract diagnoses, medications, "
        "and follow-up actions. Do not invent details not present in the source."
    ),
    max_loops=1,
)

with open("patient_chart.txt") as f:
    chart = f.read()

summary = medical_agent.run(f"Summarize this chart:\n\n{chart}")
print(summary)

from swarms import Agent, SequentialWorkflow

researcher = Agent(
    agent_name="Researcher",
    model_name="ollama/llama3.3",
    system_prompt="Research thoroughly. Stick to what's in your training data.",
    max_loops=1,
)

writer = Agent(
    agent_name="Writer",
    model_name="ollama/qwen2.5",
    system_prompt="Write a clear executive summary.",
    max_loops=1,
)

pipeline = SequentialWorkflow(agents=[researcher, writer], max_loops=1)
print(pipeline.run("Compare actor-model concurrency in Erlang, Akka, and Elixir."))

from swarms import Agent

agent = Agent(
    agent_name="Production-Ollama",
    model_name="ollama/llama3.3",
    max_loops=1,
    persistent_memory=True,
    context_compression=True,
    context_length=16_384,
    autosave=True,
    retry_attempts=3,
    print_on=False,
)