LLM API¶

LLM provider integration.

OllamaProvider¶

from legionhercules.llm.ollama_provider import OllamaProvider

provider = OllamaProvider(
    model="llama3.2",
    base_url="http://localhost:11434",
    timeout=120.0,
)

await provider.initialize()

Methods¶

chat(messages, **kwargs)¶

Send chat messages and get response.

from legionhercules.core.message import Message

messages = [
    Message.system("You are helpful"),
    Message.user("Hello!"),
]

response = await provider.chat(messages)
print(response.content)

generate(prompt, **kwargs)¶

Generate text from prompt.

list_models()¶

List available models.

health_check()¶

Check if Ollama is running.