LLM Integration

from gaia.llm import create_client

# Local LLM (Lemonade server — default)
llm = create_client()

# Generate response
response = llm.generate(
    prompt="What is AI?",
    model="Qwen3-0.6B-GGUF"
)
print(response)

# Streaming response
for chunk in llm.generate(prompt="Tell me a story", stream=True):
    print(chunk, end="", flush=True)

# Chat completions format
messages = [
    {"role": "user", "content": "Hello!"},
    {"role": "assistant", "content": "Hi! How can I help?"},
    {"role": "user", "content": "Tell me about Python"}
]

response = llm.chat(
    messages=messages,
    model="Qwen3-0.6B-GGUF"
)
print(response)

from gaia.llm import create_client

# Claude API
llm_claude = create_client(use_claude=True)

# OpenAI API
llm_openai = create_client(use_openai=True)

# LiteLLM gateway — 100+ providers (Bedrock, Vertex AI, Groq, Azure, ...)
# Requires: pip install 'gaia[litellm]'
llm_litellm = create_client("litellm", model="anthropic/claude-sonnet-4-6")

# Use same interface
response = llm_claude.generate("Explain Python decorators")

from gaia.llm.lemonade_client import DEFAULT_MODEL_NAME, DEFAULT_LEMONADE_URL

# Default configuration
MODEL = DEFAULT_MODEL_NAME  # "Gemma-4-E4B-it-GGUF"
URL = DEFAULT_LEMONADE_URL   # "http://localhost:13305/api/v1"

# Used internally by LLMClient when no provider specified