OpenAI (LLM)

Use OpenAI as the LLM (dialogue + reasoning) provider.

Setup

• Set OPENAI_API_KEY

# .env
OPENAI_API_KEY=...

Example

from siphon.plugins import openai

llm = openai.LLM(
    model="gpt-4.1-mini",
    temperature=0.3,
)

Common options

• model (default: gpt-4.1-mini)
• base_url (default: https://api.openai.com/v1)
• api_key (default: None)
• temperature (default: 0.3)
• max_completion_tokens (default: 150)
• parallel_tool_calls (default: True)
• timeout (default: 15)