Skip to main content

Documentation Index

Fetch the complete documentation index at: https://ahvn.top/llms.txt

Use this file to discover all available pages before exploring further.

Pass OpenAI-compatible tools directly to chat or stream. 
tools = [
    {
        "type": "function",
        "function": {
            "name": "lookup_user",
            "description": "Look up a user by id",
            "parameters": {
                "type": "object",
                "properties": {"user_id": {"type": "string"}},
                "required": ["user_id"],
            },
        },
    }
]

calls = llm.chat("Find user 42", tools=tools, include="tool_calls")
Tool calls are collected from streaming deltas and returned in the standard OpenAI tool_calls shape.

​
Structured output

Pass OpenAI-compatible response_format arguments directly: 
data = llm.chat(
    "Return JSON with keys name and score.",
    response_format={"type": "json_object"},
    include="structured",
)
Most providers can stream structured output through the normal path. When a model is known to be unreliable for streaming structured JSON, its model defaults can set structured_stream: false. You can also force non-streaming structured calls from user code: 
data = llm.chat(
    "Return JSON with key ok=true.",
    response_format={"type": "json_object"},
    include="structured",
    enforce_non_stream_structured=True,
)
For stream(..., enforce_non_stream_structured=True), HeavenBase performs one non-streaming request and yields a single projected chunk.