Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
LLM_Interface、OpenAICompatible、OpenAIResponsesCompatible、APIKeyPool 的 API 参考
from SimpleLLMFunc.interface import LLM_Interface
LLM_Interface(
api_key_pool: APIKeyPool,
model_name: str,
base_url: Optional[str] = None,
context_window: int = 200_000,
)
| 方法 | 签名 | 描述 |
|---|---|---|
chat | async def chat(*, trace_id, stream=False, messages, timeout=None, **kwargs) | 非流式调用 |
chat_stream | async def chat_stream(*, trace_id, stream=True, messages, timeout=None, **kwargs) -> AsyncGenerator | 流式调用 |
| 属性 | 类型 | 描述 |
|---|---|---|
model_name | str | 模型标识符 |
base_url | str | None | API 端点 |
context_window | int | 上下文窗口大小（以 token 为单位） |
api_key_pool | APIKeyPool | API 密钥轮换池 |
from SimpleLLMFunc import OpenAICompatible
OpenAICompatible(
api_key_pool: APIKeyPool,
model_name: str,
base_url: str,
max_retries: int = 5,
retry_delay: float = 1.0,
rate_limit_capacity: int = 10,
rate_limit_refill_rate: float = 1.0,
context_window: int = 200_000,
)
| 方法 | 返回值 | 描述 |
|---|---|---|
load_from_json_file(path) | Dict[str, Dict[str, OpenAICompatible]] | 从 provider.json 加载所有模型 |
| 方法 | 返回值 | 描述 |
|---|---|---|
get_rate_limit_status() | Dict[str, Any] | 当前速率限制器状态 |
reset_rate_limit() | None | 重置令牌桶 |
from SimpleLLMFunc import OpenAICompatible, APIKeyPool
# From file
models = OpenAICompatible.load_from_json_file("provider.json")
llm = models["openrouter"]["openai/gpt-4o"]
# Direct
llm = OpenAICompatible(
api_key_pool=APIKeyPool(api_keys=["sk-..."], provider_id="openai"),
model_name="gpt-4o",
base_url="https://api.openai.com/v1",
rate_limit_capacity=20,
rate_limit_refill_rate=5.0,
)
from SimpleLLMFunc import OpenAIResponsesCompatible
OpenAICompatible 相同。
| 方面 | OpenAICompatible | OpenAIResponsesCompatible |
|---|---|---|
| 系统提示词 | messages[0].role="system" | instructions 字段 |
| 流式格式 | Chat Completion 数据块 | Responses 流事件 |
| 推理支持 | 不适用 | reasoning={...} kwargs |
| 传输协议 | Chat Completions API | Responses API |
from SimpleLLMFunc import OpenAIResponsesCompatible, APIKeyPool
llm = OpenAIResponsesCompatible(
api_key_pool=APIKeyPool(api_keys=["sk-..."], provider_id="openai"),
model_name="gpt-4o",
base_url="https://api.openai.com/v1",
)
@llm_chat(llm_interface=llm, reasoning_effort="high")
async def reasoning_agent(message: str, history: list | None = None):
"""Reason carefully about the question."""
pass
from SimpleLLMFunc import APIKeyPool
APIKeyPool(
api_keys: List[str],
provider_id: str,
)
pool = APIKeyPool(
api_keys=["sk-key-1", "sk-key-2", "sk-key-3"],
provider_id="openrouter-gpt4o",
)
# Keys are rotated on each call automatically
from SimpleLLMFunc import TokenBucket
TokenBucket(
capacity: int,
refill_rate: float,
)
| 参数 | 描述 |
|---|---|
capacity | 桶中最大令牌数 |
refill_rate | 每秒补充的令牌数 |
OpenAICompatible 内部使用。暴露给外部以便自定义实现。此页面对您有帮助吗？