mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-19 02:56:17 +00:00
3dc895df4d
* feat(models): add shared RPM admission queues * fix(models): address admission pacing review feedback * docs: simplify request admission quick start guidance --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
75 lines
4.0 KiB
Python
75 lines
4.0 KiB
Python
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
|
|
class RequestAdmissionConfig(BaseModel):
|
|
"""Optional per-process pacing of model requests, shared by quota group."""
|
|
|
|
model_config = ConfigDict(extra="forbid", frozen=True)
|
|
requests_per_minute: int = Field(gt=0, strict=True)
|
|
group: str | None = Field(default=None, min_length=1, max_length=100, pattern=r"^[A-Za-z0-9_.-]+$")
|
|
max_wait_seconds: float = Field(default=300, gt=0, allow_inf_nan=False)
|
|
max_queue_size: int = Field(default=256, gt=0, strict=True)
|
|
|
|
|
|
class ModelConfig(BaseModel):
|
|
"""Config section for a model"""
|
|
|
|
name: str = Field(..., description="Unique name for the model")
|
|
request_admission: RequestAdmissionConfig | None = Field(default=None, description="Opt-in process-local RPM pacing. Changing an active group's policy requires a process restart.")
|
|
display_name: str | None = Field(..., default_factory=lambda: None, description="Display name for the model")
|
|
description: str | None = Field(..., default_factory=lambda: None, description="Description for the model")
|
|
use: str = Field(
|
|
...,
|
|
description="Class path of the model provider(e.g. langchain_openai.ChatOpenAI)",
|
|
)
|
|
model: str = Field(..., description="Model name")
|
|
model_config = ConfigDict(extra="allow")
|
|
use_responses_api: bool | None = Field(
|
|
default=None,
|
|
description="Whether to route OpenAI ChatOpenAI calls through the /v1/responses API",
|
|
)
|
|
output_version: str | None = Field(
|
|
default=None,
|
|
description="Structured output version for OpenAI responses content, e.g. responses/v1",
|
|
)
|
|
supports_thinking: bool = Field(default_factory=lambda: False, description="Whether the model supports thinking")
|
|
supports_reasoning_effort: bool = Field(default_factory=lambda: False, description="Whether the model supports reasoning effort")
|
|
when_thinking_enabled: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description="Extra settings to be passed to the model when thinking is enabled",
|
|
)
|
|
when_thinking_disabled: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description="Extra settings to be passed to the model when thinking is disabled",
|
|
)
|
|
supports_vision: bool = Field(default_factory=lambda: False, description="Whether the model supports vision/image inputs")
|
|
context_window: int | None = Field(
|
|
default=None,
|
|
gt=0,
|
|
description=(
|
|
"Positive total context window size in tokens (prompt + completion). Used to compute the real-time "
|
|
"context usage percentage displayed in the chat UI, and attached to the model's langchain profile "
|
|
"(`max_input_tokens`) so fraction-based summarization triggers can resolve their thresholds for "
|
|
"third-party OpenAI-compatible models that carry no built-in profile. Distinct from `max_tokens`, "
|
|
"which is the per-call output cap passed to the provider. Leave unset if unknown; the UI will hide "
|
|
"the percentage and fraction summarization clauses will degrade with a warning."
|
|
),
|
|
)
|
|
stream_chunk_timeout: float | None = Field(
|
|
default=None,
|
|
description=(
|
|
"Maximum seconds to wait between successive streaming chunks before "
|
|
"langchain-openai raises StreamChunkTimeoutError. None means use the "
|
|
"factory default (240s for OpenAI-compatible clients). Tune higher for "
|
|
"reasoning models with long thinking pauses; lower for latency-sensitive "
|
|
"interactive endpoints. Has no effect on non-OpenAI-compatible providers."
|
|
),
|
|
)
|
|
thinking: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description=(
|
|
"Thinking settings for the model. If provided, these settings will be passed to the model when thinking is enabled. "
|
|
"This is a shortcut for `when_thinking_enabled` and will be merged with `when_thinking_enabled` if both are provided."
|
|
),
|
|
)
|