mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-06-29 15:31:05 +08:00
0d7ad0ed0c
### What problem does this PR solve? This PR adds an Agent LLM setting to control thinking mode for official providers that expose a thinking switch. Related to #12842. Closes #15445. Some providers expose thinking controls through provider-specific request fields, but Agent LLM settings did not have a unified option for users to enable or disable thinking mode. This PR adds a `Thinking` selector with: - System default - Enabled - Disabled <img width="452" height="278" alt="8566b0b4-0546-4c8a-913d-f9bbd38319f6" src="https://github.com/user-attachments/assets/25b497f7-1ba0-4bfe-940d-6fe79287d6ab" /> <img width="471" height="971" alt="8a0a6bee-f45f-48d5-bd83-17af260de3db" src="https://github.com/user-attachments/assets/41ad43c1-5087-48f1-bf37-f2ca14c2be2f" /> Initial support is limited to the verified official providers: - Qwen / DashScope: `enable_thinking` - Kimi / Moonshot: `thinking.type` - GLM / ZHIPU-AI: `thinking.type` For LiteLLM-based providers, provider-specific fields are forwarded through `extra_body` before `drop_params` filtering so the request parameters are preserved. ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: jiashi <jiashi19@outlook.com> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
76 lines
2.5 KiB
Python
76 lines
2.5 KiB
Python
#
|
|
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
"""
|
|
Prevent rag.llm.__init__ from running its heavy auto-discovery loop.
|
|
|
|
The __init__.py dynamically imports ALL model modules (chat_model,
|
|
cv_model, ocr_model, etc.), which pull in deepdoc, xgboost, torch,
|
|
and other heavy native deps. We pre-install a lightweight stub for
|
|
the rag.llm package so that `from rag.llm.embedding_model import X`
|
|
works without triggering the full init.
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import types
|
|
from enum import StrEnum
|
|
|
|
# Resolve the real path to rag/llm/ so sub-module imports can find files
|
|
_RAGFLOW_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "..", ".."))
|
|
_RAG_LLM_DIR = os.path.join(_RAGFLOW_ROOT, "rag", "llm")
|
|
|
|
|
|
def _install_rag_llm_stub():
|
|
"""Replace rag.llm with a minimal package stub if not yet loaded.
|
|
|
|
The stub has __path__ pointing to the real rag/llm/ directory so that
|
|
`from rag.llm.embedding_model import X` resolves to the actual file,
|
|
but the __init__.py auto-discovery loop is skipped.
|
|
"""
|
|
if "rag.llm" in sys.modules:
|
|
return
|
|
|
|
# Create a stub rag.llm package that does NOT run the real __init__
|
|
llm_pkg = types.ModuleType("rag.llm")
|
|
llm_pkg.__path__ = [_RAG_LLM_DIR]
|
|
llm_pkg.__package__ = "rag.llm"
|
|
# Provide empty dicts for the mappings the real __init__ would build
|
|
llm_pkg.EmbeddingModel = {}
|
|
llm_pkg.ChatModel = {}
|
|
llm_pkg.CvModel = {}
|
|
llm_pkg.RerankModel = {}
|
|
llm_pkg.Seq2txtModel = {}
|
|
llm_pkg.TTSModel = {}
|
|
llm_pkg.OcrModel = {}
|
|
|
|
class SupportedLiteLLMProvider(StrEnum):
|
|
Tongyi_Qianwen = "Tongyi-Qianwen"
|
|
Dashscope = "Dashscope"
|
|
Moonshot = "Moonshot"
|
|
ZHIPU_AI = "ZHIPU-AI"
|
|
OpenAI = "OpenAI"
|
|
Azure_OpenAI = "Azure-OpenAI"
|
|
HunYuan = "Tencent Hunyuan"
|
|
|
|
llm_pkg.SupportedLiteLLMProvider = SupportedLiteLLMProvider
|
|
llm_pkg.FACTORY_DEFAULT_BASE_URL = {}
|
|
llm_pkg.LITELLM_PROVIDER_PREFIX = {}
|
|
sys.modules["rag.llm"] = llm_pkg
|
|
|
|
|
|
_install_rag_llm_stub()
|