# import requests
# from typing import Any, Dict, List, Optional
# from langchain_core.language_models import BaseLLM
# from langchain_core.callbacks import CallbackManagerForLLMRun
# from langchain_core.outputs import LLMResult, Generation
# from openai import OpenAI
# import httpx
# import logging


# # class OpenAiLLM:

# #     def __init__(self, url, api_key, model_name):
# #         self._api_key = api_key
# #         self._url = url
# #         self._model = model_name

# #     def generate(self, prompt):

# #         client = OpenAI(api_key=self._api_key, base_url=self._url)

# #         try:
# #             # 创建 Completion 请求
# #             completion = client.chat.completions.create(
# #                 model=self._model,
# #                 messages=[
# #                     {"role": "system", "content": "You are a helpful assistant"},
# #                     {"role": "user", "content": prompt}
# #                 ],
# #                 timeout=httpx.Timeout(300.0),
# #                 temperature=0.7,
# #             )
# #             return completion.choices[0].message.content
# #         except Exception as e:
# #             logging.error(f"LLM调用出错: {e}")
# #             return f"模型调用失败: {str(e)}"


# # llm = OpenAiLLM(
# #     url="http://172.20.0.145:9995/v1",
# #     api_key="xxx",
# #     model_name="deepseek-r1-distill-qwen2.5-32b",
# # )


# class Embedding:
#     def __init__(self, url, api_key, model_name):
#         self._api_key = api_key
#         self._url = url
#         self._model = model_name

#     def embed(self, text):
#         # 使用OpenAI客户端
#         client = OpenAI(api_key=self._api_key, base_url=self._url)

#         try:
#             # 调用embeddings API
#             response = client.embeddings.create(model=self._model, input=text, timeout=httpx.Timeout(60.0))
#             # 返回嵌入向量
#             return response.data[0].embedding
#         except Exception as e:
#             logging.error(f"嵌入模型调用出错: {e}")
#             raise RuntimeError(f"嵌入请求失败: {str(e)}")


# embedding = Embedding(url="http://172.20.0.145:9995/v1", api_key="xxx", model_name="bge-m3")


# class SiliconFlowLLM(BaseLLM):
#     """自定义硅基流动大模型调用类"""

#     api_url: str
#     api_key: str
#     model: str

#     def _generate(
#         self,
#         prompts: List[str],
#         stop: Optional[List[str]] = None,
#         run_manager: Optional[CallbackManagerForLLMRun] = None,
#         **kwargs: Any,
#     ) -> LLMResult:
#         from langchain_core.outputs import Generation, LLMResult

#         generations = []
#         for prompt in prompts:
#             try:
#                 headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
#                 payload = {
#                     "model": self.model,
#                     "messages": [{"role": "user", "content": prompt}],
#                 }
#                 response = requests.post(self.api_url, json=payload, headers=headers)
#                 response.raise_for_status()
#                 text = response.json()["choices"][0]["message"]["content"]
#                 generations.append([Generation(text=text)])
#             except Exception as e:
#                 raise Exception(f"调用硅基流动API失败: {str(e)}")

#         return LLMResult(generations=generations)

#     @property
#     def _llm_type(self) -> str:
#         return "siliconflow"


# llm = SiliconFlowLLM(
#     api_url="https://api.siliconflow.cn/v1/chat/completions",
#     api_key="sk-bbeamiumkouptsrueilgufqqyuumelcsivxwjbdugqwsqhwj",
#     model="Qwen/Qwen2.5-72B-Instruct",
# )

from equipment_calculation.main import bcl_calculate

input_dir = "data/output/merged"
output_dir = "data/output/bclresults"
bcl_dir_path = "data/output/bcl"

# 可选：指定 BCL 目录；此处不指定，沿用默认配置或调用方传入
bcl_calculate(input_dir, output_dir, bcl_dir_path=bcl_dir_path)