50 lines
1.9 KiB
Python
50 lines
1.9 KiB
Python
import os
|
|
import sys
|
|
|
|
sys.path.append(os.getcwd())
|
|
import rag2_0.dify.dify_client.dify_api as DifyApi
|
|
|
|
import pandas as pd
|
|
pd_data = pd.read_excel("data/excel/工单汇总(给AI)_工单拆分.xlsx")
|
|
|
|
|
|
dify_api = DifyApi.DifyApi()
|
|
peiwang_dataset_id = dify_api.get_or_create_dataset_by_name("配网工单数据")
|
|
zhuwang_dataset_id = dify_api.get_or_create_dataset_by_name("主网工单数据")
|
|
jianga_dataset_id = dify_api.get_or_create_dataset_by_name("技改工单数据")
|
|
chuneng_dataset_id = dify_api.get_or_create_dataset_by_name("储能工单数据")
|
|
xizang_dataset_id = dify_api.get_or_create_dataset_by_name("西藏工单数据")
|
|
|
|
|
|
soft_segments_list={}
|
|
for index, row in pd_data.iterrows():
|
|
query = row["客户问题"]
|
|
answer = row["解决方案"]
|
|
skill_group = row["技能组"]
|
|
|
|
content = f"问题：{query}\n回答：{answer}"
|
|
if skill_group not in soft_segments_list:
|
|
soft_segments_list[skill_group]=[]
|
|
soft_segments_list[skill_group].append({
|
|
"content": str(content),
|
|
"answer": "",
|
|
"keywords": []
|
|
})
|
|
|
|
for skill_group, segments_list in soft_segments_list.items():
|
|
if skill_group == "配网":
|
|
dataset_id = peiwang_dataset_id
|
|
elif skill_group == "主网":
|
|
dataset_id = zhuwang_dataset_id
|
|
elif skill_group == "技改":
|
|
dataset_id = jianga_dataset_id
|
|
elif skill_group == "储能":
|
|
dataset_id = chuneng_dataset_id
|
|
elif skill_group == "西藏":
|
|
dataset_id = xizang_dataset_id
|
|
else:
|
|
continue
|
|
document_id = dify_api.get_document_id(dataset_id=dataset_id, document_name=f"{skill_group}工单数据")
|
|
if not document_id:
|
|
document_id = dify_api.upload_text_to_document(text_name=f"{skill_group}工单数据", text="", dataset_id=dataset_id)
|
|
dify_api.add_document_segments(dataset_id=dataset_id, document_id=document_id, segments_list=segments_list) |