57 lines
1.8 KiB
Python
57 lines
1.8 KiB
Python
from ragflow_sdk import RAGFlow
|
|
|
|
#api_key = "ragflow-I5ZDNjMWNhNTdlMjExZjBiOTEwMzI0ZT"
|
|
#base_url = "http://192.168.107.165:8099"
|
|
base_url = "http://localhost:8099"
|
|
api_key = "ragflow-MyMjM2ODE2NThlMTExZjBiMzJlNzY5Mj"
|
|
|
|
rag_object = RAGFlow(api_key=api_key, base_url=base_url)
|
|
#dataset = rag_object.create_dataset(name="kb_1")
|
|
|
|
datasets = rag_object.list_datasets()
|
|
#dataset = rag_object.list_datasets(name="kb_1")
|
|
dataset = rag_object.list_datasets(name="制度")
|
|
|
|
dataset = dataset[0]
|
|
|
|
# filename1 = "ragflow.txt"
|
|
# blob = open(filename1 , "rb").read()
|
|
# dataset.upload_documents([{"display_name":filename1,"blob":blob}])
|
|
# for doc in dataset.list_documents( page=0, page_size=12):
|
|
# print(doc)
|
|
# print("=========================================")
|
|
|
|
|
|
doc = dataset.list_documents(name= '科技创新管理办法（试行）.pdf')
|
|
doc = doc[0]
|
|
# doc.update({"parser_config": {"chunk_token_count": 256}})
|
|
file_path ="G:\\11\\ragflow_api_test\\1.txt"
|
|
with open(file_path, 'r', encoding='utf-8') as file:
|
|
file_content = file.read()
|
|
for num,txt_chunk in enumerate(file_content.split('\n\n')):
|
|
print(f"处理文本块: {txt_chunk[:30]}...") # 打印前30个字符以示例
|
|
|
|
if txt_chunk.strip(): # 确保不是空行
|
|
chunk = doc.add_chunk(content=txt_chunk)
|
|
print(f"第{num+1} Chunk添加成功! ID: {chunk.id}")
|
|
|
|
|
|
|
|
# content = '''
|
|
# 第二章 部门职责>第六条 【财务管理部】
|
|
# （一） 配合投标相关费用的办理工作；
|
|
# （二） 负责提供投标所需的相关财务资料。'''
|
|
# chunk = doc.add_chunk(content=content)
|
|
# print(f"Chunk添加成功! ID: {chunk.id}")
|
|
#dataset.upload_documents([{"display_name": "1.txt", "blob": open('1.txt',"rb").read()}])
|
|
|
|
# 查询所有知识库
|
|
# for dataset in rag_object.list_datasets():
|
|
# print(dataset)
|
|
|
|
|
|
# dataset = rag_object.list_datasets(name = "制度")
|
|
#print(dataset)
|
|
|
|
|