mirror of
https://github.com/OpenSPG/KAG.git
synced 2025-07-12 19:46:22 +00:00

* add path find * fix find path * spg guided relation extraction * fix dict parse with same key * rename graphalgoclient to graphclient * rename graphalgoclient to graphclient * file reader supports http url * add checkpointer class * parser supports checkpoint * add build * remove incorrect logs * remove logs * update examples * update chain checkpointer * vectorizer batch size set to 32 * add a zodb backended checkpointer * add a zodb backended checkpointer * fix zodb based checkpointer * add thread for zodb IO * fix(common): resolve mutlithread conflict in zodb IO * fix(common): load existing zodb checkpoints * update examples * update examples * fix zodb writer * add docstring * fix jieba version mismatch * commit kag_config-tc.yaml 1、rename type to register_name 2、put a uniqe & specific name to register_name 3、rename reader to scanner 4、rename parser to reader 5、rename num_parallel to num_parallel_file, rename chain_level_num_paralle to num_parallel_chain_of_file 6、rename kag_extractor to schema_free_extractor, schema_base_extractor to schema_constraint_extractor 7、pre-define llm & vectorize_model and refer them in the yaml file Issues to be resolved: 1、examples of event extract & spg extract 2、statistic of indexer, such as nums of nodes & edges extracted, ratio of llm invoke. 3、Exceptions such as Debt, account does not exist should be thrown in llm invoke. 4、conf of solver need to be re-examined. * commit kag_config-tc.yaml 1、rename type to register_name 2、put a uniqe & specific name to register_name 3、rename reader to scanner 4、rename parser to reader 5、rename num_parallel to num_parallel_file, rename chain_level_num_paralle to num_parallel_chain_of_file 6、rename kag_extractor to schema_free_extractor, schema_base_extractor to schema_constraint_extractor 7、pre-define llm & vectorize_model and refer them in the yaml file Issues to be resolved: 1、examples of event extract & spg extract 2、statistic of indexer, such as nums of nodes & edges extracted, ratio of llm invoke. 3、Exceptions such as Debt, account does not exist should be thrown in llm invoke. 4、conf of solver need to be re-examined. * 1、fix bug in base_table_splitter * 1、fix bug in base_table_splitter * 1、fix bug in default_chain * 增加solver * add kag * update outline splitter * add main test * add op * code refactor * add tools * fix outline splitter * fix outline prompt * graph api pass * commit with page rank * add search api and graph api * add markdown report * fix vectorizer num batch compute * add retry for vectorize model call * update markdown reader * update markdown reader * update pdf reader * raise extractor failure * add default expr * add log * merge jc reader features * rm import * add build * fix zodb based checkpointer * add thread for zodb IO * fix(common): resolve mutlithread conflict in zodb IO * fix(common): load existing zodb checkpoints * update examples * update examples * fix zodb writer * add docstring * fix jieba version mismatch * commit kag_config-tc.yaml 1、rename type to register_name 2、put a uniqe & specific name to register_name 3、rename reader to scanner 4、rename parser to reader 5、rename num_parallel to num_parallel_file, rename chain_level_num_paralle to num_parallel_chain_of_file 6、rename kag_extractor to schema_free_extractor, schema_base_extractor to schema_constraint_extractor 7、pre-define llm & vectorize_model and refer them in the yaml file Issues to be resolved: 1、examples of event extract & spg extract 2、statistic of indexer, such as nums of nodes & edges extracted, ratio of llm invoke. 3、Exceptions such as Debt, account does not exist should be thrown in llm invoke. 4、conf of solver need to be re-examined. * commit kag_config-tc.yaml 1、rename type to register_name 2、put a uniqe & specific name to register_name 3、rename reader to scanner 4、rename parser to reader 5、rename num_parallel to num_parallel_file, rename chain_level_num_paralle to num_parallel_chain_of_file 6、rename kag_extractor to schema_free_extractor, schema_base_extractor to schema_constraint_extractor 7、pre-define llm & vectorize_model and refer them in the yaml file Issues to be resolved: 1、examples of event extract & spg extract 2、statistic of indexer, such as nums of nodes & edges extracted, ratio of llm invoke. 3、Exceptions such as Debt, account does not exist should be thrown in llm invoke. 4、conf of solver need to be re-examined. * 1、fix bug in base_table_splitter * 1、fix bug in base_table_splitter * 1、fix bug in default_chain * update outline splitter * add main test * add markdown report * code refactor * fix outline splitter * fix outline prompt * update markdown reader * fix vectorizer num batch compute * add retry for vectorize model call * update markdown reader * raise extractor failure * rm parser * run pipeline * add config option of whether to perform llm config check, default to false * fix * recover pdf reader * several components can be null for default chain * 支持完整qa运行 * add if * remove unused code * 使用chunk兜底 * excluded source relation to choose * add generate * default recall 10 * add local memory * 排除相似边 * 增加保护 * 修复并发问题 * add debug logger * 支持topk参数化 * 支持chunk截断和调整spo select 的prompt * 增加查询请求保护 * 增加force_chunk配置 * fix entity linker algorithm * 增加sub query改写 * fix md reader dup in test * fix * merge knext to kag parallel * fix package * 修复指标下跌问题 * scanner update * scanner update * add doc and update example scripts * fix * add bridge to spg server * add format * fix bridge * update conf for baike * disable ckpt for spg server runner * llm invoke error default raise exceptions * chore(version): bump version to X.Y.Z * update default response generation prompt * add method getSummarizationMetrics * fix(common): fix project conf empty error * fix typo * 增加上报信息 * 修改main solver * postprocessor support spg server * 修改solver支持名 * fix language * 修改chunker接口,增加openapi * rename vectorizer to vectorize_model in spg server config * generate_random_string start with gen * add knext llm vector checker * add knext llm vector checker * add knext llm vector checker * solver移除默认值 * udpate yaml and register_name for baike * udpate yaml and register_name for baike * remove config key check * 修复llmmodule * fix knext project * udpate yaml and register_name for examples * udpate yaml and register_name for examples * Revert "udpate yaml and register_name for examples" This reverts commit b3fa5ca9ba749e501133ac67bd8746027ab839d9. * update register name * fix * fix * support multiple resigter names * update component * update reader register names (#183) * fix markdown reader * fix llm client for retry * feat(common): add processed chunk id checkpoint (#185) * update reader register names * add processed chunk id checkpoint * feat(example): add example config (#186) * update reader register names * add processed chunk id checkpoint * add example config file * add max_workers parameter for getSummarizationMetrics to make it faster * add csqa data generation script generate_data.py * commit generated csqa builder and solver data * add csqa basic project files * adjust split_length and num_threads_per_chain to match lightrag settings * ignore ckpt dirs * add csqa evaluation script eval.py * save evaluation scripts summarization_metrics.py and factual_correctness.py * save LightRAG output csqa_lightrag_answers.json * ignore KAG output csqa_kag_answers.json * add README.md for CSQA * fix(solver): fix solver pipeline conf (#191) * update reader register names * add processed chunk id checkpoint * add example config file * update solver pipeline config * fix project create * update links and file paths * reformat csqa kag_config.yaml * reformat csqa python files * reformat getSummarizationMetrics and compare_summarization_answers * fix(solver): fix solver config (#192) * update reader register names * add processed chunk id checkpoint * add example config file * update solver pipeline config * fix project create * fix main solver conf * add except * fix typo in csqa README.md * feat(conf): support reinitialize config for call from java side (#199) * update reader register names * add processed chunk id checkpoint * add example config file * update solver pipeline config * fix project create * fix main solver conf * support reinitialize config for java call * revert default response generation prompt * update project list * add README.md for the hotpotqa, 2wiki and musique examples * 增加spo检索 * turn off kag config dump by default * turn off knext schema dump by default * add .gitignore and fix kag_config.yaml * add README.md for the medicine example * add README.md for the supplychain example * bugfix for risk mining * use exact out * refactor(solver): format solver code (#205) * update reader register names * add processed chunk id checkpoint * add example config file * update solver pipeline config * fix project create * fix main solver conf * support reinitialize config for java call * black format --------- Co-authored-by: peilong <peilong.zpl@antgroup.com> Co-authored-by: 锦呈 <zhangxinhong.zxh@antgroup.com> Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com> Co-authored-by: huaidong.xhd <huaidong.xhd@antgroup.com>
219 lines
6.1 KiB
Python
219 lines
6.1 KiB
Python
# coding: utf-8
|
|
# Copyright 2023 OpenSPG Authors
|
|
#
|
|
# 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.
|
|
|
|
|
|
"""
|
|
knext
|
|
|
|
No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) # noqa: E501
|
|
|
|
The version of the OpenAPI document: 1.0.0
|
|
Generated by: https://openapi-generator.tech
|
|
"""
|
|
|
|
|
|
import pprint
|
|
import re # noqa: F401
|
|
|
|
import six
|
|
|
|
from knext.common.rest.configuration import Configuration
|
|
|
|
|
|
class WriterGraphRequest(object):
|
|
"""NOTE: This class is auto generated by OpenAPI Generator.
|
|
Ref: https://openapi-generator.tech
|
|
|
|
Do not edit the class manually.
|
|
"""
|
|
|
|
"""
|
|
Attributes:
|
|
openapi_types (dict): The key is attribute name
|
|
and the value is attribute type.
|
|
attribute_map (dict): The key is attribute name
|
|
and the value is json key in definition.
|
|
"""
|
|
openapi_types = {
|
|
"project_id": "int",
|
|
"operation": "str",
|
|
"sub_graph": "object",
|
|
"enable_lead_to": "bool",
|
|
}
|
|
|
|
attribute_map = {
|
|
"project_id": "projectId",
|
|
"operation": "operation",
|
|
"sub_graph": "subGraph",
|
|
"enable_lead_to": "enableLeadTo",
|
|
}
|
|
|
|
def __init__(
|
|
self,
|
|
project_id=None,
|
|
operation=None,
|
|
sub_graph=None,
|
|
enable_lead_to=None,
|
|
local_vars_configuration=None,
|
|
): # noqa: E501
|
|
"""WriterGraphRequest - a model defined in OpenAPI""" # noqa: E501
|
|
if local_vars_configuration is None:
|
|
local_vars_configuration = Configuration()
|
|
self.local_vars_configuration = local_vars_configuration
|
|
|
|
self._project_id = None
|
|
self._operation = None
|
|
self._sub_graph = None
|
|
self._enable_lead_to = None
|
|
self.discriminator = None
|
|
|
|
if project_id is not None:
|
|
self.project_id = project_id
|
|
if operation is not None:
|
|
self.operation = operation
|
|
if sub_graph is not None:
|
|
self.sub_graph = sub_graph
|
|
if enable_lead_to is not None:
|
|
self.enable_lead_to = enable_lead_to
|
|
|
|
@property
|
|
def project_id(self):
|
|
"""Gets the project_id of this WriterGraphRequest. # noqa: E501
|
|
|
|
|
|
:return: The project_id of this WriterGraphRequest. # noqa: E501
|
|
:rtype: int
|
|
"""
|
|
return self._project_id
|
|
|
|
@project_id.setter
|
|
def project_id(self, project_id):
|
|
"""Sets the project_id of this WriterGraphRequest.
|
|
|
|
|
|
:param project_id: The project_id of this WriterGraphRequest. # noqa: E501
|
|
:type: int
|
|
"""
|
|
|
|
self._project_id = project_id
|
|
|
|
@property
|
|
def operation(self):
|
|
"""Gets the operation of this WriterGraphRequest. # noqa: E501
|
|
|
|
|
|
:return: The operation of this WriterGraphRequest. # noqa: E501
|
|
:rtype: str
|
|
"""
|
|
return self._operation
|
|
|
|
@operation.setter
|
|
def operation(self, operation):
|
|
"""Sets the operation of this WriterGraphRequest.
|
|
|
|
|
|
:param operation: The operation of this WriterGraphRequest. # noqa: E501
|
|
:type: str
|
|
"""
|
|
|
|
self._operation = operation
|
|
|
|
@property
|
|
def sub_graph(self):
|
|
"""Gets the sub_graph of this WriterGraphRequest. # noqa: E501
|
|
|
|
|
|
:return: The sub_graph of this WriterGraphRequest. # noqa: E501
|
|
:rtype: object
|
|
"""
|
|
return self._sub_graph
|
|
|
|
@sub_graph.setter
|
|
def sub_graph(self, sub_graph):
|
|
"""Sets the sub_graph of this WriterGraphRequest.
|
|
|
|
|
|
:param sub_graph: The sub_graph of this WriterGraphRequest. # noqa: E501
|
|
:type: object
|
|
"""
|
|
|
|
self._sub_graph = sub_graph
|
|
|
|
@property
|
|
def enable_lead_to(self):
|
|
"""Gets the enable_lead_to of this WriterGraphRequest. # noqa: E501
|
|
|
|
|
|
:return: The enable_lead_to of this WriterGraphRequest. # noqa: E501
|
|
:rtype: bool
|
|
"""
|
|
return self._enable_lead_to
|
|
|
|
@enable_lead_to.setter
|
|
def enable_lead_to(self, enable_lead_to):
|
|
"""Sets the enable_lead_to of this WriterGraphRequest.
|
|
|
|
|
|
:param enable_lead_to: The enable_lead_to of this WriterGraphRequest. # noqa: E501
|
|
:type: bool
|
|
"""
|
|
|
|
self._enable_lead_to = enable_lead_to
|
|
|
|
def to_dict(self):
|
|
"""Returns the model properties as a dict"""
|
|
result = {}
|
|
|
|
for attr, _ in six.iteritems(self.openapi_types):
|
|
value = getattr(self, attr)
|
|
if isinstance(value, list):
|
|
result[attr] = list(
|
|
map(lambda x: x.to_dict() if hasattr(x, "to_dict") else x, value)
|
|
)
|
|
elif hasattr(value, "to_dict"):
|
|
result[attr] = value.to_dict()
|
|
elif isinstance(value, dict):
|
|
result[attr] = dict(
|
|
map(
|
|
lambda item: (item[0], item[1].to_dict())
|
|
if hasattr(item[1], "to_dict")
|
|
else item,
|
|
value.items(),
|
|
)
|
|
)
|
|
else:
|
|
result[attr] = value
|
|
|
|
return result
|
|
|
|
def to_str(self):
|
|
"""Returns the string representation of the model"""
|
|
return pprint.pformat(self.to_dict())
|
|
|
|
def __repr__(self):
|
|
"""For `print` and `pprint`"""
|
|
return self.to_str()
|
|
|
|
def __eq__(self, other):
|
|
"""Returns true if both objects are equal"""
|
|
if not isinstance(other, WriterGraphRequest):
|
|
return False
|
|
|
|
return self.to_dict() == other.to_dict()
|
|
|
|
def __ne__(self, other):
|
|
"""Returns true if both objects are not equal"""
|
|
if not isinstance(other, WriterGraphRequest):
|
|
return True
|
|
|
|
return self.to_dict() != other.to_dict()
|