dnrops
/
KAG
mirror of https://github.com/OpenSPG/KAG
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,259 Commits 110 Branches 7 Tags 278 MiB
Commit Graph

1259 Commits

Author SHA1 Message Date
royzhao 5975127bc0
fix config (#642) 2025-07-16 14:27:07 +08:00
royzhao e1012d39e4
feat(solver): support kag thinker (#640) 
* feat(kag): update to v0.7 (#456)

* add think cost

* update csv scanner

* add final rerank

* add reasoner

* add iterative planner

* fix dpr search

* fix dpr search

* add reference data

* move odps import

* update requirement.txt

* update 2wiki

* add missing file

* fix markdown reader

* add iterative planning

* update version

* update runner

* update 2wiki example

* update bridge

* merge solver and solver_new

* add cur day

* writer delete

* update multi process

* add missing files

* fix report

* add chunk retrieved executor

* update try in stream runner result

* add path

* add math executor

* update hotpotqa example

* remove log

* fix python coder solver

* update hotpotqa example

* fix python coder solver

* update config

* fix bad

* add log

* remove unused code

* commit with task thought

* move kag model to common

* add default chat llm

* fix

* use static planner

* support chunk graph node

* add args

* support naive rag

* llm client support tool calls

* add default async

* add openai

* fix result

* fix markdown reader

* fix thinker

* update asyncio interface

* feat(solver): add mcp support (#444)

* 上传mcp client相关代码

* 1、完成一套mcp client的调用，从pipeline到planner、executor
2、允许json中传入多个mcp_server，通过大模型进行调用并选择
3、调通baidu_map_mcp的使用

* 1、schema

* bugfix:删减冗余代码

---------

Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>

* fix affairqa after solver refactor

* fix affairqa after solver refactor

* fix readme

* add params

* update version

* update mcp executor

* update mcp executor

* solver add mcp executor

* add missing file

* add mpc executor

* add executor

* x

* update

* fix requirement

* fix main llm config

* fix solver

* bugfix:修复invoke函数调用逻辑

* chg eva

* update example

* add kag layer

* add step task

* support dot refresh

* support dot refresh

* support dot refresh

* support dot refresh

* add retrieved num

* add retrieved num

* add pipelineconf

* update ppr

* update musique prompts

* update

* add to_dict for BuilderComponentData

* async build

* add deduce prompt

* add deduce prompt

* add deduce prompt

* fix reader

* add deduce prompt

* add page thinker report

* modify prmpt

* add step status

* add self cognition

* add self cognition

* add memory graph storage

* add now time

* update memory config

* add now time

* chg graph loader

* 添加prqa数据集和代码

* bugfix:prqa调用逻辑修复

* optimize：优化代码逻辑，生成答案规范化

* add retry py code

* update memory graph

* update memory graph

* fix

* fix ner

* add with_out_refer generator prompt

* fix

* close ckpt

* fix query

* fix query

* update version

* add llm checker

* add llm checker

* 1、上传evalutor.py以及修改gold_answer.json格式
2、优化代码逻辑
3、修改README.md文件

* update exp

* update exp

* rerank support

* add static rewrite query

* recall more chunks

* fix graph load

* add static rewrite query

* fix bugs

* add finish check

* add finish check

* add finish check

* add finish check

* 1、上传evalutor.py的结果
2、优化代码逻辑，优化readme文件

* add lf retry

* add memory graph api

* fix reader api

* add ner

* add metrics

* fix bug

* remove ner

* add reraise fo retry

* add edge prop to memory graph

* add memory graph

* 1、评测数据集结果修正
2、优化evaluator.py代码
3、删除结果不存在而gold_answer中有答案的问题

* 删除评测结果文件

* fix knext host addr

* async eva

* add lf prompt

* add lf prompt

* add config

* add retry

* add unknown check

* add rc result

* add rc result

* add rc result

* add rc result

* 依据kag pipeline格式修改代码逻辑并通过测试

* bugfix:删除冗余代码

* fix report prompt

* bugfix:触发重试机制

* bugfix:中文符号错误

* fix rethinker prompt

* update version to 0.6.2b78

* update version

* 1、修改evaluator.py，通过大模型计算准确率，符合最新调用逻辑
2、修改prompt，让没有回答的结果重复测试

* update affairqa for evaluate

* update affairqa for evaluate

* bugfix:修正数据集

* bugfix:修正数据集

* bugfix:修正数据集

* fix name conflict

* bugfix:删除错误问题

* bugfix:文件名命名错误导致evaluator失败

* update for affairqa eval

* bugfix:修改代码保持evaluate逻辑一致

* x

* update for affairqa readme

* remove temp eval scripts

* bugfix for math deduce

* merge 0.6.2_dev

* merge 0.6.2_dev

* fix

* update client addr

* updated version

* update for affairqa eval

* evaUtils 支持中文

* fix affairqa eval:

* remove unused example

* update kag config

* fix default value

* update readme

* fix init

* 注释信息修改，并添加部分class说明

* update example config

* Tc 0.7.0 (#459)

* 提交affairQA 代码

* fix affairqa eval

---------

Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>

* fix all examples

* reformat

---------

Co-authored-by: peilong <peilong.zpl@antgroup.com>
Co-authored-by: 锦呈 <zhangxinhong.zxh@antgroup.com>
Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>
Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>

* update chunk metadata

* update chunk metadata

* add debug reporter

* update table text

* add server

* fix math executor

* update api-key for openai vec

* update

* fix naive rag bug

* format code

* fix

---------

Co-authored-by: zhuzhongshu123 <152354526+zhuzhongshu123@users.noreply.github.com>
Co-authored-by: 锦呈 <zhangxinhong.zxh@antgroup.com>
Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>
Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>
 2025-07-08 17:44:32 +08:00
thundax 9b2d894295
fix(builder): remove KAG_PROJECT_CONF (#628) 
* fix(builder): remove KAG_PROJECT_CONF

* fix(builder): formatter

* fix(builder): copy logic from get_dense_placeholder() into get_sparse_placeholder()

* fix(tools): use self.score_normalizer in invoke

* fix(builder): prompt 'knowledge_unit_triple' missing '$'
 2025-07-08 17:05:19 +08:00
Xinhong Zhang 53f29b4967
fix(common): OpenAI vec 0701 (#630) 
* feat(kag): update to v0.7 (#456)

* add think cost

* update csv scanner

* add final rerank

* add reasoner

* add iterative planner

* fix dpr search

* fix dpr search

* add reference data

* move odps import

* update requirement.txt

* update 2wiki

* add missing file

* fix markdown reader

* add iterative planning

* update version

* update runner

* update 2wiki example

* update bridge

* merge solver and solver_new

* add cur day

* writer delete

* update multi process

* add missing files

* fix report

* add chunk retrieved executor

* update try in stream runner result

* add path

* add math executor

* update hotpotqa example

* remove log

* fix python coder solver

* update hotpotqa example

* fix python coder solver

* update config

* fix bad

* add log

* remove unused code

* commit with task thought

* move kag model to common

* add default chat llm

* fix

* use static planner

* support chunk graph node

* add args

* support naive rag

* llm client support tool calls

* add default async

* add openai

* fix result

* fix markdown reader

* fix thinker

* update asyncio interface

* feat(solver): add mcp support (#444)

* 上传mcp client相关代码

* 1、完成一套mcp client的调用，从pipeline到planner、executor
2、允许json中传入多个mcp_server，通过大模型进行调用并选择
3、调通baidu_map_mcp的使用

* 1、schema

* bugfix:删减冗余代码

---------

Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>

* fix affairqa after solver refactor

* fix affairqa after solver refactor

* fix readme

* add params

* update version

* update mcp executor

* update mcp executor

* solver add mcp executor

* add missing file

* add mpc executor

* add executor

* x

* update

* fix requirement

* fix main llm config

* fix solver

* bugfix:修复invoke函数调用逻辑

* chg eva

* update example

* add kag layer

* add step task

* support dot refresh

* support dot refresh

* support dot refresh

* support dot refresh

* add retrieved num

* add retrieved num

* add pipelineconf

* update ppr

* update musique prompts

* update

* add to_dict for BuilderComponentData

* async build

* add deduce prompt

* add deduce prompt

* add deduce prompt

* fix reader

* add deduce prompt

* add page thinker report

* modify prmpt

* add step status

* add self cognition

* add self cognition

* add memory graph storage

* add now time

* update memory config

* add now time

* chg graph loader

* 添加prqa数据集和代码

* bugfix:prqa调用逻辑修复

* optimize：优化代码逻辑，生成答案规范化

* add retry py code

* update memory graph

* update memory graph

* fix

* fix ner

* add with_out_refer generator prompt

* fix

* close ckpt

* fix query

* fix query

* update version

* add llm checker

* add llm checker

* 1、上传evalutor.py以及修改gold_answer.json格式
2、优化代码逻辑
3、修改README.md文件

* update exp

* update exp

* rerank support

* add static rewrite query

* recall more chunks

* fix graph load

* add static rewrite query

* fix bugs

* add finish check

* add finish check

* add finish check

* add finish check

* 1、上传evalutor.py的结果
2、优化代码逻辑，优化readme文件

* add lf retry

* add memory graph api

* fix reader api

* add ner

* add metrics

* fix bug

* remove ner

* add reraise fo retry

* add edge prop to memory graph

* add memory graph

* 1、评测数据集结果修正
2、优化evaluator.py代码
3、删除结果不存在而gold_answer中有答案的问题

* 删除评测结果文件

* fix knext host addr

* async eva

* add lf prompt

* add lf prompt

* add config

* add retry

* add unknown check

* add rc result

* add rc result

* add rc result

* add rc result

* 依据kag pipeline格式修改代码逻辑并通过测试

* bugfix:删除冗余代码

* fix report prompt

* bugfix:触发重试机制

* bugfix:中文符号错误

* fix rethinker prompt

* update version to 0.6.2b78

* update version

* 1、修改evaluator.py，通过大模型计算准确率，符合最新调用逻辑
2、修改prompt，让没有回答的结果重复测试

* update affairqa for evaluate

* update affairqa for evaluate

* bugfix:修正数据集

* bugfix:修正数据集

* bugfix:修正数据集

* fix name conflict

* bugfix:删除错误问题

* bugfix:文件名命名错误导致evaluator失败

* update for affairqa eval

* bugfix:修改代码保持evaluate逻辑一致

* x

* update for affairqa readme

* remove temp eval scripts

* bugfix for math deduce

* merge 0.6.2_dev

* merge 0.6.2_dev

* fix

* update client addr

* updated version

* update for affairqa eval

* evaUtils 支持中文

* fix affairqa eval:

* remove unused example

* update kag config

* fix default value

* update readme

* fix init

* 注释信息修改，并添加部分class说明

* update example config

* Tc 0.7.0 (#459)

* 提交affairQA 代码

* fix affairqa eval

---------

Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>

* fix all examples

* reformat

---------

Co-authored-by: peilong <peilong.zpl@antgroup.com>
Co-authored-by: 锦呈 <zhangxinhong.zxh@antgroup.com>
Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>
Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>

* update openai vec

* update

* update api-key for openai vec

* update api-key for openai vec

---------

Co-authored-by: zhuzhongshu123 <152354526+zhuzhongshu123@users.noreply.github.com>
Co-authored-by: peilong <peilong.zpl@antgroup.com>
Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>
Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>
 2025-07-03 20:00:38 +08:00
Xinhong Zhang 52204cf7ef
fix(common): chunk metadata 0701 (#624) 
* feat(kag): update to v0.7 (#456)

* add think cost

* update csv scanner

* add final rerank

* add reasoner

* add iterative planner

* fix dpr search

* fix dpr search

* add reference data

* move odps import

* update requirement.txt

* update 2wiki

* add missing file

* fix markdown reader

* add iterative planning

* update version

* update runner

* update 2wiki example

* update bridge

* merge solver and solver_new

* add cur day

* writer delete

* update multi process

* add missing files

* fix report

* add chunk retrieved executor

* update try in stream runner result

* add path

* add math executor

* update hotpotqa example

* remove log

* fix python coder solver

* update hotpotqa example

* fix python coder solver

* update config

* fix bad

* add log

* remove unused code

* commit with task thought

* move kag model to common

* add default chat llm

* fix

* use static planner

* support chunk graph node

* add args

* support naive rag

* llm client support tool calls

* add default async

* add openai

* fix result

* fix markdown reader

* fix thinker

* update asyncio interface

* feat(solver): add mcp support (#444)

* 上传mcp client相关代码

* 1、完成一套mcp client的调用，从pipeline到planner、executor
2、允许json中传入多个mcp_server，通过大模型进行调用并选择
3、调通baidu_map_mcp的使用

* 1、schema

* bugfix:删减冗余代码

---------

Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>

* fix affairqa after solver refactor

* fix affairqa after solver refactor

* fix readme

* add params

* update version

* update mcp executor

* update mcp executor

* solver add mcp executor

* add missing file

* add mpc executor

* add executor

* x

* update

* fix requirement

* fix main llm config

* fix solver

* bugfix:修复invoke函数调用逻辑

* chg eva

* update example

* add kag layer

* add step task

* support dot refresh

* support dot refresh

* support dot refresh

* support dot refresh

* add retrieved num

* add retrieved num

* add pipelineconf

* update ppr

* update musique prompts

* update

* add to_dict for BuilderComponentData

* async build

* add deduce prompt

* add deduce prompt

* add deduce prompt

* fix reader

* add deduce prompt

* add page thinker report

* modify prmpt

* add step status

* add self cognition

* add self cognition

* add memory graph storage

* add now time

* update memory config

* add now time

* chg graph loader

* 添加prqa数据集和代码

* bugfix:prqa调用逻辑修复

* optimize：优化代码逻辑，生成答案规范化

* add retry py code

* update memory graph

* update memory graph

* fix

* fix ner

* add with_out_refer generator prompt

* fix

* close ckpt

* fix query

* fix query

* update version

* add llm checker

* add llm checker

* 1、上传evalutor.py以及修改gold_answer.json格式
2、优化代码逻辑
3、修改README.md文件

* update exp

* update exp

* rerank support

* add static rewrite query

* recall more chunks

* fix graph load

* add static rewrite query

* fix bugs

* add finish check

* add finish check

* add finish check

* add finish check

* 1、上传evalutor.py的结果
2、优化代码逻辑，优化readme文件

* add lf retry

* add memory graph api

* fix reader api

* add ner

* add metrics

* fix bug

* remove ner

* add reraise fo retry

* add edge prop to memory graph

* add memory graph

* 1、评测数据集结果修正
2、优化evaluator.py代码
3、删除结果不存在而gold_answer中有答案的问题

* 删除评测结果文件

* fix knext host addr

* async eva

* add lf prompt

* add lf prompt

* add config

* add retry

* add unknown check

* add rc result

* add rc result

* add rc result

* add rc result

* 依据kag pipeline格式修改代码逻辑并通过测试

* bugfix:删除冗余代码

* fix report prompt

* bugfix:触发重试机制

* bugfix:中文符号错误

* fix rethinker prompt

* update version to 0.6.2b78

* update version

* 1、修改evaluator.py，通过大模型计算准确率，符合最新调用逻辑
2、修改prompt，让没有回答的结果重复测试

* update affairqa for evaluate

* update affairqa for evaluate

* bugfix:修正数据集

* bugfix:修正数据集

* bugfix:修正数据集

* fix name conflict

* bugfix:删除错误问题

* bugfix:文件名命名错误导致evaluator失败

* update for affairqa eval

* bugfix:修改代码保持evaluate逻辑一致

* x

* update for affairqa readme

* remove temp eval scripts

* bugfix for math deduce

* merge 0.6.2_dev

* merge 0.6.2_dev

* fix

* update client addr

* updated version

* update for affairqa eval

* evaUtils 支持中文

* fix affairqa eval:

* remove unused example

* update kag config

* fix default value

* update readme

* fix init

* 注释信息修改，并添加部分class说明

* update example config

* Tc 0.7.0 (#459)

* 提交affairQA 代码

* fix affairqa eval

---------

Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>

* fix all examples

* reformat

---------

Co-authored-by: peilong <peilong.zpl@antgroup.com>
Co-authored-by: 锦呈 <zhangxinhong.zxh@antgroup.com>
Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>
Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>

* update chunk metadata

* update chunk metadata

* update table text

---------

Co-authored-by: zhuzhongshu123 <152354526+zhuzhongshu123@users.noreply.github.com>
Co-authored-by: peilong <peilong.zpl@antgroup.com>
Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>
Co-authored-by: zhengke.gzk <zhengke.gzk@antgroup.com>
 2025-07-02 16:25:30 +08:00
Andy b42f48edd6
feat(readme): add v0.8.0 Release Note (#618) 
* v0.8.0 Release Notes #andy

* v0.8.0 Release Notes #andy
 2025-06-30 15:08:03 +08:00
royzhao f8c98ab2ce
fix(solver): add rate limiter and llm retry (#617) 
* add host addr

* add rate limiter

* merge master

* fix pylink
 2025-06-30 13:11:47 +08:00
huaidong.xhd de77728058 format knext code with black 2025-06-27 19:31:06 +08:00
royzhao f0005e2c4e
fix(builder): add 0.8 config (#611) 
* change 0.8.0 config

* add open benchmark

* add open benchmark

* add open benchmark

* fix concept commit

* fix concept commit

* fix concept commit
 2025-06-27 19:08:30 +08:00
royzhao 8a9e927ea3
fix(builder): add 0.8 config (#610) 
* change 0.8.0 config

* add open benchmark

* add open benchmark

* add open benchmark

* fix concept commit

* fix concept commit
 2025-06-27 19:03:49 +08:00
锦呈 1c99bd4f3b update examples readme 2025-06-27 17:47:18 +08:00
锦呈 2e77f1e363 update examples readme 2025-06-27 17:44:51 +08:00
huaidong.xhd d9eb8eb025 fix kag and knext version in __init__.py 2025-06-27 17:13:58 +08:00
huaidong.xhd e3fda2026d fix registry import 2025-06-26 15:41:15 +08:00
huaidong.xhd 18ec3a76dc fix unused imports 2025-06-26 15:32:51 +08:00
huaidong.xhd 7ebd10e320 format code with black 2025-06-26 15:27:39 +08:00
huaidong.xhd fac165c43d update KAG_VERSION to 0.8.0 for release 2025-06-26 15:21:05 +08:00
peilong.zip f329354474 merge master 2025-06-26 15:17:17 +08:00
royzhao 62dc629bf8 fix(builder): use index manager to commit index schema (#608) 
* fix writer bug

* add index type from indexmanager

* rmove unused index.schema

* add index type from indexmanager

* remove llmrun
 2025-06-26 14:41:01 +08:00
Xinhong Zhang a6023ef55d update examples (#607) 2025-06-26 14:26:56 +08:00
wxy20152016 758ca4f4ef bugfix: 修复sourceChunk和relateTo名称不一致的问题 (#606) 
* bugfix: 修复sourceChunk和relateTo名称不一致的问题

* bugfix: 修复AtomicIndexManager在返回schema时，AtomicQuery不完全的问题

---------

Co-authored-by: wanxingyu.wxy <wanxingyu.wxy@antgroup.com>
 2025-06-26 11:46:23 +08:00
royzhao fef5045f14 fix writer bug (#605) 2025-06-26 11:31:34 +08:00
peilong.zip 1435665d53 fix main solver pipeline 2025-06-25 15:15:54 +08:00
peilong.zip 7a6eba36c9 fix main solver pipeline 2025-06-25 11:42:17 +08:00
peilong.zip b5b5f7a66d fix knowledge unit extractor 2025-06-24 20:56:50 +08:00
peilong.zip 8cd2e7d6a6 fix client project 2025-06-24 16:51:20 +08:00
peilong.zip 93108d4861 add retriever name property 2025-06-24 11:46:35 +08:00
peilong.zip 8fa6ddf1a0 use ttl cache 2025-06-24 10:21:48 +08:00
peilong.zip 594c49067f fix conflict 2025-06-23 18:03:50 +08:00
peilong.zip 0ee12b0802 modify hybrid index docs 2025-06-23 18:00:12 +08:00
锦呈 1152b7ac6e Merge branch '0.8.0_dev' of github.com:OpenSPG/KAG into 0.8.0_dev 2025-06-23 17:25:58 +08:00
锦呈 7f0aa81fd0 update 2025-06-23 17:25:43 +08:00
royzhao 2b4902a799 feat(solver): add kag model pipeline and modify prompt (#598) 
* add graph

* fix bug for None

* add knowledge unit extra

* fix_prompt

* extract common function into benchmark commponent

* format code

* format code

* format code

* fix benchmark knowledge unit

* fix node

* add common component

* Revert "remove local bge model and dependency scikit-learn"

This reverts commit d1c20fc6a8.

* remove unused pkg

* add decompose

* change hybrid default config

* add trace log

* fix some bugs

* with prompt

* support benchmark unit

* support kag thinker model

* support kag thinker model config

* remove default host addr and project id

* add kag model infer script

* add kag model infer script

* modify prompt for kag model
 2025-06-23 17:24:12 +08:00
peilong.zip c566d46a58 modify prompt for kag model 2025-06-23 17:03:31 +08:00
peilong.zip 779c470813 Merge branch '0.8.0_dev' of github.com:OpenSPG/KAG into configurable_index_mng_kag_config 2025-06-23 15:09:42 +08:00
royzhao 903da86838 feat(solver): add index type and modify knowledge unit solver yaml (#595) 
* add graph

* fix bug for None

* add knowledge unit extra

* fix_prompt

* extract common function into benchmark commponent

* format code

* format code

* format code

* fix benchmark knowledge unit

* fix node

* add common component

* Revert "remove local bge model and dependency scikit-learn"

This reverts commit d1c20fc6a8.

* remove unused pkg

* add decompose

* change hybrid default config

* add trace log

* fix some bugs

* with prompt

* support benchmark unit

* support kag thinker model

* support kag thinker model config

* remove default host addr and project id

* add kag model infer script

* add kag model infer script
 2025-06-23 15:09:24 +08:00
peilong.zip 151547cad6 Merge branch '0.8.0_dev' of github.com:OpenSPG/KAG into configurable_index_mng_kag_config 2025-06-23 15:08:08 +08:00
peilong.zip c7ce41a40f add kag model infer script 2025-06-23 15:07:23 +08:00
peilong.zip 5e05b978ef add kag model infer script 2025-06-23 15:03:22 +08:00
wanxingyu.wxy a7c6efa786 bugfix: 修复测试中table index的问题 2025-06-23 11:41:48 +08:00
peilong.zip f0baa0f731 remove default host addr and project id 2025-06-23 11:20:50 +08:00
peilong.zip ccfb6ee8e5 support kag thinker model config 2025-06-20 17:40:47 +08:00
peilong.zip 1bc3c0c694 support kag thinker model 2025-06-20 17:13:20 +08:00
peilong.zip c8336f428f Merge branch '0.8.0_dev' of github.com:OpenSPG/KAG into configurable_index_mng_kag_config 2025-06-20 15:42:47 +08:00
peilong.zip 6946f865f3 support benchmark unit 2025-06-20 15:42:21 +08:00
peilong.zip 5913915e66 with prompt 2025-06-19 21:36:02 +08:00
huaidong.xhd 51fd009a2b fix the kb-retrieve tool 2025-06-19 16:31:34 +08:00
xionghuaidong 4f078f2545 feat(mcp): implement mcp server for kag (#594) 
* fix ProjectCreateRequest param userNo name

* fix kag solver pipeline name

* add kag mcp server

* add readme for kag mcp server example

* update baike readme links

* format code and readme
 2025-06-19 16:27:13 +08:00
peilong.zip 271ab06305 Merge branch '0.8.0_dev' of github.com:OpenSPG/KAG into configurable_index_mng_kag_config 2025-06-19 14:01:46 +08:00
xionghuaidong fc98ad136e fix(kag): update examples to work under branch 0.8.0 (#593) 
* add graph

* fix bug for None

* add knowledge unit extra

* fix_prompt

* extract common function into benchmark commponent

* format code

* format code

* format code

* fix benchmark knowledge unit

* fix node

* add common component

* Revert "remove local bge model and dependency scikit-learn"

This reverts commit d1c20fc6a8.

* remove unused pkg

* add decompose

* change hybrid default config

* fix legacy commands in readme

* fix example csqa

* fix example baike

* fix example domain_kg

* fix example medicine

* fix example riskmining

* fix example supplychain

* fix example EastElectric

* fix example FinAlibaba

* update readme to use python 3.10

* fix readme format

* fix google_web_search_mcp

* fix example baidu_map_mcp

* format code with black

---------

Co-authored-by: peilong.zip <peilong.zpl@antgroup.com>
 2025-06-19 11:39:29 +08:00