LarFii
290744d770
fix requirements.txt
2025-01-07 16:04:46 +08:00
童石渊
3bbd3ee1b2
在Mac端torch~=2.5.1+cu121会导致本地安装时报错
2025-01-07 13:45:18 +08:00
Samuel Chan
196350b75b
Revise the readme to fix the broken link.
2025-01-07 07:02:37 +08:00
童石渊
9662ecc102
Merge remote-tracking branch 'origin'
...
添加字符分割功能，在“insert”函数中如果增加参数split_by_character，则会按照split_by_character进行字符分割，此时如果每个分割后的chunk的tokens大于max_token_size，则会继续按token_size分割（todo：考虑字符分割后过短的chunk处理）
2025-01-07 00:43:00 +08:00
童石渊
536d6f2283
添加字符分割功能，在“insert”函数中如果增加参数split_by_character，则会按照split_by_character进行字符分割，此时如果每个分割后的chunk的tokens大于max_token_size，则会继续按token_size分割（todo：考虑字符分割后过短的chunk处理）
2025-01-07 00:28:15 +08:00
✨Data Intelligence Lab@HKU✨
22e9f1cd89
Update README.md
2025-01-06 23:21:02 +08:00
✨Data Intelligence Lab@HKU✨
e415f88bd4
Update README.md
2025-01-06 23:20:26 +08:00
xYLiuuuuuu
79646fced8
Fix:Optimized logic for automatic switching modes when keywords do not exist
2025-01-06 16:54:53 +08:00
zrguo
39a366a3dc
Update __init__.py
2025-01-06 15:43:05 +08:00
zrguo
916380e511
Update README.md
2025-01-06 15:39:44 +08:00
zrguo
e2a4819af9
Update README.md
2025-01-06 15:37:37 +08:00
zrguo
c88bb4fd53
Update LICENSE
2025-01-06 15:34:50 +08:00
zrguo
990b684a85
Update lightrag.py
2025-01-06 15:27:31 +08:00
zrguo
12f4a45440
Merge pull request #545 from ShanGor/main
...
Enhance the llm_cache_kv_store, enable the llm_cache for entity extraction and revise readme
2025-01-06 15:24:34 +08:00
Samuel Chan
85d35b16d4
Merge branch 'HKUDS:main' into main
2025-01-06 12:53:06 +08:00
Samuel Chan
6ae27d8f06
Some enhancements:
...
- Enable the llm_cache storage to support get_by_mode_and_id, to improve the performance for using real KV server
- Provide an option for the developers to cache the LLM response when extracting entities for a document. Solving the paint point that sometimes the process failed, the processed chunks we need to call LLM again, money and time wasted. With the new option (by default not enabled) enabling, we can cache that result, can significantly save the time and money for beginners.
2025-01-06 12:50:05 +08:00
zrguo
6d7a01f29d
Merge pull request #542 from xiyihan0/main
...
添加选取Neo4j指定数据库功能的支持
2025-01-05 12:46:45 +08:00
xiyihan
1e3b25db22
添加选取Neo4j指定数据库功能的支持(fix lint)
2025-01-04 22:33:35 +08:00
zrguo
6b5f4755e7
Merge pull request #539 from ShanGor/main
...
Added PostgreSQL implementation
2025-01-04 22:13:06 +08:00
xiyihan
bb4c271623
添加选取Neo4j指定数据库功能的支持
2025-01-04 21:47:52 +08:00
Samuel Chan
6c1b669f0f
Fix the lint issue
2025-01-04 18:49:32 +08:00
Samuel Chan
11f889a9df
Merge remote-tracking branch 'origin/main'
2025-01-04 18:35:39 +08:00
Samuel Chan
e053223ef0
Fix the lint issue
2025-01-04 18:34:35 +08:00
Samuel Chan
733d329aba
Merge branch 'HKUDS:main' into main
2025-01-04 18:34:24 +08:00
zrguo
fb414582c7
Merge pull request #541 from ParisNeo/main
...
Add Optional API Key Authentication to FastAPI Services
2025-01-04 13:58:43 +08:00
Saifeddine ALOUI
b15c398889
applyed linting
2025-01-04 02:23:39 +01:00
Saifeddine ALOUI
518a8a726a
Added servers protection using an API key to restrict access to only authenticated entities.
2025-01-04 02:21:37 +01:00
Samuel Chan
db663114a9
Remove unused import
2025-01-03 21:20:47 +08:00
Samuel Chan
60e8a355f0
Merge branch 'HKUDS:main' into main
2025-01-03 21:18:17 +08:00
Samuel Chan
ebe5fe1676
Merge remote-tracking branch 'origin/main'
2025-01-03 21:14:22 +08:00
Samuel Chan
f6f62c32a8
Fix the bug of AGE processing
2025-01-03 21:10:06 +08:00
zrguo
f52982d5cf
Merge pull request #533 from JasonnnW3000/main
...
Update LICENSE, fix copyright license year
2025-01-01 22:53:45 +08:00
Samuel Chan
b17cb2aa95
With a draft for progres_impl
2025-01-01 22:43:59 +08:00
JasonnnW3000
7e7230a6e3
Update LICENSE, fix license year
...
Signed-off-by: JasonnnW3000 <sufssl04@gmail.com >
2025-01-01 00:20:46 -05:00
zrguo
bb2ea3db6a
Merge pull request #532 from HKUDS/dev
...
Dev
2024-12-31 17:34:00 +08:00
zrguo
d489d9dec0
fix linting errors
2024-12-31 17:32:04 +08:00
zrguo
71e9267f4b
Update README.md
2024-12-31 17:25:57 +08:00
zrguo
cee5b2fbb0
add delete by doc id
2024-12-31 17:15:57 +08:00
zrguo
c0eef702ee
Merge pull request #527 from ChenZiHong-Gavin/retry-config
...
fix: change exception type
2024-12-31 02:46:12 +08:00
chenzihong
648645ef45
fix: fix formatting issues
2024-12-31 01:33:14 +08:00
chenzihong
97bc42d896
Merge branch 'main' of https://github.com/ChenZiHong-Gavin/LightRAG into retry-config
2024-12-31 01:22:55 +08:00
zrguo
af893a1951
Merge pull request #529 from magicyuan876/main
...
修复断点续传bug，过滤已经存在的文档是只过滤状态是已经处理完成的
2024-12-31 00:46:27 +08:00
Magic_yuan
7271ac69b7
修复断点续传bug，过滤已经存在的文档是只过滤状态是已经处理完成的
2024-12-30 20:32:10 +08:00
chenzihong
eb1fc0dae7
fix: change exception type
2024-12-30 01:46:15 +08:00
zrguo
889d056a6f
Merge pull request #525 from magicyuan876/main
...
feat: 增强知识图谱关系的时序性支持
2024-12-29 20:13:26 +08:00
Magic_yuan
b84c4d1fca
Merge branch 'HKUDS:main' into main
2024-12-29 15:45:34 +08:00
Magic_yuan
7b91dc7fd8
feat: 增强知识图谱关系的时序性支持
...
- 为关系和向量数据增加时间戳支持,记录知识获取的时间
- 优化混合查询策略,同时考虑语义相关性和时间顺序
- 增强提示词模板,指导LLM在处理冲突信息时考虑时间因素
2024-12-29 15:37:34 +08:00
Magic_yuan
4c950cf4ce
feat: 增强知识图谱关系的时序性支持
...
- 为关系和向量数据增加时间戳支持,记录知识获取的时间
- 优化混合查询策略,同时考虑语义相关性和时间顺序
- 增强提示词模板,指导LLM在处理冲突信息时考虑时间因素
2024-12-29 15:25:57 +08:00
zrguo
4ddf87ffd4
Merge pull request #524 from magicyuan876/main
...
优化mix查询模式的提示词
2024-12-29 10:00:31 +08:00
Magic_yuan
b8b371f65a
Merge branch 'HKUDS:main' into main
2024-12-29 00:35:19 +08:00
