67 Commits

Author SHA1 Message Date
binary-husky
dae180b9ea update spark v3.5, fix glm parallel problem 2024-02-18 14:08:35 +08:00
binary-husky
dd2a97e7a9 draw project struct with mermaid 2024-01-20 21:23:56 +08:00
Menghuan1918
aba871342f
修复分割函数中使用的变量错误 (#1443)
* Fix force_breakdown function parameter name

* Add handling for PDFs with lowercase starting paragraphs

* Change first lowercase word in meta_txt to uppercase
2024-01-03 19:49:17 +08:00
binary-husky
e3e9921f6b correct the misuse of spark image understanding 2023-12-23 17:46:25 +08:00
binary-husky
a0bfa7ba1c improve long text breakdown perfomance 2023-12-20 11:50:54 +08:00
binary-husky
ec60a85cac new vector store establishment 2023-12-05 00:15:17 +08:00
binary-husky
e533ed6d12 修正并行运行时的截断 2023-11-23 17:51:00 +08:00
qingxu fu
e5cd66a2f7 Merge branch 'frontier' of https://github.com/binary-husky/chatgpt_academic into frontier 2023-11-19 21:50:15 +08:00
binary-husky
27db900692 移除batchsize 2023-11-13 00:24:20 +08:00
binary-husky
c45336a3cd change nougat batchsize 2023-11-12 15:57:18 +08:00
binary-husky
f34f1091c3 fix nougat 2023-11-12 14:13:49 +08:00
xiangsam
33bf795c66 更新精准翻译PDF文档(NOUGAT)插件 2023-11-10 12:06:39 +00:00
binary-husky
527f9d28ad change get_conf 2023-10-29 00:34:40 +08:00
binary-husky
cf085565a7 rename folder 2023-10-28 17:44:17 +08:00
qingxu fu
a711db0b5b stashed commit 2023-10-25 11:32:32 +08:00
binary-husky
f925fe7692 添加对NOUGAT的代理设置 2023-10-20 10:43:04 +08:00
qingxu fu
4ad432e1da 新版HTML报告页面 2023-10-16 22:13:59 +08:00
binary-husky
5aea7b3d09 多线程运行微调 2023-10-15 19:13:25 +08:00
binary-husky
2d8f37baba 细分代理场景 2023-09-23 22:43:15 +08:00
binary-husky
3672c97a06 动态代码解释器 2023-09-23 01:51:05 +08:00
binary-husky
abea0d07ac 修复logging的Bug 2023-09-15 11:00:30 +08:00
binary-husky
567c6530d8 增加NOUGAT消息提示和错误操作提示 2023-09-14 21:38:47 +08:00
binary-husky
a1cc2f733c 修复nougat线程锁释放Bug 2023-09-14 15:26:03 +08:00
binary-husky
14de282302 给nougat加线程锁 合并冗余代码 2023-09-13 23:21:00 +08:00
qingxu fu
4b5f13bff2 修复知识库的依赖问题 2023-09-12 11:35:31 +08:00
binary-husky
28d777a96b 修正报错消息 2023-09-10 16:52:35 +08:00
qingxu fu
13c9606af7 修正下载PDF失败时产生的错误提示 2023-09-08 09:47:29 +08:00
binary-husky
5e0dc9b9ad 修复PDF下载路径时间戳的问题 2023-09-07 18:51:09 +08:00
qingxu fu
9c0bc48420 修复Azure OpenAI接口的各种bug 2023-07-07 10:42:38 +08:00
505030475
cb0bb6ab4a fix minor bugs 2023-06-21 00:41:33 +10:00
binary-husky
61b0e49fed fix some bugs in linux 2023-05-31 23:49:25 +08:00
505030475
3e4c2b056c knowledge base 2023-05-30 19:55:38 +08:00
505030475
6d1ea643e9 langchain 2023-05-30 12:54:42 +08:00
qingxu fu
e6f292c14b 修复最后一个完成的线程不更新状态的问题 2023-05-25 01:04:26 +08:00
binary-husky
6c17f3e9c8 添加历史存档读取的功能 2023-04-29 00:00:26 +08:00
binary-husky
73ce471a0e max_worker_limit 2023-04-24 19:24:19 +08:00
binary-husky
ab61418410 better traceback 2023-04-23 18:13:30 +08:00
Your Name
b0409b929b tiktoken做lazyload处理 2023-04-19 14:27:34 +08:00
505030475
abd11e5dff Merge branch 'master' into v3.1 2023-04-18 23:33:49 +08:00
binary-husky
0a5464d7d6
Update crazy_utils.py 2023-04-18 23:24:15 +08:00
Your Name
d35d7710c1 修复pdf分解bug 2023-04-18 16:14:30 +08:00
Your Name
05c74e66e7 多线程限制更正 2023-04-17 23:28:31 +08:00
Your Name
b5c4cd2f10 多线程超频错误 2023-04-17 23:21:12 +08:00
Your Name
2472185de9 unify tiktoken model 2023-04-17 19:41:50 +08:00
qingxu fu
8049296bee 上传 2023-04-15 21:08:44 +08:00
qingxu fu
6aba339538 ChatGLM改成多进程运行 2023-04-15 19:09:03 +08:00
qingxu fu
91609d6d39 Rebase v3.0 2023-04-15 15:24:18 +08:00
qingxu fu
cd6a1fd399 当无法正常切割PDF文档时,强制切割 2023-04-14 13:52:56 +08:00
qingxu fu
f10ea20351 延长遇到Rate limit reached时的等待时间 2023-04-14 13:15:42 +08:00
qingxu fu
2e044d97c7 更新提示 2023-04-14 13:10:40 +08:00