weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
723 Commits 1 Branch 0 Tags 72 MiB
Commit Graph

723 Commits

Author SHA1 Message Date
liunux4odoo 179c2a9a92 修改server.chat.openai_chat中的参数定义，使其与openai中/v1/chat/completions接口的入参保持一致，并按照model_config提供默认值。 
openai_chat中的接口还要修改：openai根据参数stream有不同的返回值，本接口要与其对应。
 2023-07-30 08:56:49 +08:00
liunux4odoo 1a7271e966 fix: model_worker need global variable: args 2023-07-29 23:22:25 +08:00
liunux4odoo c880412300 use multiprocessing to run fastchat server 2023-07-29 23:01:24 +08:00
liunux4odoo 829ced398b make api.py import model_config coreectlly 2023-07-29 23:00:50 +08:00
liunux4odoo 8b1cf7effd fix: os.environ['OPENAI_API_KEY'] exception when no environment variable set 2023-07-28 16:51:58 +08:00
liunux4odoo 70c6870776 增加api_one.py，把fastchat 
3个服务端整合在一起。后面考虑把api.py也整合进来。
3个进程变成1个进程可能带来少许性能损失，但对于个人用户降低了部署难度。
 2023-07-28 16:41:45 +08:00
hzg0601 97ee4686a1 更新会议记录 2023-07-28 16:16:59 +08:00
hzg0601 154cad1b45 会议记录 2023-07-28 16:12:57 +08:00
imClumsyPanda e95996a9b9 update requirements.txt 2023-07-28 06:59:16 +08:00
imClumsyPanda 59442dcd4a update webui.py 2023-07-28 06:58:34 +08:00
imClumsyPanda dd0f90b4a4 readd .github 2023-07-28 06:54:54 +08:00
imClumsyPanda 620ccb3bdc update model_config.py 2023-07-27 23:28:33 +08:00
imClumsyPanda dcf49a59ef v0.2.0 first commit 2023-07-27 23:22:07 +08:00
imClumsyPanda f7a32f9248
Update README.md 2023-07-27 09:23:31 +08:00
imClumsyPanda 36a1c72573
Add files via upload 2023-07-27 09:23:07 +08:00
imClumsyPanda 01a54d1042 add chatglm-fitness-RLHF made by @BoFan-tunning to llm_model_dict in model_config.py 2023-07-26 21:41:27 +08:00
imClumsyPanda 0a062ba07b update img 2023-07-26 21:37:22 +08:00
imClumsyPanda db80358df8
Update model_config.py 
fix openai api url
 2023-07-25 11:16:02 +08:00
imClumsyPanda 3f627af745
Update README.md 2023-07-24 08:32:21 +08:00
imClumsyPanda b586ee6e1f
Add files via upload 2023-07-24 08:31:54 +08:00
imClumsyPanda fdd353e48a Merge branch 'master' into dev 2023-07-23 18:40:04 +08:00
imClumsyPanda ff5d2ecc1e update img 2023-07-23 18:39:49 +08:00
imClumsyPanda 0f43845a98 merge master 2023-07-23 18:38:51 +08:00
hzg0601 1e1075b98a Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev 2023-07-21 23:13:11 +08:00
hzg0601 b2278f2f25 更改api.py的chat函数的history的类型为Optional,修复chat接口不可调用的问题 2023-07-21 23:12:28 +08:00
liunux4odoo a6f42e7c8e fix iss#889: 
when init_model on startup, set llm model's history_len to LLM_HISTORY_LEN from model_config.
 2023-07-21 23:07:50 +08:00
Ma Zhiming 3f76cb5f47
[Fix] INSTALL.md (#907) 
* Update INSTALL.md

* Update INSTALL.md
 2023-07-21 16:42:53 +08:00
hzg0601 3b6819f091 更改默认的LLM_MODEL 2023-07-21 15:35:17 +08:00
hzg0601 6ec1e56e03 Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev 2023-07-21 15:29:53 +08:00
Zhi-guo Huang acee2d5ad2
Merge pull request #905 from chinainfant/dev 
解决加载ptuning检查点失败的问题
 2023-07-21 15:32:37 +08:00
chinainfant c1c2ed1943
Update loader.py 解决加载ptuning报错的问题 2023-07-21 15:30:19 +08:00
hzg0601 32122ee225 update gitignore 2023-07-21 15:29:36 +08:00
chinainfant ec2bf9757c
Update args.py 将use-ptuning-v2的命名行改为action='store_true' 2023-07-21 15:28:11 +08:00
Zhi-guo Huang 7d37dc876e
Merge pull request #904 from bones-zhu/dev 
1 修复model_config.py的type;2 修改默认的LLM_model;3. 移除chatglm_llm.py的无用模块
 2023-07-21 15:14:33 +08:00
bones-zhu 5479a74789
Update chatglm_llm.py remove unused library 2023-07-21 15:11:51 +08:00
bones-zhu e2eaefc999
Update model_config.py 修改默认的LLM_MODEL 2023-07-21 15:10:13 +08:00
bones-zhu a1b454fc43
Update model_config.py fix type 2023-07-21 15:09:33 +08:00
hzg0601 5f4f8dcedc 解决loader.py中以名称匹配模型式未排除chatglm2的问题 2023-07-21 09:49:18 +08:00
hzg0601 a5294748a4 Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev 2023-07-21 09:32:19 +08:00
hzg0601 915f4f359a 补充openai的连接失败问题解决方案 2023-07-21 09:29:43 +08:00
imClumsyPanda bf940e9041
Update README.md 2023-07-20 15:06:02 +08:00
imClumsyPanda 2db6604c55
Add files via upload 2023-07-20 15:04:12 +08:00
liunux@home dd3617fcdf 将paddle相关loader改为动态引入，可以在不上传pdf/image知识文件的前提下使用protobuf=4.x。 
这样可以使用最新版streamlit和chainlit。
 2023-07-20 12:32:37 +08:00
Zhi-guo Huang ee7285cd93
在args.py中增加ptuning相关的参数 (#838) 
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项

* 更新FAQ，增加了[Errno 110] Connection timed out的原因与解决方案

* 修改loader.py中load_in_8bit失败的原因和详细解决方案

* update loader.py

* stream_chat_bing

* 修改stream_chat的接口，在请求体中选择knowledge_base_id;增加stream_chat_bing接口

* 优化cli_demo.py的逻辑：支持 输入提示；多输入；重新输入

* update cli_demo.py

* 按照review建议进行修改

* 修改默认的多卡部署方案，基本保证针对新模型也不会失败

* 测试openai接口成功

* add ptuning-v2 dir

* 支持命令行输入ptuning路径

* 在FAQ中给出加载量化版本失败的原因和解决方案

* print error

* udpate

* Update args.py

* debug for fastchat_openai_llm

* temporarily save

* update faq for

---------

Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Co-authored-by: zg h <bj wang@hzg0601-acer.hundsun.com>
 2023-07-19 23:15:14 +08:00
hzg0601 50c872c0b8 update faq for 2023-07-19 23:09:19 +08:00
hzg0601 c501df2405 temporarily save 2023-07-19 10:57:09 +08:00
hzg0601 6199c45a13 Merge branch 'dev' of github.com:hzg0601/langchain-ChatGLM-annotation into dev 
git pull origin dev.
 2023-07-19 10:04:05 +08:00
hzg0601 391dc1d33a debug for fastchat-openai-llm 2023-07-19 10:02:39 +08:00
hzg0601 90fe40b221 debug for fastchat_openai_llm 2023-07-19 10:00:23 +08:00
liunux4odoo f88bf2cbf3
fix issue#580: 新建知识库出错 (#880) 
* Add files via upload

* Update README.md

* fix: make get_vs_list return folders only

* fix: bugs when create new knowledgebase

---------

Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
 2023-07-18 23:40:18 +08:00