RYDE-WORK/Langchain-Chatchat
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/Langchain-Chatchat.git synced 2026-02-09 00:25:46 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 3318cef751 update streamlit ui: support latest knowledge base and search engine chat api; export messages to markdown. liunux4odoo 2023-08-04 12:52:58 +08:00
  • 27d49be706 make apirequest support streaming dict liunux4odoo 2023-08-04 12:49:39 +08:00
  • c4994e85df fix: knowledge_base_chat and search_engine_chat should stream json text instead of dict. client should use json.loads. liunux4odoo 2023-08-04 12:12:13 +08:00
  • 88682c87ff 优化server下知识库相关模块的结构：将知识库相关操作从knowledge_base_chat移动到knowledge_base.utils；优化kb_doc_api中embeddings加载。 liunux4odoo 2023-08-04 10:16:30 +08:00
  • 9a18218293 add new config variable to config example liunux4odoo 2023-08-04 09:16:28 +08:00
  • 82aa805bf3 update requirements.txt imClumsyPanda 2023-08-03 23:42:55 +08:00
  • 329c24ee73 1. change bing_search_chat and duckduckgo_search_chat into search_engine_chat 2. add knowledge_base not found to knowledge_base_chat and add search_engine not found to search_engine_chat imClumsyPanda 2023-08-03 18:22:36 +08:00
  • b62ea6bd2a add top-k to search_chat apis and add top-k params in model_config imClumsyPanda 2023-08-03 17:06:43 +08:00
  • 5c804aac75 make api and webui support top_k paramter liunux4odoo 2023-08-03 15:47:53 +08:00
  • df61f31c8e 修改knowledge_base_chat实现:利用缓存避免每次请求重新加载向量库；增加top_k参数。 liunux4odoo 2023-08-03 15:22:46 +08:00
  • e1698ce12e webui中增加多会话功能 liunux4odoo 2023-08-03 15:06:10 +08:00
  • fdbff8a91f Merge branch 'dev_fastchat' of github.com:chatchat-space/langchain-ChatGLM into dev_fastchat hzg0601 2023-08-03 14:39:14 +08:00
  • 6f93a27e53 更新llm_api_sh.py调用说明 hzg0601 2023-08-03 14:39:00 +08:00
  • 4651b50176 WEB UI中对话功能已完成。目前很多参数还不支持，待API接口完善后再加入。 liunux4odoo 2023-08-03 13:41:31 +08:00
  • dc74bdab41 将httpx.stream返回结果转化为普通生成器，使得httpx api请求与直接调用server.chat.xx返回相同的结果。 liunux4odoo 2023-08-03 12:52:49 +08:00
  • f7d465b7d4 bug fix liunux4odoo 2023-08-03 12:11:18 +08:00
  • 3c2b8a85d6 add knowledge base api methods liunux4odoo 2023-08-03 10:49:57 +08:00
  • d36d801a58 add api request methods for all chat apis liunux4odoo 2023-08-03 09:33:24 +08:00
  • 904eaa58c4
         Update README.md imClumsyPanda 2023-08-02 11:01:02 +08:00
  • 6b03914446
         Add files via upload imClumsyPanda 2023-08-02 11:00:38 +08:00
  • d0fd6253a3 update llm_api_sh hzg0601 2023-08-02 09:19:58 +08:00
  • 1d1a8e9339 Merge branch 'dev_fastchat' of github.com:chatchat-space/langchain-ChatGLM into dev_fastchat hzg0601 2023-08-01 22:07:12 +08:00
  • ab7a76f380 update llm_api_sh.py and model_config.example hzg0601 2023-08-01 22:07:05 +08:00
  • e4fed93989 update format in api.py imClumsyPanda 2023-08-01 21:53:19 +08:00
  • 18a94fcf45 Merge branch 'dev_fastchat' of github.com:chatchat-space/langchain-ChatGLM into dev_fastchat hzg0601 2023-08-01 18:02:52 +08:00
  • 15e67a4d3e 1.*在config里将所有fastchat的命令行参数加入;2.*加入启动和停止fastchat的shell脚本；3. **增加了通过命令行启动所有fastchat服务的python脚本llm_api_sh.py;4. 修改了默认的config日志格式 hzg0601 2023-08-01 17:59:20 +08:00
  • 7c01a2a253 add bing_search_chat.py and duckduckgo_search_chat.py imClumsyPanda 2023-08-01 16:39:17 +08:00
  • 5ce2484af0 update webui.py imClumsyPanda 2023-08-01 15:08:19 +08:00
  • 7d79b676d5 add model_config.py.example instead of model_config.py imClumsyPanda 2023-08-01 14:55:00 +08:00
  • 8261deb99d fix model_config path imClumsyPanda 2023-08-01 14:49:49 +08:00
  • bcfd3f5af5 add webui_pages imClumsyPanda 2023-08-01 14:47:38 +08:00
  • c8a75ab11f update llm_api.py and webui.py imClumsyPanda 2023-08-01 14:33:18 +08:00
  • 2c5b6bb0ad streamlit ui 实现LLM流式对话 liunux4odoo 2023-08-01 14:18:30 +08:00
  • a1a7484ef4 增加webui_utils.py，包括制作webui通用的工具，方便以后开发其他webui liunux4odoo 2023-08-01 14:15:42 +08:00
  • 9f4567865c add chatglm2-6b-32k and make m3e default embedding model imClumsyPanda 2023-08-01 14:12:28 +08:00
  • 00cb7bf598 add support for chatglm2-6b-32k imClumsyPanda 2023-08-01 10:58:05 +08:00
  • dfe7bee243 Merge branch 'master' into dev imClumsyPanda 2023-07-31 19:54:43 +08:00
  • 9e2b411b01 cuda error with multiprocessing, change model_worker to main process liunux4odoo 2023-07-31 11:18:57 +08:00
  • 47dfb6cd8b udpate llm_api hzg0601 2023-07-31 11:00:33 +08:00
  • 946f10e1f2 split api_start to create_app & run_api. user can run api with uvicorn in console: uvicorn server.api:app --port 7861 liunux4odoo 2023-07-31 10:05:19 +08:00
  • 463659f0ba llm_api升级到fschat==0.2.20，支持百川模型 liunux4odoo 2023-07-30 23:16:47 +08:00
  • 51ea717606 Merge branch 'dev_fastchat_me' into dev_fastchat liunux4odoo 2023-07-30 09:01:31 +08:00
  • 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。 liunux4odoo 2023-07-30 08:56:49 +08:00
  • 05ccc0346e update test code imClumsyPanda 2023-07-30 00:48:07 +08:00
  • 41444fd4b5 update requirements.txt and llm_api.py imClumsyPanda 2023-07-30 00:24:34 +08:00
  • d4ffc70d96 update requirements.txt imClumsyPanda 2023-07-29 23:46:02 +08:00
  • 1a7271e966 fix: model_worker need global variable: args liunux4odoo 2023-07-29 23:22:25 +08:00
  • c880412300 use multiprocessing to run fastchat server liunux4odoo 2023-07-29 23:01:24 +08:00
  • 829ced398b make api.py import model_config coreectlly liunux4odoo 2023-07-29 23:00:50 +08:00
  • fef931d2b8
         Merge pull request #859 from cylee0909/chatglm2cpp Zhi-guo Huang 2023-07-28 22:24:51 +08:00
  • 8b1cf7effd fix: os.environ['OPENAI_API_KEY'] exception when no environment variable set liunux4odoo 2023-07-28 16:51:58 +08:00
  • 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。 liunux4odoo 2023-07-28 16:33:42 +08:00
  • 97ee4686a1 更新会议记录 hzg0601 2023-07-28 16:16:59 +08:00
  • 154cad1b45 会议记录 hzg0601 2023-07-28 16:12:57 +08:00
  • 4235270a32
         Merge branch 'dev' into chatglm2cpp cylee 2023-07-28 14:41:14 +08:00
  • e95996a9b9 update requirements.txt imClumsyPanda 2023-07-28 06:59:16 +08:00
  • 59442dcd4a update webui.py imClumsyPanda 2023-07-28 06:58:34 +08:00
  • dd0f90b4a4 readd .github imClumsyPanda 2023-07-28 06:54:54 +08:00
  • 161c9e6c50 fix typo hzg0601 2023-07-28 03:59:29 +08:00
  • 620ccb3bdc update model_config.py imClumsyPanda 2023-07-27 23:28:33 +08:00
  • 9326c63a62 Merge branch 'dev' of https://github.com/imClumsyPanda/langchain-ChatGLM into dev hzg0601 2023-07-27 23:27:53 +08:00
  • dcf49a59ef v0.2.0 first commit imClumsyPanda 2023-07-27 23:22:07 +08:00
  • cd91290bfb 删除reqirements的中文 hzg0601 2023-07-27 14:28:58 +08:00
  • c431bee941 删除requirements的中文 hzg0601 2023-07-27 14:27:11 +08:00
  • 310a865ccd 删除requirements的中文 hzg0601 2023-07-27 14:26:50 +08:00
  • f7a32f9248
         Update README.md imClumsyPanda 2023-07-27 09:23:31 +08:00
  • 36a1c72573
         Add files via upload imClumsyPanda 2023-07-27 09:23:07 +08:00
  • 8732dcc1c4 恢复被PR659覆盖的model_config liunux4odoo 2023-07-27 08:42:17 +08:00
  • 01a54d1042 add chatglm-fitness-RLHF made by @BoFan-tunning to llm_model_dict in model_config.py imClumsyPanda 2023-07-26 21:41:27 +08:00
  • 0a062ba07b update img imClumsyPanda 2023-07-26 21:37:22 +08:00
  • 34a2af118b update model_config.py hzg0601 2023-07-26 18:04:35 +08:00
  • e8ff31be1f 1.使api.py里可以使用args.py的参数;2.兼容args.py和model_config.py的控制方式;3.更新fastchat调用模型名的说明 hzg0601 2023-07-26 17:46:02 +08:00
  • 58a5de92a5 1.更改加载lora的方式;2.允许api.py调用args.py的命令行;3. FastChat路径提示 hzg0601 2023-07-26 17:05:37 +08:00
  • 5f74f70515 fix: streamlit ui在上传多个文件到知识库时出错 liunux4odoo 2023-07-25 22:36:49 +08:00
  • 466f0c9c97
         安装教程conda create新增默认的/envs下面，而不只是只能要额外指定路径 用-p (#482) YuhaoWU 2023-07-25 16:58:25 +08:00
  • 18d453cc18 merge PR 659: make chat api support streaming liunux4odoo 2023-07-25 13:16:43 +08:00
  • db80358df8
         Update model_config.py imClumsyPanda 2023-07-25 11:16:02 +08:00
  • f21fea41b4 bug fix: api.py中,所有chat接口的参数history,其元素应支持None，方便其他框架调用。 否则以history=[[None,'some thing']]调用时会返回422错误。 liunux4odoo 2023-07-25 08:53:28 +08:00
  • 1f8924eeac
         Merge branch 'dev' into chatglm2cpp Zhi-guo Huang 2023-07-24 14:44:00 +08:00
  • 62ba7679fe support chatglm2cpp lichongyang 2023-07-16 17:24:46 +08:00
  • 3f627af745
         Update README.md imClumsyPanda 2023-07-24 08:32:21 +08:00
  • b586ee6e1f
         Add files via upload imClumsyPanda 2023-07-24 08:31:54 +08:00
  • fdd353e48a Merge branch 'master' into dev imClumsyPanda 2023-07-23 18:40:04 +08:00
  • ff5d2ecc1e update img imClumsyPanda 2023-07-23 18:39:49 +08:00
  • 0f43845a98 merge master imClumsyPanda 2023-07-23 18:38:51 +08:00
  • 1e1075b98a Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev hzg0601 2023-07-21 23:13:11 +08:00
  • 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 hzg0601 2023-07-21 23:12:28 +08:00
  • a6f42e7c8e fix iss#889: when init_model on startup, set llm model's history_len to LLM_HISTORY_LEN from model_config. liunux4odoo 2023-07-21 23:07:50 +08:00
  • 3f76cb5f47
         [Fix] INSTALL.md (#907) Ma Zhiming 2023-07-21 16:42:53 +08:00
  • 3b6819f091 更改默认的LLM_MODEL hzg0601 2023-07-21 15:35:17 +08:00
  • 6ec1e56e03 Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev hzg0601 2023-07-21 15:29:53 +08:00
  • acee2d5ad2
         Merge pull request #905 from chinainfant/dev Zhi-guo Huang 2023-07-21 15:32:37 +08:00
  • c1c2ed1943
         Update loader.py 解决加载ptuning报错的问题 chinainfant 2023-07-21 15:30:19 +08:00
  • 32122ee225 update gitignore hzg0601 2023-07-21 15:29:36 +08:00
  • ec2bf9757c
         Update args.py 将use-ptuning-v2的命名行改为action='store_true' chinainfant 2023-07-21 15:28:11 +08:00
  • 7d37dc876e
         Merge pull request #904 from bones-zhu/dev Zhi-guo Huang 2023-07-21 15:14:33 +08:00
  • 5479a74789
         Update chatglm_llm.py remove unused library bones-zhu 2023-07-21 15:11:51 +08:00
  • e2eaefc999
         Update model_config.py 修改默认的LLM_MODEL bones-zhu 2023-07-21 15:10:13 +08:00
  • a1b454fc43
         Update model_config.py fix type bones-zhu 2023-07-21 15:09:33 +08:00
  • 5f4f8dcedc 解决loader.py中以名称匹配模型式未排除chatglm2的问题 hzg0601 2023-07-21 09:49:18 +08:00