weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,528 Commits 1 Branch 0 Tags 72 MiB
Commit Graph

220 Commits

Author SHA1 Message Date
hzg0601 2d823aa4b1 1. debug vllm加速框架完毕；2. 修改requirements,requirements_api对vllm的依赖；3.注释掉serve_config中baichuan-7b的device为cpu的配置 2023-09-24 02:05:40 +08:00
hzg0601 810145c5fb 新增特性：1.支持vllm推理加速框架；2. 更新支持模型列表 2023-09-23 01:37:37 +08:00
hzg0601 89aed8e675 update readme_en,readme,requirements_api,requirements,model_config.py.example:测试baichuan2-7b;更新相关文档 2023-09-22 14:30:28 +08:00
Leego 9bcce0a572
【功能新增】在线 LLM 模型支持阿里云通义千问 (#1534) 
* feat: add qwen-api

* 使Qwen API支持temperature参数；添加测试用例

* 将online-api的sdk列为可选依赖

---------

Co-authored-by: liunux4odoo <liunux@qq.com>
 2023-09-20 21:34:12 +08:00
glide-the 7d31e84cc7 langchain日志开关 2023-09-17 14:18:22 +08:00
liunux4odoo a65bc4a63c
添加configs/prompt_config.py，允许用户自定义prompt模板： (#1504) 
1、 默认包含2个模板，分别用于LLM对话，知识库和搜索引擎对话
2、 server/utils.py提供函数get_prompt_template，获取指定的prompt模板内容（支持热加载）
3、 api.py中chat/knowledge_base_chat/search_engine_chat接口支持prompt_name参数
 2023-09-17 13:27:11 +08:00
liunux4odoo 745a105bae feat: support volc fangzhou 2023-09-16 22:21:16 +08:00
liunux4odoo 42d76aabdf
Update model_config.py.example: wrong provider for qianfan-api (#1499) 2023-09-16 11:19:22 +08:00
liunux4odoo 3dde02be28
优化LLM模型列表获取、切换的逻辑： (#1497) 
1、更准确的获取未运行的可用模型
2、优化WEBUI模型列表显示与切换的控制逻辑
 2023-09-16 07:15:08 +08:00
liunux4odoo 955b0bc211
修复ChatGPT api_base_url错误；用户可以在model_config在线模型配置中覆盖默认的api_base_url (#1496) 2023-09-15 22:56:13 +08:00
liunux4odoo 80375e1ff3
fix merge conflict for #1474 (#1494) 2023-09-15 18:11:15 +08:00
liunux4odoo f7c73b842a
优化configs (#1474) 
* remove llm_model_dict

* optimize configs

* fix get_model_path

* 更改一些默认参数，添加千帆的默认配置

* Update server_config.py.example
 2023-09-15 17:52:22 +08:00
imClumsyPanda a87a2815da update knowledge_base and dialogue page of webui 2023-09-15 13:45:47 +08:00
imClumsyPanda 20eef45a58 update README.md 2023-09-15 09:53:58 +08:00
liunux4odoo 30aeec1c45
修改智谱API默认名称，给WEBUI设置主题 (#1484) 
* 給WEBUI设置主题

* chatglm-api更名为zhipu-api
 2023-09-15 01:48:02 +08:00
liunux4odoo f0f1dc2537 补充更多千帆平台支持的模型；除了指定模型名称，支持直接指定模型APIURL，便于填写单独申请的模型地址 2023-09-15 00:30:18 +08:00
liunux4odoo 4cf2e5ea5e 修复文心一言，添加测试用例 2023-09-14 23:37:34 +08:00
imClumsyPanda 1813814a65 update model_config.py.example 2023-09-14 22:29:49 +08:00
imClumsyPanda 4c61a642cf update model_config.py.example 2023-09-14 22:29:26 +08:00
imClumsyPanda bda1b01a2d update model_config.py.example 2023-09-14 22:27:57 +08:00
imClumsyPanda 883445e5b2
增加 百度文心一言 API 接入支持 (#1477) 
* add RapidOCRPDFLoader

* update mypdfloader.py and requirements.txt

* add myimgloader.py

* add test samples

* add TODO to mypdfloader

* add loaders to KnowledgeFile class

* add loaders to KnowledgeFile class

* add ChineseRecursiveTextSplitter

* add ChineseRecursiveTextSplitter

* add baidu ernie api
 2023-09-14 15:30:06 +08:00
唐国梁 4c5fc6ab01 edit model_config.py.example 2023-09-14 12:38:37 +08:00
zR 769d75d784
修复测试文件 (#1467) 
Co-authored-by: zR <zRzRzRzRzRzRzR>
 2023-09-13 17:12:05 +08:00
zR bfdbe69fa1
增加了自定义分词器适配 (#1462) 
* 添加了自定义分词器适配和测试文件
---------

Co-authored-by: zR <zRzRzRzRzRzRzR>
 2023-09-13 15:42:12 +08:00
liunux4odoo 512638a3b1
支持讯飞星火大模型在线API (#1460) 
* 支持讯飞星火大模型在线API
 2023-09-13 13:51:05 +08:00
liunux4odoo 16d8809c9a
api和webui知识库操作支持chunk_size/overlap_size/zh_title_enhance参数 (#1459) 2023-09-13 11:19:47 +08:00
liunux4odoo a03b8d330d
升级到langchain==0.0.287,fschat==0.0.28;处理langchain.Milvus bug(#10492) (#1454) 
* 修复milvus_kb_service中一些bug，添加文档后将数据同步到数据库
* 升级到langchain==0.0.287,fschat==0.0.28;处理langchain.Milvus bug(#10492)
* 修复切换模型BUG: 从在线API切换模型时出错
 2023-09-13 08:43:11 +08:00
liunux4odoo 03c021d50f
添加MiniMax在线API支持 (#1445) 2023-09-12 15:24:47 +08:00
glide-the 5550e3c1a9 增加显示详细日志开关 2023-09-08 20:48:31 +08:00
imClumsyPanda 6ea4fc7a30 Merge branch 'master' into dev 2023-09-06 21:19:59 +08:00
imClumsyPanda 54cf79f521 add support for new embedding models sensenova/piccolo-base-zh and sensenova/piccolo-large-zh 2023-09-06 21:17:32 +08:00
imClumsyPanda 74cca5eb0e add support for shibing624/text2vec-bge-large-chinese 2023-09-05 18:19:13 +08:00
imClumsyPanda 780c1457d0 add support for shibing624/text2vec-bge-large-chinese 2023-09-05 18:04:21 +08:00
glide-the 0b60a25f2a 知识库默认存储路径 默认自动创建 2023-09-05 17:27:43 +08:00
imClumsyPanda 8ea75417ec update VERSION 2023-09-05 10:20:59 +08:00
imClumsyPanda d1b4dea2ca update VERSION 2023-09-05 10:19:14 +08:00
imClumsyPanda 15619a1270 update model_config.py.example 2023-09-05 08:59:06 +08:00
imClumsyPanda 9855bc6f55 update model_config.py.example 2023-09-03 15:52:17 +08:00
imClumsyPanda 3391155077 update model_config.py.example 2023-09-02 15:33:57 +08:00
liunux4odoo 6cb1bdf623
添加切换模型功能，支持智谱AI在线模型 (#1342) 
* 添加LLM模型切换功能，需要在server_config中设置可切换的模型
* add tests for api.py/llm_model/*
* - 支持模型切换
- 支持智普AI线上模型
- startup.py增加参数`--api-worker`，自动运行所有的线上API模型。使用`-a
  (--all-webui), --all-api`时默认开启该选项
* 修复被fastchat覆盖的标准输出
* 对fastchat日志进行更细致的控制，startup.py中增加-q(--quiet)开关，可以减少无用的fastchat日志输出
* 修正chatglm api的对话模板


Co-authored-by: liunux4odoo <liunu@qq.com>
 2023-09-01 23:58:09 +08:00
zqt ab4c8d2e5d Merge remote-tracking branch 'origin/dev' into dev 2023-09-01 18:10:32 +08:00
zqt 9b664d5eb2 添加例子例子"openai_proxy": 'http://127.0.0.1:4780' 2023-09-01 18:09:59 +08:00
liunux4odoo b1201a5f23
优化LLM和Embedding模型运行设备配置，可设为auto自动检测；修复：重建知识库时FAISS未保存 (#1330) 
* 避免configs对torch的依赖；
* webui自动从configs获取api地址(close #1319)
* bug fix: 重建知识库时FAISS未保存
* 优化LLM和Embedding模型运行设备配置，可设为auto自动检测
 2023-08-31 17:44:48 +08:00
liunux4odoo 26a9237237
避免configs对torch的依赖；webui自动从configs获取api地址(close #1319) (#1328) 2023-08-31 16:18:12 +08:00
liunux4odoo 34a416b941
优化server_config配置项 (#1293) 
* update server_config.py:
- 在model_config中增加HISTORY_LEN配置参数
- 将server_config中helper function移动到server.utils中
- 统一set_httpx_timeout的定义和调用

* update webui.py:
应用model_config中的配置项：HISTORY_LEN,VECTOR_SEARCH_TOP_K,SEARCH_ENGINE_TOP_K

---------

Co-authored-by: liunux4odoo <liunu@qq.com>
 2023-08-29 10:06:09 +08:00
liunux4odoo 6ef8844b2b
修复使用chatgpt等在线API服务时模型加载错误 (#1271) 
* close #1172: 给webui_page/utils添加一些log信息，方便定位错误

* 修复：重建知识库时页面未实时显示进度

* skip model_worker running when using online model api such as chatgpt

---------

Co-authored-by: liunux4odoo <liunu@qq.com>
 2023-08-27 16:46:59 +08:00
imClumsyPanda fea7e8ddf1 update VERSION 2023-08-26 11:10:45 +08:00
imClumsyPanda 79d225be36 update VERSION 2023-08-25 16:26:51 +08:00
hzg0601 cc0bd4efd9 update server_config.py.example: 增加多卡启动的说明 2023-08-25 11:27:39 +08:00
zqt ea4b5ebd16 Merge branch 'master' into dev 2023-08-24 14:16:21 +08:00
zqt 37454db3ec 添加chatgpt 调用代理设置 2023-08-24 13:51:17 +08:00
imClumsyPanda 3504cb5274 update model_config.py.example 2023-08-23 23:04:13 +08:00
zR 7291e77978
support for bge-large-zh-noinstruct and openai text-embedding-ada-002 (#1119) 
* support for bge-large-zh-noinstruct and openai text-embedding-ada-002

* 完善了readme,修改了BGE模型的载入方式

* 补充了readme中bge-large-zh-noinstruct的信息

* Update faiss_kb_service.py

* Update utils.py

---------

Co-authored-by: zR <zRzRzRzRzRzRzR>
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
 2023-08-23 22:55:53 +08:00
imClumsyPanda 4bcc74d214 update prompt template 2023-08-23 21:52:12 +08:00
liunux4odoo 44edce6bcf fix #1142: 在History中使用jinja2模板代替f-string，避免消息中含有{ }时出错 2023-08-23 08:35:26 +08:00
zqt996 cb29e1ed23
Merge pull request #1198 from chatchat-space/dev 
pg similarity_search 转 similarity_search_with_score
 2023-08-22 16:41:37 +08:00
zqt b3450bfc96 添加milvus 和 pg QA说明 2023-08-20 18:03:23 +08:00
imClumsyPanda d694652b87 update VERSION 2023-08-20 10:40:31 +08:00
imClumsyPanda adb102f5f0 update VERSION 2023-08-17 22:32:42 +08:00
imClumsyPanda 52837429d2 update configs.__init__, webui.py and api.py 2023-08-17 22:19:37 +08:00
imClumsyPanda 5ec512801f update configs.__init__ 2023-08-17 21:51:21 +08:00
liunux4odoo f8229fc4a9 update server_config example 2023-08-17 21:50:36 +08:00
imClumsyPanda 7f7238168c reformat model_config.py.example 2023-08-17 21:31:30 +08:00
imClumsyPanda 4318197ac7 reformat server_config.py.example 2023-08-17 21:30:40 +08:00
liunux4odoo f92b002342 add startup.py: start specified servers with one command. see python startup.py --help 2023-08-17 13:24:53 +08:00
hzg0601 1a40d464be 更新model_config.py.example: 更改所有模型的默认端口为8888 2023-08-16 22:26:18 +08:00
imClumsyPanda f7c82c13da update model_config.py.example 2023-08-14 19:17:34 +08:00
imClumsyPanda afc6aa968d update webui layout 2023-08-11 23:40:41 +08:00
liunux4odoo a261fda20b add tools to migrate knowledge base 2023-08-11 08:33:05 +08:00
liunux4odoo 17ddee38a4 fix conflict between def_fastchat and pr1037 2023-08-10 15:02:41 +08:00
zqt d4f728dfa2 添加向量数据库pg支持，和向量库docker-compose.ym环境文件 2023-08-10 11:16:52 +08:00
imClumsyPanda 8df00d0b04 add SCORE_THRESHOLD to faiss and milvus kb service 2023-08-10 00:36:59 +08:00
imClumsyPanda d67e354276 update model_config.py.example and README.md 2023-08-09 23:45:27 +08:00
imClumsyPanda dd26f552db update model_config.py.example 2023-08-09 23:39:05 +08:00
hzg0601 be7d31416c update model_config.py.example 2023-08-09 23:24:17 +08:00
imClumsyPanda 24a280ce8c re-add zh_title_enhance.py 2023-08-09 23:09:24 +08:00
liunux4odoo e918244159 move KBServiceFactory to server.knowledge_base.kb_service.base 2023-08-08 17:41:58 +08:00
liunux4odoo 7e07f0bbf4 move configs to configs.model_config 2023-08-08 15:56:32 +08:00
zqt b61e0772c9 使用orm操作数据库 2023-08-08 14:25:55 +08:00
zqt 72951d95fb 添加milvus库支持 2023-08-07 16:32:34 +08:00
imClumsyPanda 18d31f5116 add KBService and KBServiceFactory class 2023-08-06 23:44:02 +08:00
imClumsyPanda 3f045cedb9 1. add add_doc and list_docs to KnowledgeBase class 
2. add DB_ROOT_PATH to model_config.py.example
 2023-08-05 22:57:19 +08:00
liunux4odoo 9a18218293 add new config variable to config example 2023-08-04 09:16:28 +08:00
hzg0601 ab7a76f380 update llm_api_sh.py and model_config.example 2023-08-01 22:07:05 +08:00
hzg0601 18a94fcf45 Merge branch 'dev_fastchat' of github.com:chatchat-space/langchain-ChatGLM into dev_fastchat 2023-08-01 18:02:52 +08:00
hzg0601 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 2023-08-01 17:59:20 +08:00
imClumsyPanda 7c01a2a253 add bing_search_chat.py and duckduckgo_search_chat.py 2023-08-01 16:39:17 +08:00
imClumsyPanda 7d79b676d5 add model_config.py.example instead of model_config.py 2023-08-01 14:55:00 +08:00
imClumsyPanda 8261deb99d fix model_config path 2023-08-01 14:49:49 +08:00
imClumsyPanda bcfd3f5af5 add webui_pages 2023-08-01 14:47:38 +08:00
imClumsyPanda 9f4567865c add chatglm2-6b-32k and make m3e default embedding model 2023-08-01 14:12:28 +08:00
liunux4odoo 8b1cf7effd fix: os.environ['OPENAI_API_KEY'] exception when no environment variable set 2023-07-28 16:51:58 +08:00
hzg0601 154cad1b45 会议记录 2023-07-28 16:12:57 +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 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 db80358df8
Update model_config.py 
fix openai api url
 2023-07-25 11:16:02 +08:00
hzg0601 3b6819f091 更改默认的LLM_MODEL 2023-07-21 15:35:17 +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