b161985d79
fix #1519 : streamlit-chatbox旧版BUG，但新版有兼容问题，先在webui中作处理，并限定chatbox版本 ( #1525 )
...
close #1519
2023-09-20 16:47:07 +08:00
fbaca1009e
update requirements.txt, requirements_api.txt, test_different_splitter.py and chinese_recursive_text_splitter.py
2023-09-14 22:59:05 +08:00
c4cb4e19e5
清理不必要的依赖，增加星火API需要的websockets ( #1463 )
2023-09-13 15:35:04 +08:00
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
b0a9d8f30e
增加显示ocr识别进度
2023-09-08 21:32:41 +08:00
673410ecd5
fix pdf ocr bug
2023-09-06 20:08:56 +08:00
9da7313e7e
update requirements.txt
2023-09-05 14:46:26 +08:00
220b1bd9ae
update requirements.txt
2023-09-05 13:41:08 +08:00
6c4ef26e9a
add RapidOCRPDFLoader and RapidOCRLoader ( #1275 )
...
* 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
2023-09-01 10:23:57 +08:00
37985f29f0
Update requirements.txt
2023-08-26 13:35:47 +08:00
32bf508745
update requirements
2023-08-25 22:53:49 +08:00
2e930cf43c
update requirements.txt
2023-08-25 22:14:56 +08:00
fd5988422e
update langchain version requirements
2023-08-20 16:52:56 +08:00
8ed1f8efca
update fastchat to 0.2.24
2023-08-16 16:15:45 +08:00
f64affc930
update llm_api and api server:
...
1. fastchat's controller/model_worker/api_server use swagger UI offline.
2. add custom title and icon.
3. remove fastapi-offline dependence
2023-08-16 14:20:09 +08:00
353d9fc72b
update init_database.py
2023-08-13 10:25:02 +08:00
e65458a506
update requirements.txt
2023-08-12 10:44:04 +08:00
2a57f49d80
update knowledge base management ui.
...
remove numpy/pandas from requirements, move them to webui requirements
2023-08-11 13:53:20 +08:00
9fc467274f
update requirements.txt
2023-08-10 21:53:09 +08:00
8a4d9168fa
update import pkgs and format
2023-08-10 21:26:05 +08:00
b733a47902
split requirements to 2 parts: basic with api; webui
2023-08-10 15:51:22 +08:00
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
53fef3a7e9
add streamlit-aggrid to requirements
2023-08-10 07:50:24 +08:00
2d49746a8d
add history to chat apis
2023-08-08 23:54:51 +08:00
79be21521a
补充SQLAlchemy==2.0.19版本
2023-08-08 14:29:08 +08:00
40b6d1f178
add python-magic-bin to requirements on windows. or document loader failed at `from unstructured.partion.auto import partion` on windows
2023-08-08 12:03:33 +08:00
44c713ef98
use KBServiceFactory to replace all the KnowledgeBase.
...
make KBServiceFactory support embed_model parameter.
rewrite api: recreate_vector_store.
fix some bugs.
2023-08-07 20:37:16 +08:00
7bfbe18011
update requirements.txt and kb_doc_api.py
2023-08-04 15:12:14 +08:00
3318cef751
update streamlit ui: support latest knowledge base and search engine
...
chat api; export messages to markdown.
2023-08-04 12:52:58 +08:00
82aa805bf3
update requirements.txt
2023-08-03 23:42:55 +08:00
2c5b6bb0ad
streamlit ui 实现LLM流式对话
2023-08-01 14:18:30 +08:00
463659f0ba
llm_api升级到fschat==0.2.20，支持百川模型
2023-07-30 23:16:47 +08:00
41444fd4b5
update requirements.txt and llm_api.py
2023-07-30 00:24:34 +08:00
d4ffc70d96
update requirements.txt
2023-07-29 23:46:02 +08:00
e95996a9b9
update requirements.txt
2023-07-28 06:59:16 +08:00
dcf49a59ef
v0.2.0 first commit
2023-07-27 23:22:07 +08:00
1ef3ef5d27
update gradio version in requirements.txt
2023-07-18 04:03:28 +08:00
a5ca4bf26a
1.增加对llama-cpp模型的支持；2.增加对bloom/chatyuan/baichuan模型的支持；3. 修复多GPU部署的bug;4. 修复了moss_llm.py的bug；5. 增加对openai支持（没有api,未测试);6. 支持在多卡情况自定义设备GPU ( #664 )
...
* 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
* add bloom-3b,bloom-7b1,ggml-vicuna-13b-1.1
* 1.增加对llama-cpp模型的支持；2.增加对bloom模型的支持；3. 修复多GPU部署的bug;4. 增加对openai支持（没有api,未测试)；5.增加了llama-cpp模型部署的说明
* llama模型兼容性说明
* modified: ../configs/model_config.py
modified: ../docs/INSTALL.md
在install.md里增加对llama-cpp模型调用的说明
* 修改llama_llm.py以适应llama-cpp模型
* 完成llama-cpp模型的支持；
* make fastchat and openapi compatiable
* 1. 修复/增加对chatyuan,bloom,baichuan-7等模型的支持；2. 修复了moss_llm.py的bug;
* set default model be chatglm-6b
* 在多卡情况下也支持自定义GPU设备
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-07-11 19:36:50 +08:00
f6218316e3
update requirements.txt and model_config.py
2023-06-18 21:52:49 +08:00
27a9bf2433
更新FAQ和requirements,解决upload_file接口的两个异常 ( #593 )
2023-06-11 21:25:02 +08:00
23052629ad
update requirements.txt
2023-05-31 22:31:54 +08:00
561c40afee
Merge remote-tracking branch 'origin/dev' into dev
2023-05-26 22:32:25 +08:00
994401670b
拓展功能检查依赖提示安装
2023-05-26 22:32:12 +08:00
11bcb58ae6
增加rss订阅，以及添加了依赖文件
2023-05-26 18:50:20 +08:00
9dc9ac6380
添加依赖feedparser
2023-05-26 18:46:18 +08:00
1ee12266e8
更新 requirements.txt
2023-05-24 00:12:59 +08:00
5f38645fa1
update api.py
2023-05-21 22:27:02 +08:00
94b4599cda
update requirements.txt
2023-05-20 01:58:08 +08:00
33bbb4779e
llm_model_dict 处理了loader的一些预设行为，如加载位置，模型名称，模型处理器实例, 定义checkpoint名称和远程路径
...
loader.py: 模型重载
定义 generatorAnswer 增加 AnswerResultStream
定义generate_with_callback收集器，在每次响应时将队列数据同步到AnswerResult
requirements.txt 变更项目依赖
2023-05-18 22:54:41 +08:00
cb8466900f
Fix MOSS模型BUG ( #389 )
2023-05-17 13:44:39 +08:00
liunux4odoo
imClumsyPanda
glide-the
liunux4odoo
zqt
liunux4odoo
Zhi-guo Huang
keenzhu
CHANGXUBO