Merge branch 'TY_V4.0_TESTING' into Agent_Hub_Dev

2025-08-28 04:44:14 +00:00 · 2023-10-20 10:44:05 +08:00 · 2023-10-20 10:44:05 +08:00 · 1920f0d699
commit 1920f0d699
parent 655e0818ef 49cd0d4e57
52 changed files with 960 additions and 151 deletions
--- a/assets/chat_agent/agent_hub_1.png
+++ b/assets/chat_agent/agent_hub_1.png
--- a/assets/chat_agent/agent_hub_2.png
+++ b/assets/chat_agent/agent_hub_2.png
--- a/assets/chat_agent/chat_agent0.png
+++ b/assets/chat_agent/chat_agent0.png
--- a/assets/chat_agent/chat_agent1.png
+++ b/assets/chat_agent/chat_agent1.png
--- a/assets/chat_agent/chat_agent2.png
+++ b/assets/chat_agent/chat_agent2.png
--- a/docker/examples/excel/example.xlsx
+++ b/docker/examples/excel/example.xlsx
--- a/docker/examples/excel/zx.csv
+++ b/docker/examples/excel/zx.csv
@ -0,0 +1,69 @@
+序号,大项,明细,备注,预算,实际,费用小计,超额,已支出,支出小计,其他
+1,中央空调,内外机,1拖5 140 31600,30600,30600,30600,0,30600,30600,
+2,基装,地砖,,106000,32100,107948.4,1948.4,32100,107948.4,1948.4
+3,,地板,,,,,,,,
+4,,门,颜色升级,,37450,,,37450,,
+5,,橱柜,浴柜、马桶、花洒 自选,,,,,,,
+6,,卫生间墙地,,,28149.4,,,28149.4,,
+7,,厨房,墙、地（大改小增项）、菜盆去掉自选,,,,,,,
+8,,打拆改建,,,10249,,,10249,,
+9,其他费用,物业装修管理费（物业）,405.58,26936.23,405.58,20836.23,-6100,405.58,20036.23,
+10,,建渣清运费（物业）,281.65,,281.65,,,281.65,,
+11,,打拆清运费（物业）,1300,,1300,,,1300,,
+,,预交水费,200,,200,,,200,,
+,,客卧加墙,1500,,1500,,,1500,,
+,,天然气暗改,1800,,1800,,,1800,,
+,,天然气明改,719,,719,,,719,,
+,,开槽（150）,0,,0,,,0,,
+,,防水增加,358,,358,,,358,,
+,,墙砖背胶（大砖上墙加背胶）,208,,208,,,208,,
+,,美缝3000,3100,,3100,,,2500,,
+,,淋浴隔断（18980439828）,3130,,3130,,,3130,,
+,,橱柜增加费用,4500,,,,,,,
+,,电费,200,,200,,,200,,
+,,门锁,844,,844,,,844,,
+,,空调机位封窗,1500,,1500,,,1300,,
+,,开关灯安装,1000,,,,,,,
+,,空调机位门,600,,,,,,,
+,,瓷白胶,190,,190,,,190,,
+,,瓷白胶人工,300,,300,,,300,,
+,,每逢增加(橱柜浴柜),,,,,,,,
+,,乳胶漆人工,,,,,,,,
+12,,乳胶漆自购,4800,,4800,,,4800,,
+13,水电改造,材料,16446,18636,16446,18425,-211,16446,18425,
+14,,人工,,,,,,,,
+,,开关插座补,531,,320,,,320,,
+15,,开关插座,1659,,1659,,,1659,,
+16,封窗,,15000,14500,14500,14500,0,4500,14500,
+,,,,,,,,8000,,
+17,,,,,,,,2000,,
+18,基装(自购),马桶*2,9000,8200,8200,20000,,8200,20000,
+19,,花洒*2,3000,4000,4000,,,4000,,
+20,,浴柜*2,5000,4600,4600,,,4600,,
+21,,菜盆,2500,3200,3200,,,3200,,
+22,衣柜定做,鞋柜亮面、衣柜肤质、板材克诺斯邦、侧面表层,40*730,33000,5000,31000,,5000,31000,
+23,,,,,15000,,,15000,,
+,,,,,11000,,,11000,,
+24,,,,,,,,,,
+25,基础家电,燃气热水器,计划史密斯智能4000,3798,3798,18551,,3798,18841,24期免息
+,,燃气热水器安装,,355,355,,,355,,
+26,,洗碗机,计划西门子5999,6999,6999,,,6999,,
+27,,冰箱,计划西门子,6000,,,,,,
+28,,电视,,8000,,,,,,
+,,洗衣机(安装),,290,,,,290,,
+,,抽油烟机+灶具(升级),方太型号升级,3900,3900,,,3900,,
+29,,洗衣机,计划西门子6500,3499,3499,,,3499,,
+30,软装,沙发,15000,71799.8,,10877.8,,,9777.8,
+31,,茶几,5000,,,,,,,
+32,,电视柜,6000,,,,,,,
+33,,餐桌,7000,,,,,,,
+34,,床*2,7000,,,,,,,
+,,床垫*2,13000,,,,,,,
+,,窗帘,10400,,10500,,,9400,,
+,,洞灯,399.8,,377.8,,,377.8,,
+,,书桌,2000,,,,,,,
+35,,灯具,6000,,,,,,,
+36,合计,,,354313.03,272738.43,272738.43,-4362.6,,271128.43,-83184.6
+37,,,,,,,,,,
+38,双十一,,,,,38551,,,,
+,,,,,,,,,,
--- a/docs/getting_started/application/chatagent/chatagent.md
+++ b/docs/getting_started/application/chatagent/chatagent.md
@ -1,25 +1,24 @@
 ChatAgent
 ==================================
 ChatAgent can automatically select the right tool to answer and solve user problems through LLM.
-![ChatAgent](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)
+![ChatAgent](https://github.com/eosphoros-ai/DB-GPT/blob/82d8e4f3bd74bfe7f19b96e51d3483f382227bed/assets/chat_agent/chat_agent0.png)

 ### 1.Update Plugins From Git
 Update the latest plug-in information from the DB-GPT official plug-in repository.
-![Update From Github](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)
+![Update From Github](https://github.com/eosphoros-ai/DB-GPT/blob/82d8e4f3bd74bfe7f19b96e51d3483f382227bed/assets/chat_agent/agent_hub_1.png)

 ### 2.Install Plugin
 Install the plugin you want to use from the list of agent hub plugins.
-![Install Plugin](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)
-
+![Update From Github](https://github.com/eosphoros-ai/DB-GPT/blob/82d8e4f3bd74bfe7f19b96e51d3483f382227bed/assets/chat_agent/agent_hub_1.png)

 ### 3.Upload My Local Plugin File
 If you want to use a private plug-in developed by yourself, you can upload the plug-in first and then use it.
-![Upload Private Plugin](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)

 ### 4.Select installed plug-ins dialog
 Select an installed plugin to have a conversation.
-![Select Plugins](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)
+![Select Plugins](https://github.com/eosphoros-ai/DB-GPT/blob/82d8e4f3bd74bfe7f19b96e51d3483f382227bed/assets/chat_agent/chat_agent1.png)
+![Success Use](https://github.com/eosphoros-ai/DB-GPT/blob/82d8e4f3bd74bfe7f19b96e51d3483f382227bed/assets/chat_agent/chat_agent2.png)

 ### 5.Uninstall My Plugin
 Uninstall plugins you no longer need.
-![Uninstall Plugin](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)
+![Uninstall Plugin](https://github.com/eosphoros-ai/DB-GPT/blob/82d8e4f3bd74bfe7f19b96e51d3483f382227bed/assets/chat_agent/agent_hub_2.png)
--- a/docs/getting_started/application/chatdb/img.png
+++ b/docs/getting_started/application/chatdb/img.png
--- a/docs/getting_started/faq/deploy/deploy_faq.md
+++ b/docs/getting_started/faq/deploy/deploy_faq.md
@ -97,4 +97,10 @@ pip install langchain>=0.0.286

 ```commandline
 pip install --use-pep517 fschat
-```
+```
+
+##### Q9: alembic.util.exc.CommandError: Target database is not up to date.
+delete files in `DB-GPT/pilot/meta_data/alembic/versions/` and reboot.
+```commandline
+rm -rf DB-GPT/pilot/meta_data/alembic/versions/*
+```
--- a/docs/getting_started/install/cluster/vms/standalone.md
+++ b/docs/getting_started/install/cluster/vms/standalone.md
@ -0,0 +1,98 @@
+Standalone Deployment
+==================================
+(standalone-index)=
+
+### Install Prepare
+```commandline
+git clone https://github.com/eosphoros-ai/DB-GPT.git
+
+cd DB-GPT
+```
+
+### Create conda environment
+```commandline
+conda create -n dbgpt_env python=3.10
+
+conda activate dbgpt_env
+```
+
+
+### Install Default Requirements
+```commandline
+# Install Default Requirements
+pip install -e ".[default]"
+```
+
+### Download and Prepare LLM Model and Embedding Model
+```{tip}
+ If you don't have high performance hardware server
+```
+you can use openai api, tongyi api , bard api, etc.
+```commandline
+mkdir models && cd models
+
+# download embedding model, eg: text2vec-large-chinese
+git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese
+
+```
+
+set proxy api in .env
+```commandline
+#set LLM_MODEL TYPE
+LLM_MODEL=proxyllm
+#set your Proxy Api key and Proxy Server url
+PROXY_API_KEY={your-openai-sk}
+PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
+```
+```{tip}
+If you have high performance hardware server
+```
+
+```commandline
+mkdir models && cd models
+
+# # download embedding model, eg: vicuna-13b-v1.5 or  
+git clone https://huggingface.co/lmsys/vicuna-13b-v1.5
+
+# download embedding model, eg: text2vec-large-chinese
+git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese
+
+popd
+```
+### Start all services with a single command.
+```commandline
+LLM_MODEL=vicuna-13b-v1.5 
+dbgpt start webserver --port 6006
+```
+By default, the "dbgpt start webserver" command will start the Webserver, Model Controller, and Model Worker in a single Python process. Here, we specify the service to be started on port 6006.
+
+### View and validate the model service in the command line, you can use the following commands
+##### 1.list the started model services and deployed Model Workers, you can use the following command
+```commandline
+dbgpt model list
+```
+output is:
+```commandline
+-----------------+------------+------------+------+---------+---------+-----------------+----------------------------+
+|    Model Name   | Model Type |    Host    | Port | Healthy | Enabled | Prompt Template |       Last Heartbeat       |
+-----------------+------------+------------+------+---------+---------+-----------------+----------------------------+
+| vicuna-13b-v1.5 |    llm     | 172.17.0.9 | 6006 |   True  |   True  |                 | 2023-10-16T19:49:59.201313 |
+|  WorkerManager  |  service   | 172.17.0.9 | 6006 |   True  |   True  |                 | 2023-10-16T19:49:59.246756 |
+-----------------+------------+------------+------+---------+---------+-----------------+----------------------------+
+```
+The WorkerManager is the management process for Model Workers
+
+##### validate the deployed model in the command line, you can use the following command
+```commandline
+dbgpt model chat --model_name vicuna-13b-v1.5
+```
+Then an interactive page will be launched where you can have a conversation with the deployed LLM in the terminal.
+```commandline
+Chatbot started with model vicuna-13b-v1.5. Type 'exit' to leave the chat.
+
+
+You: Hello
+Bot: Hello! How can I assist you today?
+
+You: 
+```
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/chatagent/chatagent.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/chatagent/chatagent.po
@ -0,0 +1,123 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2023, csunny
+# This file is distributed under the same license as the DB-GPT package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: DB-GPT 👏👏 0.3.9\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2023-10-17 17:24+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.12.1\n"
+
+#: ../../getting_started/application/chatagent/chatagent.md:1
+#: ../../getting_started/application/chatagent/chatagent.md:3
+#: 17aae18073594c7498c8b2434d50b218 77f0177e55e144a89e3bcf735b0d52de
+msgid "ChatAgent"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:3
+#: 41b42808938245dc946960571c09026a
+msgid ""
+"ChatAgent can automatically select the right tool to answer and solve "
+"user problems through LLM. ![ChatAgent](https://github.com/eosphoros-ai"
+"/DB-GPT/assets/13723926/)"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:6
+#: bb76bb44442647a091d008c9e1427e4a
+msgid "1.Update Plugins From Git"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:7
+#: a7f188c3de7e4b85b2d3079128b535b2
+msgid ""
+"Update the latest plug-in information from the DB-GPT official plug-in "
+"repository. ![Update From Github](https://github.com/eosphoros-ai/DB-"
+"GPT/assets/13723926/)"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:7
+#: 612cb75edb2f48a087fc99e6d0890b80
+msgid "Update From Github"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:10
+#: 1ad3f7680837410cb8018fff5787366f
+msgid "2.Install Plugin"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:11
+#: b32e9318a8e347339b6c4cad4b966880
+msgid ""
+"Install the plugin you want to use from the list of agent hub plugins. "
+"![Install Plugin](https://github.com/eosphoros-ai/DB-"
+"GPT/assets/13723926/)"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:11
+#: bee96f7936564bc6be98655bfc6aae0d
+msgid "Install Plugin"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:15
+#: 20d562b9ed004336bb6df8d163554924
+msgid "3.Upload My Local Plugin File"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:16
+#: b43e485ff4f042dd80b5950444c0db08
+msgid ""
+"If you want to use a private plug-in developed by yourself, you can "
+"upload the plug-in first and then use it. ![Upload Private "
+"Plugin](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:16
+#: a05724784c0e45528039b8238fd9ed3c
+msgid "Upload Private Plugin"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:19
+#: 726b5c4cad7d4be9815e9fbeedaecc2b
+msgid "4.Select installed plug-ins dialog"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:20
+#: e3d9dc892d054cbca29267cd0fffe7be
+msgid ""
+"Select an installed plugin to have a conversation. ![Select "
+"Plugins](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:20
+#: 97f28bacc02444c580f6481b21e6c155
+msgid "Select Plugins"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:23
+#: d0272e7d94d743289fb2c1613ee85c36
+msgid "5.Uninstall My Plugin"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:24
+#: 2fee213a12da4674b19fe8891e4318f5
+msgid ""
+"Uninstall plugins you no longer need. ![Uninstall "
+"Plugin](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/)"
+msgstr ""
+
+#: ../../getting_started/application/chatagent/chatagent.md:24
+#: 32e5405249134863bcaf85b0ef91260f
+msgid "Uninstall Plugin"
+msgstr ""
+
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/faq/deploy/deploy_faq.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/faq/deploy/deploy_faq.po
@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-09-26 17:47+0800\n"
+"POT-Creation-Date: 2023-10-19 19:31+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@ -20,12 +20,12 @@ msgstr ""
 "Generated-By: Babel 2.12.1\n"

 #: ../../getting_started/faq/deploy/deploy_faq.md:1
-#: ca823e9d6d1d433db7ed15c8273e1b00
+#: fb640f7c38744cbf996dcf7f73f325f6
 msgid "Installation FAQ"
 msgstr "Installation FAQ"

 #: ../../getting_started/faq/deploy/deploy_faq.md:5
-#: 3803d098c534434f9f513b3a62de54a4
+#: 79fd80e469d14d608554d53a0e0ed2e3
 #, fuzzy
 msgid ""
 "Q1: execute `pip install -e .` error, found some package cannot find "
@ -35,18 +35,18 @@ msgstr ""
 "cannot find correct version."

 #: ../../getting_started/faq/deploy/deploy_faq.md:6
-#: b785864f47e643df9a4669d8da6167d6
+#: f1f6e3291d1446b5bbcf744cd4c4e89a
 msgid "change the pip source."
 msgstr "替换pip源."

 #: ../../getting_started/faq/deploy/deploy_faq.md:13
 #: ../../getting_started/faq/deploy/deploy_faq.md:20
-#: c41f026fb1464c71a45d0746c224ecce f70fb69b568d4fc4ad4c4731b2032eaf
+#: 68e1b39a08774a81b9061cc5205e4c1c dd34901f446749e998cd34ec5b6c44f4
 msgid "or"
 msgstr "或者"

 #: ../../getting_started/faq/deploy/deploy_faq.md:27
-#: d179e3d695764f838dc354eb0d978bb3
+#: 0899f0e28dae443b8f912d96c797b79c
 msgid ""
 "Q2: sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) unable to"
 " open database file"
@ -55,86 +55,97 @@ msgstr ""
 " open database file"

 #: ../../getting_started/faq/deploy/deploy_faq.md:29
-#: 55174e8d247a414e8c6c8861d4707a55
+#: 3e60d8190e49436b8c40b34a67b7bfb3
 msgid "make sure you pull latest code or create directory with mkdir pilot/data"
 msgstr "make sure you pull latest code or create directory with mkdir pilot/data"

 #: ../../getting_started/faq/deploy/deploy_faq.md:31
-#: dbce9e9cae734a5083a6f0fc28bce7cd
+#: baeaae20238842d3b8e4ae5b337198e5
 msgid "Q3: The model keeps getting killed."
 msgstr "Q3: The model keeps getting killed."

 #: ../../getting_started/faq/deploy/deploy_faq.md:33
-#: 2de5648d2e7546bf85f20f4162003298
+#: eb3936307ad64b19b73483ff9ae126f2
 msgid ""
 "your GPU VRAM size is not enough, try replace your hardware or replace "
 "other llms."
 msgstr "GPU显存不够, 增加显存或者换一个显存小的模型"

 #: ../../getting_started/faq/deploy/deploy_faq.md:35
-#: 47810771cd364964b9b5b8fd85bca4ee
+#: f6dba770717041699c73b4cd00d48aad
 msgid "Q4: How to access website on the public network"
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:37
-#: e8c5bac6680648509d528ea6aaf5994e
+#: 447d9e9374de44bab6d8a03f2c936676
 msgid ""
 "You can try to use gradio's [network](https://github.com/gradio-"
 "app/gradio/blob/main/gradio/networking.py) to achieve."
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:48
-#: bb75ec127f574c00a09d92d5206e9357
+#: 5e34dd4dfcf34feeb1815dfa974041d0
 msgid "Open `url` with your browser to see the website."
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:50
-#: 5fdb87b84bd94385a1a93dab8d41ebe8
+#: aaef774ce6124021a3862bc0a25d465f
 msgid "Q5: (Windows) execute `pip install -e .` error"
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:52
-#: 31eef51e044044f29f3ad08defa9c305
+#: ec3945df451c4ec2b32ebb476f45c82b
 msgid "The error log like the following:"
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:71
-#: aaba0c3060b443e4b9877f70d78321ce
+#: 1df09f6d9f9b4c1a8a32d6e271e5ee39
 msgid ""
 "Download and install `Microsoft C++ Build Tools` from [visual-cpp-build-"
 "tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/)"
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:75
-#: 4c8137546e5c4240884f7ea6d9d922bf
+#: 251f47bfa5694242a1c9d81a2022b7a0
 msgid "Q6: `Torch not compiled with CUDA enabled`"
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:82
-#: 01daf14f8c494219b1d9a5af4449951e
+#: bc9dfdfc47924a0e8d3ec535e23bf923
 msgid "Install [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit-archive)"
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:83
-#: c75e6371911e4d5ca6859e51501c9679
+#: b5a632baa42745bdbee5d6ba516d8d8b
 msgid ""
 "Reinstall PyTorch [start-locally](https://pytorch.org/get-started/locally"
 "/#start-locally) with CUDA support."
 msgstr ""

 #: ../../getting_started/faq/deploy/deploy_faq.md:85
-#: 7cfb9003e505445ebb9ed3d015e184e2
+#: 0092fb91642749f5a55b629017c0de6a
 msgid "Q7: ImportError: cannot import name 'PersistentClient' from 'chromadb'."
 msgstr "Q7: ImportError: cannot import name 'PersistentClient' from 'chromadb'."

 #: ../../getting_started/faq/deploy/deploy_faq.md:91
-#: e1d5d5d85ddc480d8d81f7b550848cbf
+#: 4aa87418f2a54c138bf3b7ff28a7e776
 msgid ""
 "Q8: pydantic.error_wrappers.ValidationError:1 validation error for "
 "HuggingFaceEmbeddings.model_kwargs extra not permitted"
-msgstr "Q8: pydantic.error_wrappers.ValidationError:1 validation error for "
+msgstr ""
+"Q8: pydantic.error_wrappers.ValidationError:1 validation error for "
 "HuggingFaceEmbeddings.model_kwargs extra not permitted"

+#: ../../getting_started/faq/deploy/deploy_faq.md:102
+#: 6b690ab272af44f6b126cfe5ce1435ef
+msgid "Q9: alembic.util.exc.CommandError: Target database is not up to date."
+msgstr ""
+
+#: ../../getting_started/faq/deploy/deploy_faq.md:103
+#: 223026d3b9124363b695937922d8f8d5
+msgid "delete files in `DB-GPT/pilot/meta_data/alembic/versions/` and reboot."
+msgstr "删除`DB-GPT/pilot/meta_data/alembic/versions/`目录下文件"
+
 #~ msgid ""
 #~ "Q2: When use Mysql, Access denied "
 #~ "for user 'root@localhost'(using password :NO)"
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/cluster/vms/standalone.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/cluster/vms/standalone.po
@ -0,0 +1,117 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2023, csunny
+# This file is distributed under the same license as the DB-GPT package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: DB-GPT 👏👏 0.3.9\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2023-10-17 17:24+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.12.1\n"
+
+#: ../../getting_started/install/cluster/vms/standalone.md:1
+#: 40af95d327574e5ea9a6c29f68a7709c
+msgid "Standalone Deployment"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:5
+#: 7ef23971a0d2415a857d5eb9c4d955ac
+msgid "Install Prepare"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:12
+#: f3cd2941fa2d49d686fc246237f82e68
+msgid "Create conda environment"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:20
+#: 589d80d5d97044ee93747091904583c5
+msgid "Install Default Requirements"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:26
+#: 1d151e72660644e7b43084ffccb99598
+msgid "Download and Prepare LLM Model and Embedding Model"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:28
+#: 4443c83f8dfa4fdba30929f1e5ecf619
+msgid "If you don't have high performance hardware server"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:30
+#: 33a6ee878a4a467d8bcfe5dfbdcbe184
+msgid "you can use openai api, tongyi api , bard api, etc."
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:39
+#: 7efdb99bc36d42819b1fcd1341b45eef
+msgid "set proxy api in .env"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:48
+#: 50154ece70bc421ebe7ac05966369bc8
+msgid "If you have high performance hardware server"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:62
+#: 4f3696ed069a4a84b2d794593df23765
+msgid "Start all services with a single command."
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:67
+#: f5f671962cb14a10aba34c4274d2fc2c
+msgid ""
+"By default, the \"dbgpt start webserver\" command will start the "
+"Webserver, Model Controller, and Model Worker in a single Python process."
+" Here, we specify the service to be started on port 6006."
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:69
+#: 4883221a356843f6a6335c25847aecd2
+msgid ""
+"View and validate the model service in the command line, you can use the "
+"following commands"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:70
+#: 1346eb55d7c647be90a90a867ba04ec3
+msgid ""
+"1.list the started model services and deployed Model Workers, you can use"
+" the following command"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:74
+#: 8ab332ebce554758952dbe85c68330a9
+msgid "output is:"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:83
+#: efb460bbb70842218f5c056cf05ba1a0
+msgid "The WorkerManager is the management process for Model Workers"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:85
+#: 10e5b79f3d914ee3974b1a0d07962fe2
+msgid ""
+"validate the deployed model in the command line, you can use the "
+"following command"
+msgstr ""
+
+#: ../../getting_started/install/cluster/vms/standalone.md:89
+#: 39d062e7fea948949c1c5c099893f308
+msgid ""
+"Then an interactive page will be launched where you can have a "
+"conversation with the deployed LLM in the terminal."
+msgstr ""
+
--- a/pilot/base_modules/agent/db/my_plugin_db.py
+++ b/pilot/base_modules/agent/db/my_plugin_db.py
@ -9,7 +9,10 @@ from pilot.base_modules.meta_data.meta_data import Base, engine, session

 class MyPluginEntity(Base):
    __tablename__ = "my_plugin"
-
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    id = Column(Integer, primary_key=True, comment="autoincrement id")
    tenant = Column(String(255), nullable=True, comment="user's tenant")
    user_code = Column(String(255), nullable=False, comment="user code")
@ -27,7 +30,7 @@ class MyPluginEntity(Base):
    created_at = Column(
        DateTime, default=datetime.utcnow, comment="plugin install time"
    )
-    __table_args__ = (UniqueConstraint("user_code", "name", name="uk_name"),)
+    UniqueConstraint("user_code", "name", name="uk_name")


 class MyPluginDao(BaseDao[MyPluginEntity]):
--- a/pilot/base_modules/agent/db/plugin_hub_db.py
+++ b/pilot/base_modules/agent/db/plugin_hub_db.py
@ -1,7 +1,7 @@
 from datetime import datetime
 import pytz
 from typing import List
-from sqlalchemy import Column, Integer, String, Index, DateTime, func, Boolean
+from sqlalchemy import Column, Integer, String, Index, DateTime, func, Boolean, DDL
 from sqlalchemy import UniqueConstraint
 from pilot.base_modules.meta_data.meta_data import Base

@ -9,8 +9,15 @@ from pilot.base_modules.meta_data.base_dao import BaseDao
 from pilot.base_modules.meta_data.meta_data import Base, engine, session


+char_set_sql = DDL("ALTER TABLE plugin_hub CONVERT TO CHARACTER SET utf8mb4")
+
+
 class PluginHubEntity(Base):
    __tablename__ = "plugin_hub"
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    id = Column(
        Integer, primary_key=True, autoincrement=True, comment="autoincrement id"
    )
@ -26,10 +33,8 @@ class PluginHubEntity(Base):
    created_at = Column(DateTime, default=datetime.utcnow, comment="plugin upload time")
    installed = Column(Integer, default=False, comment="plugin already installed count")

-    __table_args__ = (
-        UniqueConstraint("name", name="uk_name"),
-        Index("idx_q_type", "type"),
-    )
+    UniqueConstraint("name", name="uk_name")
+    Index("idx_q_type", "type")


 class PluginHubDao(BaseDao[PluginHubEntity]):
--- a/pilot/connections/manages/connection_manager.py
+++ b/pilot/connections/manages/connection_manager.py
@ -154,7 +154,7 @@ class ConnectManager:
            db_type = DBType.of_db_type(db_info.db_type)
            connect_instance = self.get_cls_by_dbtype(db_type.value())
            if db_type.is_file_db():
-                db_path = db_info.db_path
+                db_path = db_info.file_path
                return connect_instance.from_file_path(db_path)
            else:
                db_name = db_info.db_name
--- a/pilot/connections/rdbms/base.py
+++ b/pilot/connections/rdbms/base.py
@ -52,7 +52,18 @@ class RDBMSDatabase(BaseConnect):
        custom_table_info: Optional[dict] = None,
        view_support: bool = False,
    ):
-        """Create engine from database URI."""
+        """Create engine from database URI.
+        Args:
+           - engine: Engine sqlalchemy.engine
+           - schema: Optional[str].
+           - metadata: Optional[MetaData]
+           - ignore_tables: Optional[List[str]]
+           - include_tables: Optional[List[str]]
+           - sample_rows_in_table_info: int default:3,
+           - indexes_in_table_info: bool = False,
+           - custom_table_info: Optional[dict] = None,
+           - view_support: bool = False,
+        """
        self._engine = engine
        self._schema = schema
        if include_tables and ignore_tables:
@ -92,6 +103,15 @@ class RDBMSDatabase(BaseConnect):
        engine_args: Optional[dict] = None,
        **kwargs: Any,
    ) -> RDBMSDatabase:
+        """Construct a SQLAlchemy engine from uri database.
+        Args:
+            host (str): database host.
+            port (int): database port.
+            user (str): database user.
+            pwd (str): database password.
+            db_name (str): database name.
+            engine_args (Optional[dict]):other engine_args.
+        """
        db_url: str = (
            cls.driver
            + "://"
@ -329,7 +349,7 @@ class RDBMSDatabase(BaseConnect):
    def run(self, command: str, fetch: str = "all") -> List:
        """Execute a SQL command and return a string representing the results."""
        print("SQL:" + command)
-        if not command:
+        if not command or len(command) <0:
            return []
        parsed, ttype, sql_type, table_name = self.__sql_parse(command)
        if ttype == sqlparse.tokens.DML:
--- a/pilot/embedding_engine/csv_embedding.py
+++ b/pilot/embedding_engine/csv_embedding.py
@ -21,7 +21,13 @@ class CSVEmbedding(SourceEmbedding):
        source_reader: Optional = None,
        text_splitter: Optional[TextSplitter] = None,
    ):
-        """Initialize with csv path."""
+        """Initialize with csv path.
+        Args:
+           - file_path: data source path
+           - vector_store_config: vector store config params.
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+        """
        super().__init__(
            file_path, vector_store_config, source_reader=None, text_splitter=None
        )
--- a/pilot/embedding_engine/embedding_engine.py
+++ b/pilot/embedding_engine/embedding_engine.py
@ -28,7 +28,16 @@ class EmbeddingEngine:
        text_splitter: Optional[TextSplitter] = None,
        embedding_factory: EmbeddingFactory = None,
    ):
-        """Initialize with knowledge embedding client, model_name, vector_store_config, knowledge_type, knowledge_source"""
+        """Initialize with knowledge embedding client, model_name, vector_store_config, knowledge_type, knowledge_source
+        Args:
+           - model_name: model_name
+           - vector_store_config: vector store config: Dict
+           - knowledge_type: Optional[KnowledgeType]
+           - knowledge_source: Optional[str]
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+           - embedding_factory: EmbeddingFactory
+        """
        self.knowledge_source = knowledge_source
        self.model_name = model_name
        self.vector_store_config = vector_store_config
@ -65,6 +74,11 @@ class EmbeddingEngine:
        )

    def similar_search(self, text, topk):
+        """vector db similar search
+        Args:
+           - text: query text
+           - topk: top k
+        """
        vector_client = VectorStoreConnector(
            self.vector_store_config["vector_store_type"], self.vector_store_config
        )
@ -75,12 +89,17 @@ class EmbeddingEngine:
        return ans

    def vector_exist(self):
+        """vector db is exist"""
        vector_client = VectorStoreConnector(
            self.vector_store_config["vector_store_type"], self.vector_store_config
        )
        return vector_client.vector_name_exists()

    def delete_by_ids(self, ids):
+        """delete vector db by ids
+        Args:
+           - ids: vector ids
+        """
        vector_client = VectorStoreConnector(
            self.vector_store_config["vector_store_type"], self.vector_store_config
        )
--- a/pilot/embedding_engine/pdf_embedding.py
+++ b/pilot/embedding_engine/pdf_embedding.py
@ -23,7 +23,13 @@ class PDFEmbedding(SourceEmbedding):
        source_reader: Optional = None,
        text_splitter: Optional[TextSplitter] = None,
    ):
-        """Initialize pdf word path."""
+        """Initialize pdf word path.
+        Args:
+           - file_path: data source path
+           - vector_store_config: vector store config params.
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+        """
        super().__init__(
            file_path, vector_store_config, source_reader=None, text_splitter=None
        )
--- a/pilot/embedding_engine/ppt_embedding.py
+++ b/pilot/embedding_engine/ppt_embedding.py
@ -23,7 +23,13 @@ class PPTEmbedding(SourceEmbedding):
        source_reader: Optional = None,
        text_splitter: Optional[TextSplitter] = None,
    ):
-        """Initialize ppt word path."""
+        """Initialize ppt word path.
+        Args:
+           - file_path: data source path
+           - vector_store_config: vector store config params.
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+        """
        super().__init__(
            file_path, vector_store_config, source_reader=None, text_splitter=None
        )
--- a/pilot/embedding_engine/source_embedding.py
+++ b/pilot/embedding_engine/source_embedding.py
@ -29,7 +29,14 @@ class SourceEmbedding(ABC):
        text_splitter: Optional[TextSplitter] = None,
        embedding_args: Optional[Dict] = None,
    ):
-        """Initialize with Loader url, model_name, vector_store_config"""
+        """Initialize with Loader url, model_name, vector_store_config
+        Args:
+           - file_path: data source path
+           - vector_store_config: vector store config params.
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+           - embedding_args: Optional
+        """
        self.file_path = file_path
        self.vector_store_config = vector_store_config
        self.source_reader = source_reader or None
@ -44,21 +51,33 @@ class SourceEmbedding(ABC):

    @register
    def data_process(self, text):
-        """pre process data."""
+        """pre process data.
+        Args:
+          - text: raw text
+        """

    @register
    def text_splitter(self, text_splitter: TextSplitter):
-        """add text split chunk"""
+        """add text split chunk
+        Args:
+           - text_splitter: TextSplitter
+        """
        pass

    @register
    def text_to_vector(self, docs):
-        """transform vector"""
+        """transform vector
+        Args:
+           - docs: List[Document]
+        """
        pass

    @register
    def index_to_store(self, docs):
-        """index to vector store"""
+        """index to vector store
+        Args:
+           - docs: List[Document]
+        """
        self.vector_client = VectorStoreConnector(
            self.vector_store_config["vector_store_type"], self.vector_store_config
        )
@ -66,7 +85,10 @@ class SourceEmbedding(ABC):

    @register
    def similar_search(self, doc, topk):
-        """vector store similarity_search"""
+        """vector store similarity_search
+        Args:
+           - query: query
+        """
        self.vector_client = VectorStoreConnector(
            self.vector_store_config["vector_store_type"], self.vector_store_config
        )
@ -82,6 +104,7 @@ class SourceEmbedding(ABC):
        return self.vector_client.vector_name_exists()

    def source_embedding(self):
+        """read()->data_process()->text_split()->index_to_store()"""
        if "read" in registered_methods:
            text = self.read()
        if "data_process" in registered_methods:
--- a/pilot/embedding_engine/string_embedding.py
+++ b/pilot/embedding_engine/string_embedding.py
@ -20,7 +20,13 @@ class StringEmbedding(SourceEmbedding):
        source_reader: Optional = None,
        text_splitter: Optional[TextSplitter] = None,
    ):
-        """Initialize raw text word path."""
+        """Initialize raw text word path.
+        Args:
+           - file_path: data source path
+           - vector_store_config: vector store config params.
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+        """
        super().__init__(
            file_path=file_path,
            vector_store_config=vector_store_config,
--- a/pilot/embedding_engine/url_embedding.py
+++ b/pilot/embedding_engine/url_embedding.py
@ -22,7 +22,13 @@ class URLEmbedding(SourceEmbedding):
        source_reader: Optional = None,
        text_splitter: Optional[TextSplitter] = None,
    ):
-        """Initialize url word path."""
+        """Initialize url word path.
+        Args:
+           - file_path: data source path
+           - vector_store_config: vector store config params.
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+        """
        super().__init__(
            file_path, vector_store_config, source_reader=None, text_splitter=None
        )
--- a/pilot/embedding_engine/word_embedding.py
+++ b/pilot/embedding_engine/word_embedding.py
@ -23,7 +23,13 @@ class WordEmbedding(SourceEmbedding):
        source_reader: Optional = None,
        text_splitter: Optional[TextSplitter] = None,
    ):
-        """Initialize with word path."""
+        """Initialize with word path.
+        Args:
+           - file_path: data source path
+           - vector_store_config: vector store config params.
+           - source_reader: Optional[BaseLoader]
+           - text_splitter: Optional[TextSplitter]
+        """
        super().__init__(
            file_path, vector_store_config, source_reader=None, text_splitter=None
        )
--- a/pilot/memory/chat_history/chat_history_db.py
+++ b/pilot/memory/chat_history/chat_history_db.py
@ -10,6 +10,10 @@ class ChatHistoryEntity(Base):
    id = Column(
        Integer, primary_key=True, autoincrement=True, comment="autoincrement id"
    )
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    conv_uid = Column(
        String(255),
        unique=False,
@ -21,12 +25,10 @@ class ChatHistoryEntity(Base):
    user_name = Column(String(255), nullable=True, comment="interlocutor")
    messages = Column(Text, nullable=True, comment="Conversation details")

-    __table_args__ = (
-        UniqueConstraint("conv_uid", name="uk_conversation"),
-        Index("idx_q_user", "user_name"),
-        Index("idx_q_mode", "chat_mode"),
-        Index("idx_q_conv", "summary"),
-    )
+    UniqueConstraint("conv_uid", name="uk_conversation")
+    Index("idx_q_user", "user_name")
+    Index("idx_q_mode", "chat_mode")
+    Index("idx_q_conv", "summary")


 class ChatHistoryDao(BaseDao[ChatHistoryEntity]):
--- a/pilot/model/cluster/controller/controller.py
+++ b/pilot/model/cluster/controller/controller.py
@ -185,7 +185,7 @@ def run_model_controller():
    setup_logging(
        "pilot",
        logging_level=controller_params.log_level,
-        logger_filename="dbgpt_model_controller.log",
+        logger_filename=controller_params.log_file,
    )

    initialize_controller(host=controller_params.host, port=controller_params.port)
--- a/pilot/model/cluster/worker/manager.py
+++ b/pilot/model/cluster/worker/manager.py
@ -1006,7 +1006,7 @@ def run_worker_manager(
    setup_logging(
        "pilot",
        logging_level=worker_params.log_level,
-        logger_filename="dbgpt_model_worker_manager.log",
+        logger_filename=worker_params.log_file,
    )

    embedded_mod = True
@ -1019,7 +1019,7 @@ def run_worker_manager(
    system_app = SystemApp(app)
    initialize_tracer(
        system_app,
-        os.path.join(LOGDIR, "dbgpt_model_worker_manager_tracer.jsonl"),
+        os.path.join(LOGDIR, worker_params.tracer_file),
        root_operation_name="DB-GPT-WorkerManager-Entry",
    )

--- a/pilot/model/parameter.py
+++ b/pilot/model/parameter.py
@ -46,6 +46,18 @@ class ModelControllerParameters(BaseParameters):
            ],
        },
    )
+    log_file: Optional[str] = field(
+        default="dbgpt_model_controller.log",
+        metadata={
+            "help": "The filename to store log",
+        },
+    )
+    tracer_file: Optional[str] = field(
+        default="dbgpt_model_controller_tracer.jsonl",
+        metadata={
+            "help": "The filename to store tracer span records",
+        },
+    )


@dataclass
@ -122,6 +134,18 @@ class ModelWorkerParameters(BaseModelParameters):
            ],
        },
    )
+    log_file: Optional[str] = field(
+        default="dbgpt_model_worker_manager.log",
+        metadata={
+            "help": "The filename to store log",
+        },
+    )
+    tracer_file: Optional[str] = field(
+        default="dbgpt_model_worker_manager_tracer.jsonl",
+        metadata={
+            "help": "The filename to store tracer span records",
+        },
+    )


@dataclass
--- a/pilot/openapi/api_v1/feedback/feed_back_db.py
+++ b/pilot/openapi/api_v1/feedback/feed_back_db.py
@ -1,16 +1,18 @@
 from datetime import datetime

 from sqlalchemy import Column, Integer, Text, String, DateTime
-from sqlalchemy.ext.declarative import declarative_base

-from pilot.connections.rdbms.base_dao import BaseDao
+from pilot.base_modules.meta_data.base_dao import BaseDao
+from pilot.base_modules.meta_data.meta_data import Base, engine, session
 from pilot.openapi.api_v1.feedback.feed_back_model import FeedBackBody

-Base = declarative_base()
-

 class ChatFeedBackEntity(Base):
    __tablename__ = "chat_feed_back"
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    id = Column(Integer, primary_key=True)
    conv_uid = Column(String(128))
    conv_index = Column(Integer)
@ -33,13 +35,15 @@ class ChatFeedBackEntity(Base):

 class ChatFeedBackDao(BaseDao):
    def __init__(self):
-        super().__init__(database="history", orm_base=Base, create_not_exist_table=True)
+        super().__init__(
+            database="dbgpt", orm_base=Base, db_engine=engine, session=session
+        )

    def create_or_update_chat_feed_back(self, feed_back: FeedBackBody):
        # Todo: We need to have user information first.
        def_user_name = ""

-        session = self.Session()
+        session = self.get_session()
        chat_feed_back = ChatFeedBackEntity(
            conv_uid=feed_back.conv_uid,
            conv_index=feed_back.conv_index,
@ -73,7 +77,7 @@ class ChatFeedBackDao(BaseDao):
        session.close()

    def get_chat_feed_back(self, conv_uid: str, conv_index: int):
-        session = self.Session()
+        session = self.get_session()
        result = (
            session.query(ChatFeedBackEntity)
            .filter(ChatFeedBackEntity.conv_uid == conv_uid)
--- a/pilot/scene/base_chat.py
+++ b/pilot/scene/base_chat.py
@ -21,6 +21,12 @@ CFG = Config()


 class BaseChat(ABC):
+    """DB-GPT Chat Service Base Module
+    Include:
+    stream_call():scene + prompt -> stream response
+    nostream_call():scene + prompt -> nostream response
+    """
+
    chat_scene: str = None
    llm_model: Any = None
    # By default, keep the last two rounds of conversation records as the context
@ -32,6 +38,14 @@ class BaseChat(ABC):
        arbitrary_types_allowed = True

    def __init__(self, chat_param: Dict):
+        """Chat Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) select param
+        """
        self.chat_session_id = chat_param["chat_session_id"]
        self.chat_mode = chat_param["chat_mode"]
        self.current_user_input: str = chat_param["current_user_input"]
@ -359,7 +373,10 @@ class BaseChat(ABC):
                )
            if len(self.history_message) > self.chat_retention_rounds:
                for first_message in self.history_message[0]["messages"]:
-                    if not first_message["type"] in [ModelMessageRoleType.VIEW, ModelMessageRoleType.SYSTEM]:
+                    if not first_message["type"] in [
+                        ModelMessageRoleType.VIEW,
+                        ModelMessageRoleType.SYSTEM,
+                    ]:
                        message_type = first_message["type"]
                        message_content = first_message["data"]["content"]
                        history_text += (
--- a/pilot/scene/chat_agent/chat.py
+++ b/pilot/scene/chat_agent/chat.py
@ -18,10 +18,20 @@ logger = logging.getLogger("chat_agent")


 class ChatAgent(BaseChat):
+    """Chat With Agent through plugin"""
+
    chat_scene: str = ChatScene.ChatAgent.value()
    chat_retention_rounds = 0

    def __init__(self, chat_param: Dict):
+        """Chat Agent Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) agent plugin
+        """
        if not chat_param["select_param"]:
            raise ValueError("Please select a Plugin!")
        self.select_plugins = chat_param["select_param"].split(",")
@ -53,7 +63,6 @@ class ChatAgent(BaseChat):

    def stream_plugin_call(self, text):
        text = text.replace("\n", " ")
-        print(f"stream_plugin_call:{text}")
        return self.api_call.run(text)

    def __list_to_prompt_str(self, list: List) -> str:
--- a/pilot/scene/chat_dashboard/chat.py
+++ b/pilot/scene/chat_dashboard/chat.py
@ -19,10 +19,17 @@ CFG = Config()
 class ChatDashboard(BaseChat):
    chat_scene: str = ChatScene.ChatDashboard.value()
    report_name: str
-    """Number of results to return from the query"""
+    """Chat Dashboard to generate dashboard chart"""

    def __init__(self, chat_param: Dict):
-        """ """
+        """Chat Dashboard Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) dbname
+        """
        self.db_name = chat_param["select_param"]
        chat_param["chat_mode"] = ChatScene.ChatDashboard
        super().__init__(chat_param=chat_param)
--- a/pilot/scene/chat_data/chat_excel/excel_analyze/chat.py
+++ b/pilot/scene/chat_data/chat_excel/excel_analyze/chat.py
@ -19,10 +19,20 @@ CFG = Config()


 class ChatExcel(BaseChat):
+    """a Excel analyzer to analyze Excel Data"""
+
    chat_scene: str = ChatScene.ChatExcel.value()
    chat_retention_rounds = 1

    def __init__(self, chat_param: Dict):
+        """Chat Excel Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) file path
+        """
        chat_mode = ChatScene.ChatExcel

        self.select_param = chat_param["select_param"]
@ -78,5 +88,4 @@ class ChatExcel(BaseChat):

    def stream_plugin_call(self, text):
        text = text.replace("\n", " ")
-        print(f"stream_plugin_call:{text}")
        return self.api_call.run_display_sql(text, self.excel_reader.get_df_by_sql_ex)
--- a/pilot/scene/chat_db/auto_execute/chat.py
+++ b/pilot/scene/chat_db/auto_execute/chat.py
@ -16,6 +16,14 @@ class ChatWithDbAutoExecute(BaseChat):
    """Number of results to return from the query"""

    def __init__(self, chat_param: Dict):
+        """Chat Data Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) dbname
+        """
        chat_mode = ChatScene.ChatWithDbExecute
        self.db_name = chat_param["select_param"]
        chat_param["chat_mode"] = chat_mode
@ -33,6 +41,9 @@ class ChatWithDbAutoExecute(BaseChat):
        self.api_call = ApiCall(display_registry=CFG.command_disply)

    def generate_input_values(self):
+        """
+        generate input values
+        """
        try:
            from pilot.summary.db_summary_client import DBSummaryClient
        except ImportError:
--- a/pilot/scene/chat_db/auto_execute/out_parser.py
+++ b/pilot/scene/chat_db/auto_execute/out_parser.py
@ -36,8 +36,8 @@ class DbChatOutputParser(BaseOutputParser):

        ### tool out data to table view
        data_loader = DbDataLoader()
-        if len(data) <= 1:
-            data.insert(0, ["result"])
+        if len(data) < 1:
+            data.insert(0, [])
        df = pd.DataFrame(data[1:], columns=data[0])
        if not CFG.NEW_SERVER_MODE and not CFG.SERVER_LIGHT_MODE:
            table_style = """<style> 
--- a/pilot/scene/chat_db/data_loader.py
+++ b/pilot/scene/chat_db/data_loader.py
@ -3,7 +3,7 @@ class DbDataLoader:
        import pandas as pd

        ### tool out data to table view
-        if len(data) <= 1:
+        if len(data) < 1:
            data.insert(0, ["result"])
        df = pd.DataFrame(data[1:], columns=data[0])
        html_table = df.to_html(index=False, escape=False, sparsify=False)
--- a/pilot/scene/chat_db/professional_qa/chat.py
+++ b/pilot/scene/chat_db/professional_qa/chat.py
@ -12,10 +12,17 @@ CFG = Config()
 class ChatWithDbQA(BaseChat):
    chat_scene: str = ChatScene.ChatWithDbQA.value()

-    """Number of results to return from the query"""
+    """As a DBA, Chat DB Module, chat with combine DB meta schema """

    def __init__(self, chat_param: Dict):
-        """ """
+        """Chat DB Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) dbname
+        """
        self.db_name = chat_param["select_param"]
        chat_param["chat_mode"] = ChatScene.ChatWithDbQA
        super().__init__(chat_param=chat_param)
--- a/pilot/scene/chat_execution/chat.py
+++ b/pilot/scene/chat_execution/chat.py
@ -11,11 +11,21 @@ CFG = Config()


 class ChatWithPlugin(BaseChat):
+    """Chat With Plugin"""
+
    chat_scene: str = ChatScene.ChatExecution.value()
    plugins_prompt_generator: PluginPromptGenerator
    select_plugin: str = None

    def __init__(self, chat_param: Dict):
+        """Chat Dashboard Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) plugin selector
+        """
        self.plugin_selector = chat_param["select_param"]
        chat_param["chat_mode"] = ChatScene.ChatExecution
        super().__init__(chat_param=chat_param)
--- a/pilot/scene/chat_knowledge/v1/chat.py
+++ b/pilot/scene/chat_knowledge/v1/chat.py
@ -19,10 +19,17 @@ CFG = Config()
 class ChatKnowledge(BaseChat):
    chat_scene: str = ChatScene.ChatKnowledge.value()

-    """Number of results to return from the query"""
+    """KBQA Chat Module"""

    def __init__(self, chat_param: Dict):
-        """ """
+        """Chat Knowledge Module Initialization
+        Args:
+           - chat_param: Dict
+            - chat_session_id: (str) chat session_id
+            - current_user_input: (str) current user input
+            - model_name:(str) llm model name
+            - select_param:(str) space name
+        """
        from pilot.embedding_engine.embedding_engine import EmbeddingEngine
        from pilot.embedding_engine.embedding_factory import EmbeddingFactory

@ -92,7 +99,7 @@ class ChatKnowledge(BaseChat):
        context = [d.page_content for d in docs]
        context = context[: self.max_token]
        relations = list(
-            set([os.path.basename(d.metadata.get("source", "")) for d in docs])
+            set([os.path.basename(str(d.metadata.get("source", ""))) for d in docs])
        )
        input_values = {
            "context": context,
--- a/pilot/server/base.py
+++ b/pilot/server/base.py
@ -21,6 +21,7 @@ def signal_handler(sig, frame):


 def async_db_summary(system_app: SystemApp):
+    """async db schema into vector db"""
    from pilot.summary.db_summary_client import DBSummaryClient

    client = DBSummaryClient(system_app=system_app)
@ -94,6 +95,19 @@ class WebWerverParameters(BaseParameters):
    daemon: Optional[bool] = field(
        default=False, metadata={"help": "Run Webserver in background"}
    )
+    controller_addr: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "The Model controller address to connect. If None, read model controller address from environment key `MODEL_SERVER`."
+        },
+    )
+    model_name: str = field(
+        default=None,
+        metadata={
+            "help": "The default model name to use. If None, read model name from environment key `LLM_MODEL`.",
+            "tags": "fixed",
+        },
+    )
    share: Optional[bool] = field(
        default=False,
        metadata={
@ -122,3 +136,15 @@ class WebWerverParameters(BaseParameters):
        },
    )
    light: Optional[bool] = field(default=False, metadata={"help": "enable light mode"})
+    log_file: Optional[str] = field(
+        default="dbgpt_webserver.log",
+        metadata={
+            "help": "The filename to store log",
+        },
+    )
+    tracer_file: Optional[str] = field(
+        default="dbgpt_webserver_tracer.jsonl",
+        metadata={
+            "help": "The filename to store tracer span records",
+        },
+    )
--- a/pilot/server/dbgpt_server.py
+++ b/pilot/server/dbgpt_server.py
@ -115,6 +115,9 @@ def _get_webserver_params(args: List[str] = None):
 def initialize_app(param: WebWerverParameters = None, args: List[str] = None):
    """Initialize app
    If you use gunicorn as a process manager, initialize_app can be invoke in `on_starting` hook.
+    Args:
+        param:WebWerverParameters
+        args:List[str]
    """
    if not param:
        param = _get_webserver_params(args)
@ -122,7 +125,7 @@ def initialize_app(param: WebWerverParameters = None, args: List[str] = None):
    if not param.log_level:
        param.log_level = _get_logging_level()
    setup_logging(
-        "pilot", logging_level=param.log_level, logger_filename="dbgpt_webserver.log"
+        "pilot", logging_level=param.log_level, logger_filename=param.log_file
    )
    # Before start
    system_app.before_start()
@ -136,14 +139,16 @@ def initialize_app(param: WebWerverParameters = None, args: List[str] = None):
    model_start_listener = _create_model_start_listener(system_app)
    initialize_components(param, system_app, embedding_model_name, embedding_model_path)

-    model_path = LLM_MODEL_CONFIG.get(CFG.LLM_MODEL)
+    model_name = param.model_name or CFG.LLM_MODEL
+
+    model_path = LLM_MODEL_CONFIG.get(model_name)
    if not param.light:
        print("Model Unified Deployment Mode!")
        if not param.remote_embedding:
            embedding_model_name, embedding_model_path = None, None
        initialize_worker_manager_in_client(
            app=app,
-            model_name=CFG.LLM_MODEL,
+            model_name=model_name,
            model_path=model_path,
            local_port=param.port,
            embedding_model_name=embedding_model_name,
@ -155,12 +160,13 @@ def initialize_app(param: WebWerverParameters = None, args: List[str] = None):
        CFG.NEW_SERVER_MODE = True
    else:
        # MODEL_SERVER is controller address now
+        controller_addr = param.controller_addr or CFG.MODEL_SERVER
        initialize_worker_manager_in_client(
            app=app,
-            model_name=CFG.LLM_MODEL,
+            model_name=model_name,
            model_path=model_path,
            run_locally=False,
-            controller_addr=CFG.MODEL_SERVER,
+            controller_addr=controller_addr,
            local_port=param.port,
            start_listener=model_start_listener,
            system_app=system_app,
@ -185,7 +191,7 @@ def run_uvicorn(param: WebWerverParameters):
 def run_webserver(param: WebWerverParameters = None):
    if not param:
        param = _get_webserver_params()
-    initialize_tracer(system_app, os.path.join(LOGDIR, "dbgpt_webserver_tracer.jsonl"))
+    initialize_tracer(system_app, os.path.join(LOGDIR, param.tracer_file))

    with root_tracer.start_span(
        "run_webserver",
--- a/pilot/server/knowledge/chunk_db.py
+++ b/pilot/server/knowledge/chunk_db.py
@ -2,18 +2,20 @@ from datetime import datetime
 from typing import List

 from sqlalchemy import Column, String, DateTime, Integer, Text, func
-from sqlalchemy.orm import declarative_base

+from pilot.base_modules.meta_data.base_dao import BaseDao
+from pilot.base_modules.meta_data.meta_data import Base, engine, session
 from pilot.configs.config import Config
-from pilot.connections.rdbms.base_dao import BaseDao

 CFG = Config()

-Base = declarative_base()
-

 class DocumentChunkEntity(Base):
    __tablename__ = "document_chunk"
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    id = Column(Integer, primary_key=True)
    document_id = Column(Integer)
    doc_name = Column(String(100))
@ -30,11 +32,11 @@ class DocumentChunkEntity(Base):
 class DocumentChunkDao(BaseDao):
    def __init__(self):
        super().__init__(
-            database="knowledge_management", orm_base=Base, create_not_exist_table=True
+            database="dbgpt", orm_base=Base, db_engine=engine, session=session
        )

    def create_documents_chunks(self, documents: List):
-        session = self.Session()
+        session = self.get_session()
        docs = [
            DocumentChunkEntity(
                doc_name=document.doc_name,
@ -52,7 +54,7 @@ class DocumentChunkDao(BaseDao):
        session.close()

    def get_document_chunks(self, query: DocumentChunkEntity, page=1, page_size=20):
-        session = self.Session()
+        session = self.get_session()
        document_chunks = session.query(DocumentChunkEntity)
        if query.id is not None:
            document_chunks = document_chunks.filter(DocumentChunkEntity.id == query.id)
@ -82,7 +84,7 @@ class DocumentChunkDao(BaseDao):
        return result

    def get_document_chunks_count(self, query: DocumentChunkEntity):
-        session = self.Session()
+        session = self.get_session()
        document_chunks = session.query(func.count(DocumentChunkEntity.id))
        if query.id is not None:
            document_chunks = document_chunks.filter(DocumentChunkEntity.id == query.id)
@ -107,13 +109,13 @@ class DocumentChunkDao(BaseDao):
        return count

    # def update_knowledge_document(self, document:KnowledgeDocumentEntity):
-    #     session = self.Session()
+    #     session = self.get_session()
    #     updated_space = session.merge(document)
    #     session.commit()
    #     return updated_space.id

    def delete(self, document_id: int):
-        session = self.Session()
+        session = self.get_session()
        if document_id is None:
            raise Exception("document_id is None")
        query = DocumentChunkEntity(document_id=document_id)
--- a/pilot/server/knowledge/document_db.py
+++ b/pilot/server/knowledge/document_db.py
@ -1,18 +1,20 @@
 from datetime import datetime

 from sqlalchemy import Column, String, DateTime, Integer, Text, func
-from sqlalchemy.orm import declarative_base

+from pilot.base_modules.meta_data.base_dao import BaseDao
+from pilot.base_modules.meta_data.meta_data import Base, engine, session
 from pilot.configs.config import Config
-from pilot.connections.rdbms.base_dao import BaseDao

 CFG = Config()

-Base = declarative_base()
-

 class KnowledgeDocumentEntity(Base):
    __tablename__ = "knowledge_document"
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    id = Column(Integer, primary_key=True)
    doc_name = Column(String(100))
    doc_type = Column(String(100))
@ -26,6 +28,8 @@ class KnowledgeDocumentEntity(Base):
    gmt_created = Column(DateTime)
    gmt_modified = Column(DateTime)

+    __table_args__ = {"mysql_charset": "utf8mb4"}
+
    def __repr__(self):
        return f"KnowledgeDocumentEntity(id={self.id}, doc_name='{self.doc_name}', doc_type='{self.doc_type}', chunk_size='{self.chunk_size}', status='{self.status}', last_sync='{self.last_sync}', content='{self.content}', result='{self.result}', gmt_created='{self.gmt_created}', gmt_modified='{self.gmt_modified}')"

@ -33,11 +37,11 @@ class KnowledgeDocumentEntity(Base):
 class KnowledgeDocumentDao(BaseDao):
    def __init__(self):
        super().__init__(
-            database="knowledge_management", orm_base=Base, create_not_exist_table=True
+            database="dbgpt", orm_base=Base, db_engine=engine, session=session
        )

    def create_knowledge_document(self, document: KnowledgeDocumentEntity):
-        session = self.Session()
+        session = self.get_session()
        knowledge_document = KnowledgeDocumentEntity(
            doc_name=document.doc_name,
            doc_type=document.doc_type,
@ -58,7 +62,7 @@ class KnowledgeDocumentDao(BaseDao):
        return doc_id

    def get_knowledge_documents(self, query, page=1, page_size=20):
-        session = self.Session()
+        session = self.get_session()
        knowledge_documents = session.query(KnowledgeDocumentEntity)
        if query.id is not None:
            knowledge_documents = knowledge_documents.filter(
@ -92,7 +96,7 @@ class KnowledgeDocumentDao(BaseDao):
        return result

    def get_documents(self, query):
-        session = self.Session()
+        session = self.get_session()
        knowledge_documents = session.query(KnowledgeDocumentEntity)
        if query.id is not None:
            knowledge_documents = knowledge_documents.filter(
@ -123,7 +127,7 @@ class KnowledgeDocumentDao(BaseDao):
        return result

    def get_knowledge_documents_count(self, query):
-        session = self.Session()
+        session = self.get_session()
        knowledge_documents = session.query(func.count(KnowledgeDocumentEntity.id))
        if query.id is not None:
            knowledge_documents = knowledge_documents.filter(
@ -150,14 +154,14 @@ class KnowledgeDocumentDao(BaseDao):
        return count

    def update_knowledge_document(self, document: KnowledgeDocumentEntity):
-        session = self.Session()
+        session = self.get_session()
        updated_space = session.merge(document)
        session.commit()
        return updated_space.id

    #
    def delete(self, query: KnowledgeDocumentEntity):
-        session = self.Session()
+        session = self.get_session()
        knowledge_documents = session.query(KnowledgeDocumentEntity)
        if query.id is not None:
            knowledge_documents = knowledge_documents.filter(
--- a/pilot/server/knowledge/service.py
+++ b/pilot/server/knowledge/service.py
@ -57,12 +57,21 @@ class SyncStatus(Enum):

 # @singleton
 class KnowledgeService:
+    """KnowledgeService
+    Knowledge Management Service:
+        -knowledge_space management
+        -knowledge_document management
+        -embedding management
+    """
+
    def __init__(self):
        pass

-    """create knowledge space"""
-
    def create_knowledge_space(self, request: KnowledgeSpaceRequest):
+        """create knowledge space
+        Args:
+           - request: KnowledgeSpaceRequest
+        """
        query = KnowledgeSpaceEntity(
            name=request.name,
        )
@ -72,9 +81,11 @@ class KnowledgeService:
        knowledge_space_dao.create_knowledge_space(request)
        return True

-    """create knowledge document"""
-
    def create_knowledge_document(self, space, request: KnowledgeDocumentRequest):
+        """create knowledge document
+        Args:
+           - request: KnowledgeDocumentRequest
+        """
        query = KnowledgeDocumentEntity(doc_name=request.doc_name, space=space)
        documents = knowledge_document_dao.get_knowledge_documents(query)
        if len(documents) > 0:
@ -91,9 +102,11 @@ class KnowledgeService:
        )
        return knowledge_document_dao.create_knowledge_document(document)

-    """get knowledge space"""
-
    def get_knowledge_space(self, request: KnowledgeSpaceRequest):
+        """get knowledge space
+        Args:
+           - request: KnowledgeSpaceRequest
+        """
        query = KnowledgeSpaceEntity(
            name=request.name, vector_type=request.vector_type, owner=request.owner
        )
@ -116,6 +129,10 @@ class KnowledgeService:
        return responses

    def arguments(self, space_name):
+        """show knowledge space arguments
+        Args:
+            - space_name: Knowledge Space Name
+        """
        query = KnowledgeSpaceEntity(name=space_name)
        spaces = knowledge_space_dao.get_knowledge_space(query)
        if len(spaces) != 1:
@ -128,6 +145,11 @@ class KnowledgeService:
        return json.loads(context)

    def argument_save(self, space_name, argument_request: SpaceArgumentRequest):
+        """save argument
+        Args:
+            - space_name: Knowledge Space Name
+            - argument_request: SpaceArgumentRequest
+        """
        query = KnowledgeSpaceEntity(name=space_name)
        spaces = knowledge_space_dao.get_knowledge_space(query)
        if len(spaces) != 1:
@ -136,9 +158,12 @@ class KnowledgeService:
        space.context = argument_request.argument
        return knowledge_space_dao.update_knowledge_space(space)

-    """get knowledge get_knowledge_documents"""
-
    def get_knowledge_documents(self, space, request: DocumentQueryRequest):
+        """get knowledge documents
+        Args:
+            - space: Knowledge Space Name
+            - request: DocumentQueryRequest
+        """
        query = KnowledgeDocumentEntity(
            doc_name=request.doc_name,
            doc_type=request.doc_type,
@ -153,9 +178,12 @@ class KnowledgeService:
        res.page = request.page
        return res

-    """sync knowledge document chunk into vector store"""
-
    def sync_knowledge_document(self, space_name, sync_request: DocumentSyncRequest):
+        """sync knowledge document chunk into vector store
+        Args:
+            - space: Knowledge Space Name
+            - sync_request: DocumentSyncRequest
+        """
        from pilot.embedding_engine.embedding_engine import EmbeddingEngine
        from pilot.embedding_engine.embedding_factory import EmbeddingFactory
        from pilot.embedding_engine.pre_text_splitter import PreTextSplitter
@ -249,11 +277,6 @@ class KnowledgeService:
            doc.chunk_size = len(chunk_docs)
            doc.gmt_modified = datetime.now()
            knowledge_document_dao.update_knowledge_document(doc)
-            # async doc embeddings
-            # thread = threading.Thread(
-            #     target=self.async_doc_embedding, args=(client, chunk_docs, doc)
-            # )
-            # thread.start()
            executor = CFG.SYSTEM_APP.get_component(
                ComponentType.EXECUTOR_DEFAULT, ExecutorFactory
            ).create()
@ -277,16 +300,21 @@ class KnowledgeService:

        return True

-    """update knowledge space"""
-
    def update_knowledge_space(
        self, space_id: int, space_request: KnowledgeSpaceRequest
    ):
+        """update knowledge space
+        Args:
+            - space_id: space id
+            - space_request: KnowledgeSpaceRequest
+        """
        knowledge_space_dao.update_knowledge_space(space_id, space_request)

-    """delete knowledge space"""
-
    def delete_space(self, space_name: str):
+        """delete knowledge space
+        Args:
+            - space_name: knowledge space name
+        """
        query = KnowledgeSpaceEntity(name=space_name)
        spaces = knowledge_space_dao.get_knowledge_space(query)
        if len(spaces) == 0:
@ -312,6 +340,11 @@ class KnowledgeService:
        return knowledge_space_dao.delete_knowledge_space(space)

    def delete_document(self, space_name: str, doc_name: str):
+        """delete document
+        Args:
+            - space_name: knowledge space name
+            - doc_name: doocument name
+        """
        document_query = KnowledgeDocumentEntity(doc_name=doc_name, space=space_name)
        documents = knowledge_document_dao.get_documents(document_query)
        if len(documents) != 1:
@ -332,9 +365,11 @@ class KnowledgeService:
        # delete document
        return knowledge_document_dao.delete(document_query)

-    """get document chunks"""
-
    def get_document_chunks(self, request: ChunkQueryRequest):
+        """get document chunks
+        Args:
+            - request: ChunkQueryRequest
+        """
        query = DocumentChunkEntity(
            id=request.id,
            document_id=request.document_id,
@ -350,6 +385,12 @@ class KnowledgeService:
        return res

    def async_doc_embedding(self, client, chunk_docs, doc):
+        """async document embedding into vector db
+        Args:
+            - client: EmbeddingEngine Client
+            - chunk_docs: List[Document]
+            - doc: doc
+        """
        logger.info(
            f"async_doc_embedding, doc:{doc.doc_name}, chunk_size:{len(chunk_docs)}, begin embedding to vector store-{CFG.VECTOR_STORE_TYPE}"
        )
@ -391,6 +432,10 @@ class KnowledgeService:
        return context_template_string

    def get_space_context(self, space_name):
+        """get space contect
+        Args:
+           - space_name: space name
+        """
        request = KnowledgeSpaceRequest()
        request.name = space_name
        spaces = self.get_knowledge_space(request)
--- a/pilot/server/knowledge/space_db.py
+++ b/pilot/server/knowledge/space_db.py
@ -1,18 +1,21 @@
 from datetime import datetime

 from sqlalchemy import Column, Integer, Text, String, DateTime
-from sqlalchemy.ext.declarative import declarative_base

+from pilot.base_modules.meta_data.base_dao import BaseDao
+from pilot.base_modules.meta_data.meta_data import Base, engine, session
 from pilot.configs.config import Config
 from pilot.server.knowledge.request.request import KnowledgeSpaceRequest
-from pilot.connections.rdbms.base_dao import BaseDao

 CFG = Config()
-Base = declarative_base()


 class KnowledgeSpaceEntity(Base):
    __tablename__ = "knowledge_space"
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    id = Column(Integer, primary_key=True)
    name = Column(String(100))
    vector_type = Column(String(100))
@ -29,11 +32,11 @@ class KnowledgeSpaceEntity(Base):
 class KnowledgeSpaceDao(BaseDao):
    def __init__(self):
        super().__init__(
-            database="knowledge_management", orm_base=Base, create_not_exist_table=True
+            database="dbgpt", orm_base=Base, db_engine=engine, session=session
        )

    def create_knowledge_space(self, space: KnowledgeSpaceRequest):
-        session = self.Session()
+        session = self.get_session()
        knowledge_space = KnowledgeSpaceEntity(
            name=space.name,
            vector_type=CFG.VECTOR_STORE_TYPE,
@ -47,7 +50,7 @@ class KnowledgeSpaceDao(BaseDao):
        session.close()

    def get_knowledge_space(self, query: KnowledgeSpaceEntity):
-        session = self.Session()
+        session = self.get_session()
        knowledge_spaces = session.query(KnowledgeSpaceEntity)
        if query.id is not None:
            knowledge_spaces = knowledge_spaces.filter(
@ -86,14 +89,14 @@ class KnowledgeSpaceDao(BaseDao):
        return result

    def update_knowledge_space(self, space: KnowledgeSpaceEntity):
-        session = self.Session()
+        session = self.get_session()
        session.merge(space)
        session.commit()
        session.close()
        return True

    def delete_knowledge_space(self, space: KnowledgeSpaceEntity):
-        session = self.Session()
+        session = self.get_session()
        if space:
            session.delete(space)
            session.commit()
--- a/pilot/server/llmserver.py
+++ b/pilot/server/llmserver.py
@ -16,6 +16,9 @@ CFG = Config()
 model_path = LLM_MODEL_CONFIG.get(CFG.LLM_MODEL)

 if __name__ == "__main__":
+    """run llm server including controller, manager worker
+    If you use gunicorn as a process manager, initialize_app can be invoke in `on_starting` hook.
+    """
    run_worker_manager(
        model_name=CFG.LLM_MODEL,
        model_path=model_path,
--- a/pilot/server/prompt/prompt_manage_db.py
+++ b/pilot/server/prompt/prompt_manage_db.py
@ -1,19 +1,22 @@
 from datetime import datetime

 from sqlalchemy import Column, Integer, Text, String, DateTime
-from sqlalchemy.ext.declarative import declarative_base

+from pilot.base_modules.meta_data.base_dao import BaseDao
+from pilot.base_modules.meta_data.meta_data import Base, engine, session
 from pilot.configs.config import Config
-from pilot.connections.rdbms.base_dao import BaseDao

 from pilot.server.prompt.request.request import PromptManageRequest

 CFG = Config()
-Base = declarative_base()


 class PromptManageEntity(Base):
    __tablename__ = "prompt_manage"
+    __table_args__ = {
+        "mysql_charset": "utf8mb4",
+        "mysql_collate": "utf8mb4_unicode_ci",
+    }
    id = Column(Integer, primary_key=True)
    chat_scene = Column(String(100))
    sub_chat_scene = Column(String(100))
@ -31,11 +34,11 @@ class PromptManageEntity(Base):
 class PromptManageDao(BaseDao):
    def __init__(self):
        super().__init__(
-            database="prompt_management", orm_base=Base, create_not_exist_table=True
+            database="dbgpt", orm_base=Base, db_engine=engine, session=session
        )

    def create_prompt(self, prompt: PromptManageRequest):
-        session = self.Session()
+        session = self.get_session()
        prompt_manage = PromptManageEntity(
            chat_scene=prompt.chat_scene,
            sub_chat_scene=prompt.sub_chat_scene,
@ -51,7 +54,7 @@ class PromptManageDao(BaseDao):
        session.close()

    def get_prompts(self, query: PromptManageEntity):
-        session = self.Session()
+        session = self.get_session()
        prompts = session.query(PromptManageEntity)
        if query.chat_scene is not None:
            prompts = prompts.filter(PromptManageEntity.chat_scene == query.chat_scene)
@ -78,13 +81,13 @@ class PromptManageDao(BaseDao):
        return result

    def update_prompt(self, prompt: PromptManageEntity):
-        session = self.Session()
+        session = self.get_session()
        session.merge(prompt)
        session.commit()
        session.close()

    def delete_prompt(self, prompt: PromptManageEntity):
-        session = self.Session()
+        session = self.get_session()
        if prompt:
            session.delete(prompt)
            session.commit()
--- a/pilot/utils/tracer/span_storage.py
+++ b/pilot/utils/tracer/span_storage.py
@ -1,6 +1,7 @@
 import os
 import json
 import time
+import datetime
 import threading
 import queue
 import logging
@ -27,6 +28,13 @@ class FileSpanStorage(SpanStorage):
    def __init__(self, filename: str, batch_size=10, flush_interval=10):
        super().__init__()
        self.filename = filename
+        # Split filename into prefix and suffix
+        self.filename_prefix, self.filename_suffix = os.path.splitext(filename)
+        if not self.filename_suffix:
+            self.filename_suffix = ".log"
+        self.last_date = (
+            datetime.datetime.now().date()
+        )  # Store the current date for checking date changes
        self.queue = queue.Queue()
        self.batch_size = batch_size
        self.flush_interval = flush_interval
@ -52,7 +60,21 @@ class FileSpanStorage(SpanStorage):
            except queue.Full:
                pass  # If the signal queue is full, it's okay. The flush thread will handle it.

+    def _get_dated_filename(self, date: datetime.date) -> str:
+        """Return the filename based on a specific date."""
+        date_str = date.strftime("%Y-%m-%d")
+        return f"{self.filename_prefix}_{date_str}{self.filename_suffix}"
+
+    def _roll_over_if_needed(self):
+        """Checks if a day has changed since the last write, and if so, renames the current file."""
+        current_date = datetime.datetime.now().date()
+        if current_date != self.last_date:
+            if os.path.exists(self.filename):
+                os.rename(self.filename, self._get_dated_filename(self.last_date))
+            self.last_date = current_date
+
    def _write_to_file(self):
+        self._roll_over_if_needed()
        spans_to_write = []
        while not self.queue.empty():
            spans_to_write.append(self.queue.get())
--- a/pilot/utils/tracer/tests/test_span_storage.py
+++ b/pilot/utils/tracer/tests/test_span_storage.py
@ -4,6 +4,8 @@ import asyncio
 import json
 import tempfile
 import time
+from unittest.mock import patch
+from datetime import datetime, timedelta

 from pilot.utils.tracer import SpanStorage, FileSpanStorage, Span, SpanType

@ -122,3 +124,46 @@ def test_non_existent_file(storage: SpanStorage):
    assert len(spans_in_file) == 2
    assert spans_in_file[0]["trace_id"] == "1"
    assert spans_in_file[1]["trace_id"] == "2"
+
+
+@pytest.mark.parametrize(
+    "storage", [{"batch_size": 1, "file_does_not_exist": True}], indirect=True
+)
+def test_log_rollover(storage: SpanStorage):
+    # mock start date
+    mock_start_date = datetime(2023, 10, 18, 23, 59)
+
+    with patch("datetime.datetime") as mock_datetime:
+        mock_datetime.now.return_value = mock_start_date
+
+        span1 = Span("1", "a", SpanType.BASE, "b", "op1")
+        storage.append_span(span1)
+        time.sleep(0.1)
+
+        # mock new day
+        mock_datetime.now.return_value = mock_start_date + timedelta(minutes=1)
+
+        span2 = Span("2", "c", SpanType.BASE, "d", "op2")
+        storage.append_span(span2)
+        time.sleep(0.1)
+
+    # origin filename need exists
+    assert os.path.exists(storage.filename)
+
+    # get roll over filename
+    dated_filename = os.path.join(
+        os.path.dirname(storage.filename),
+        f"{os.path.basename(storage.filename).split('.')[0]}_2023-10-18.jsonl",
+    )
+
+    assert os.path.exists(dated_filename)
+
+    # check origin filename just include the second span
+    spans_in_original_file = read_spans_from_file(storage.filename)
+    assert len(spans_in_original_file) == 1
+    assert spans_in_original_file[0]["trace_id"] == "2"
+
+    # check the roll over filename just include the first span
+    spans_in_dated_file = read_spans_from_file(dated_filename)
+    assert len(spans_in_dated_file) == 1
+    assert spans_in_dated_file[0]["trace_id"] == "1"
--- a/pilot/vector_store/connector.py
+++ b/pilot/vector_store/connector.py
@ -14,7 +14,11 @@ class VectorStoreConnector:
    """

    def __init__(self, vector_store_type, ctx: {}) -> None:
-        """initialize vector store connector."""
+        """initialize vector store connector.
+        Args:
+            - vector_store_type: vector store type Milvus, Chroma, Weaviate
+            - ctx: vector store config params.
+        """
        self.ctx = ctx
        self._register()

@ -30,20 +34,30 @@ class VectorStoreConnector:
        """load document in vector database."""
        return self.client.load_document(docs)

-    def similar_search(self, docs, topk):
-        """similar search in vector database."""
-        return self.client.similar_search(docs, topk)
+    def similar_search(self, doc: str, topk: int):
+        """similar search in vector database.
+        Args:
+           - doc: query text
+           - topk: topk
+        """
+        return self.client.similar_search(doc, topk)

    def vector_name_exists(self):
        """is vector store name exist."""
        return self.client.vector_name_exists()

    def delete_vector_name(self, vector_name):
-        """vector store delete"""
+        """vector store delete
+        Args:
+            - vector_name: vector store name
+        """
        return self.client.delete_vector_name(vector_name)

    def delete_by_ids(self, ids):
-        """vector store delete by ids."""
+        """vector store delete by ids.
+        Args:
+            - ids: vector ids
+        """
        return self.client.delete_by_ids(ids=ids)

    def _match(self, vector_store_type) -> bool: