diff --git a/assets/chat_dashboard/chat_dashboard_1.png b/assets/chat_dashboard/chat_dashboard_1.png
new file mode 100644
index 000000000..d5c45fdee
Binary files /dev/null and b/assets/chat_dashboard/chat_dashboard_1.png differ
diff --git a/assets/chat_dashboard/chat_dashboard_2.png b/assets/chat_dashboard/chat_dashboard_2.png
new file mode 100644
index 000000000..e8b6bf817
Binary files /dev/null and b/assets/chat_dashboard/chat_dashboard_2.png differ
diff --git a/assets/chat_excel/chat_excel_1.png b/assets/chat_excel/chat_excel_1.png
new file mode 100644
index 000000000..156249ef8
Binary files /dev/null and b/assets/chat_excel/chat_excel_1.png differ
diff --git a/assets/chat_excel/chat_excel_2.png b/assets/chat_excel/chat_excel_2.png
new file mode 100644
index 000000000..20559d7ef
Binary files /dev/null and b/assets/chat_excel/chat_excel_2.png differ
diff --git a/assets/chat_excel/chat_excel_3.png b/assets/chat_excel/chat_excel_3.png
new file mode 100644
index 000000000..c2e0cdf6f
Binary files /dev/null and b/assets/chat_excel/chat_excel_3.png differ
diff --git a/assets/chat_excel/chat_excel_4.png b/assets/chat_excel/chat_excel_4.png
new file mode 100644
index 000000000..0ce346022
Binary files /dev/null and b/assets/chat_excel/chat_excel_4.png differ
diff --git a/assets/chat_excel/chat_excel_5.png b/assets/chat_excel/chat_excel_5.png
new file mode 100644
index 000000000..da5c2bb0b
Binary files /dev/null and b/assets/chat_excel/chat_excel_5.png differ
diff --git a/assets/chat_excel/chat_excel_6.png b/assets/chat_excel/chat_excel_6.png
new file mode 100644
index 000000000..e2f53da13
Binary files /dev/null and b/assets/chat_excel/chat_excel_6.png differ
diff --git a/assets/chat_excel/chat_excel_7.png b/assets/chat_excel/chat_excel_7.png
new file mode 100644
index 000000000..9e0268541
Binary files /dev/null and b/assets/chat_excel/chat_excel_7.png differ
diff --git a/docs/getting_started/application.rst b/docs/getting_started/application.rst
index 747a01b08..641b86f36 100644
--- a/docs/getting_started/application.rst
+++ b/docs/getting_started/application.rst
@@ -18,4 +18,5 @@ DB-GPT product is a Web application that you can chat database, chat knowledge,
 
    ./application/chatdb/chatdb.md
    ./application/kbqa/kbqa.md
-   ./application/dashboard/dashboard.md
\ No newline at end of file
+   ./application/dashboard/dashboard.md
+   ./application/chatexcel/chatexcel.md
\ No newline at end of file
diff --git a/docs/getting_started/application/chatexcel/chatexcel.md b/docs/getting_started/application/chatexcel/chatexcel.md
new file mode 100644
index 000000000..bdd67991c
--- /dev/null
+++ b/docs/getting_started/application/chatexcel/chatexcel.md
@@ -0,0 +1,27 @@
+ChatExcel
+==================================
+![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/4113ac15-83c2-4350-86c0-5fc795677abd)
+ChatExcel uses natural language to analyze and query Excel data.![db plugins demonstration](../../../../assets/chat_excel/chat_excel_1.png)
+
+### 1.Select And Upload Excel or CSV File
+Select your excel or csv file to upload and start the conversation.
+```{tip}
+ChatExcel 
+
+The ChatExcel function supports Excel and CSV format files, select the corresponding file to use.
+```
+![db plugins demonstration](../../../../assets/chat_excel/chat_excel_2.png)
+![db plugins demonstration](../../../../assets/chat_excel/chat_excel_3.png)
+
+### 2.Wait for Data Processing
+After the data is uploaded, it will first learn and process the data structure and field meaning.
+![db plugins demonstration](../../../../assets/chat_excel/chat_excel_4.png)
+
+### 3.Use Data Analysis Calculation
+Now you can use natural language to analyze and query data in the dialog box.
+![db plugins demonstration](../../../../assets/chat_excel/chat_excel_5.png)
+![db plugins demonstration](../../../../assets/chat_excel/chat_excel_6.png)
+![db plugins demonstration](../../../../assets/chat_excel/chat_excel_7.png)
+
+
+
diff --git a/docs/getting_started/application/dashboard/dashboard.md b/docs/getting_started/application/dashboard/dashboard.md
index 4e9fee8d8..5cab32581 100644
--- a/docs/getting_started/application/dashboard/dashboard.md
+++ b/docs/getting_started/application/dashboard/dashboard.md
@@ -29,9 +29,8 @@ data in pilot/mock_datas/, you should follow the steps.
 #### 4.Input your analysis goals
 
 ![document](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/3f427350-5bd5-4675-8f89-1bd5c63ff2c6)
-![document](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/3d14a2da-165e-4b2f-a921-325c20fe5ae9)
+![db plugins demonstration](../../../../assets/chat_dashboard/chat_dashboard_1.png)
 
 #### 5.Adjust and modify your report
-
-![upload](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/cb802b94-041b-44b4-b6ec-891bf8da52a4)
+![db plugins demonstration](../../../../assets/chat_dashboard/chat_dashboard_2.png)
 
diff --git a/docs/getting_started/application/kbqa/kbqa.md b/docs/getting_started/application/kbqa/kbqa.md
index 2b6b6cfcc..f048b10f4 100644
--- a/docs/getting_started/application/kbqa/kbqa.md
+++ b/docs/getting_started/application/kbqa/kbqa.md
@@ -1,5 +1,7 @@
 KBQA
 ==================================
+![chat_knowledge](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/bc343c94-df3e-41e5-90d5-23b68c768c59)
+
 DB-GPT supports a knowledge question-answering module, which aims to create an intelligent expert in the field of databases and provide professional knowledge-based answers to database practitioners.
 
 ![chat_knowledge](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/6e55f2e5-94f7-4906-aed6-097db5c6c721)
diff --git a/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/chatexcel/chatexcel.po b/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/chatexcel/chatexcel.po
new file mode 100644
index 000000000..47f93237c
--- /dev/null
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/chatexcel/chatexcel.po
@@ -0,0 +1,102 @@
+# 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 👏👏 0.3.6\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2023-08-29 21:14+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/chatexcel/chatexcel.md:1
+#: ../../getting_started/application/chatexcel/chatexcel.md:9
+#: 6efcbf4652954b27beb55f600cfe75c7 eefb0c3bc131439fb2dd4045761f1ae9
+msgid "ChatExcel"
+msgstr ""
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:3
+#: 5fc4ddd2690f46658df1e09c601d81ad
+#, fuzzy
+msgid ""
+"![db plugins demonstration](https://github.com/eosphoros-ai/DB-"
+"GPT/assets/13723926/4113ac15-83c2-4350-86c0-5fc795677abd) ChatExcel uses "
+"natural language to analyze and query Excel data.![db plugins "
+"demonstration](../../../../assets/chat_excel/chat_excel_1.png)"
+msgstr "使用自然语言进行Excel数据的分析处理"
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:3
+#: ../../getting_started/application/chatexcel/chatexcel.md:13
+#: ../../getting_started/application/chatexcel/chatexcel.md:17
+#: ../../getting_started/application/chatexcel/chatexcel.md:21
+#: 4c91baf5f0b244abb021f461851674cc 4eead9a4f81e4855a5c362774696999c
+#: 5f309a06170946108ae70806dff157ea 790016c9c68f4a29a84b7ef8e14d6dc2
+#: 93db1eb6af69452982f6028eff626a57 e758c8b320894e2b93f8db78459b7a1f
+#: ea3c99f7eafc4ae0a19706a47e4c7bf6 f18d2b88de244173ab2673f2a5e828c0
+msgid "db plugins demonstration"
+msgstr ""
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:6
+#: 45f137031025409ba2ada9c8f7c5f1e4
+msgid "1.Select And Upload Excel or CSV File"
+msgstr ""
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:7
+#: cd282be2b4ef49ea8b0eaa3d53042f22
+msgid "Select your excel or csv file to upload and start the conversation."
+msgstr "选择你的Excel或者CSV文件上传开始对话"
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:11
+#: a5ebc8643eff4b44a951b28d85488143
+msgid ""
+"The ChatExcel function supports Excel and CSV format files, select the "
+"corresponding file to use."
+msgstr "ChatExcel功能支持Excel和CSV格式的文件，选择对应格式的文件开始使用"
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:13
+#: d52927be09654c8daf29e2ef0c60a671
+msgid ""
+"![db plugins "
+"demonstration](../../../../assets/chat_excel/chat_excel_2.png) ![db "
+"plugins demonstration](../../../../assets/chat_excel/chat_excel_3.png)"
+msgstr ""
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:16
+#: d86202165fdc4da6be06024b45f9af55
+msgid "2.Wait for Data Processing"
+msgstr "等待数据处理"
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:17
+#: 3de7205fbdc741e2b79996d67264c058
+msgid ""
+"After the data is uploaded, it will first learn and process the data "
+"structure and field meaning. ![db plugins "
+"demonstration](../../../../assets/chat_excel/chat_excel_4.png)"
+msgstr "等待数据上传完成，会自动进行数据结构的学习和处理"
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:20
+#: fb0620dec5a24b469ceccf86e918fe54
+msgid "3.Use Data Analysis Calculation"
+msgstr "开始使用数据分析计算"
+
+#: ../../getting_started/application/chatexcel/chatexcel.md:21
+#: 221733f01fe04e38b19f191d4001c7a7
+msgid ""
+"Now you can use natural language to analyze and query data in the dialog "
+"box. ![db plugins "
+"demonstration](../../../../assets/chat_excel/chat_excel_5.png) ![db "
+"plugins demonstration](../../../../assets/chat_excel/chat_excel_6.png) "
+"![db plugins "
+"demonstration](../../../../assets/chat_excel/chat_excel_7.png)"
+msgstr "现在可以开始进行自然语言进行数据的分析查询对话了"
+
diff --git a/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/dashboard/dashboard.po b/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/dashboard/dashboard.po
index 5b94c4b09..32686d68c 100644
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/dashboard/dashboard.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/dashboard/dashboard.po
@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-08-22 13:28+0800\n"
+"POT-Creation-Date: 2023-08-29 20:50+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/application/dashboard/dashboard.md:1
-#: 8017757596ff4c7faa06f7e7d18902ca
+#: 2a1224e675d144269e5cc3695d4d60b4
 msgid "Dashboard"
 msgstr "Dashboard"
 
 #: ../../getting_started/application/dashboard/dashboard.md:3
-#: 5b84a61923404d8c81d5a1430b3fa12c
+#: 2b6d2f94f73d43e68806bf4c6d0d9269
 msgid ""
 "The purpose of the DB-GPT Dashboard is to empower data analysts with "
 "efficiency. DB-GPT provides intelligent reporting technology, allowing "
@@ -34,37 +34,37 @@ msgid ""
 msgstr "DB-GPT Dashboard目的是赋能数据分析人员。DB-GPT通过提供智能报表技术，使得业务分析人员可以直接使用简单的自然语言进行自助分析。"
 
 #: ../../getting_started/application/dashboard/dashboard.md:8
-#: 48604cca2b3f482692bb65a01f0297a7
+#: 9612fa76c4264bab8e629ac50959faa9
 msgid "Dashboard now support Datasource Type"
 msgstr "Dashboard目前支持的数据源类型"
 
 #: ../../getting_started/application/dashboard/dashboard.md:9
-#: e4371bc220be46f0833dc7d0c804f263
+#: bb0b15742ebe41628fb0d1fc38caabe2
 msgid "Mysql"
 msgstr "Mysql"
 
 #: ../../getting_started/application/dashboard/dashboard.md:10
-#: 719c578796fa44a3ad062289aa4650d7
+#: 35491581125b4bdd8422f35b11c7bc2c
 msgid "Sqlite"
 msgstr "Sqlite"
 
 #: ../../getting_started/application/dashboard/dashboard.md:11
-#: c7817904bbf34dfca56a19a004937146
+#: 8c4389354e0344aa9a781bdfc94c2cac
 msgid "DuckDB"
 msgstr "DuckDB"
 
 #: ../../getting_started/application/dashboard/dashboard.md:13
-#: 1cebeafe853d43809e6ced45d2b68812
+#: 18e8c60f5c2f4aa698cec1e8e8b354c8
 msgid "Steps to Dashboard In DB-GPT"
 msgstr "Dashboard使用步骤"
 
 #: ../../getting_started/application/dashboard/dashboard.md:15
-#: 977520bbea44423ea290617712482148
+#: 94f98e0f5c2e451ba29b9b77c4139ed9
 msgid "1 add datasource"
 msgstr "1.添加数据源"
 
 #: ../../getting_started/application/dashboard/dashboard.md:17
-#: a8fcef153c68498fa9886051e8d7b072
+#: 34e1211e65b940c3beb6234bcfa423a1
 #, fuzzy
 msgid ""
 "If you are using Dashboard for the first time, you need to mock some data"
@@ -75,17 +75,17 @@ msgid ""
 msgstr "如果你是第一次使用Dashboard，需要构造测试数据，DB-GPT在pilot/mock_datas/提供了测试数据，只需要将数据源进行添加即可"
 
 #: ../../getting_started/application/dashboard/dashboard.md:17
-#: 1abcaa9d7fad4b53a0622ab3e982e6d5
+#: f29905929b32442ba05833b6c52a11be
 msgid "add_datasource"
 msgstr "添加数据源"
 
 #: ../../getting_started/application/dashboard/dashboard.md:21
-#: 21ebb5bf568741a9b3d7a4275dde69fa
+#: 367a487dd1d54681a6e83d8fdda5b793
 msgid "2.Choose Dashboard Mode"
 msgstr "2.进入Dashboard"
 
 #: ../../getting_started/application/dashboard/dashboard.md:23
-#: 1b55d97634b44543acf8f367f77d8436
+#: 1ee1e980934e4a618591b7c43921c304
 msgid ""
 "![create_space](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/5e888880-0e97-4b60-8e5c-b7e7224197f0)"
@@ -94,17 +94,17 @@ msgstr ""
 "GPT/assets/13723926/5e888880-0e97-4b60-8e5c-b7e7224197f0)"
 
 #: ../../getting_started/application/dashboard/dashboard.md:23
-#: 6c97d2aa26fa401cb3c4172bfe4aea6a
+#: 12c756afdad740a9afc9cb46cc834af8
 msgid "create_space"
 msgstr "create_space"
 
 #: ../../getting_started/application/dashboard/dashboard.md:25
-#: ff8e96f78698428a9a578b4f90e0feb4
+#: 5a575b17408c42fbacd32d8ff792d5a8
 msgid "3.Select Datasource"
 msgstr "3.选择数据源"
 
 #: ../../getting_started/application/dashboard/dashboard.md:27
-#: 277c924a6f2b49f98414cde95310384f
+#: ae051f852a5a4044a147c853cc3fba60
 msgid ""
 "![document](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/da2ac8b5-eca4-48ef-938f-f9dc1ca711b3)"
@@ -114,45 +114,53 @@ msgstr ""
 
 #: ../../getting_started/application/dashboard/dashboard.md:27
 #: ../../getting_started/application/dashboard/dashboard.md:31
-#: 33164f10fb38452fbf98be5aabaeeb91 3a46cb4427cf4ba386230dff47cf7647
-#: d0093988bb414c41a93e8ad6f88e8404
+#: 94907bb0dc694bc3a4d2ee57a84b8242 ecc0666385904fce8bb1000735482f65
 msgid "document"
 msgstr "document"
 
 #: ../../getting_started/application/dashboard/dashboard.md:29
-#: 6a57e48482724d23adf51e888d126562
+#: c8697e93661c48b19674e63094ba7486
 msgid "4.Input your analysis goals"
 msgstr "4.输入分析目标"
 
 #: ../../getting_started/application/dashboard/dashboard.md:31
-#: cb96df3f9135450fbf71177978c50141
+#: 473fc0d00ab54ee6bc5c21e017591cc4
+#, fuzzy
 msgid ""
 "![document](https://github.com/eosphoros-ai/DB-"
-"GPT/assets/13723926/3f427350-5bd5-4675-8f89-1bd5c63ff2c6) "
-"![document](https://github.com/eosphoros-ai/DB-GPT/assets/13723926"
-"/3d14a2da-165e-4b2f-a921-325c20fe5ae9)"
+"GPT/assets/13723926/3f427350-5bd5-4675-8f89-1bd5c63ff2c6) ![db plugins "
+"demonstration](../../../../assets/chat_dashboard/chat_dashboard_1.png)"
 msgstr ""
 "![document](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/3f427350-5bd5-4675-8f89-1bd5c63ff2c6) "
 "![document](https://github.com/eosphoros-ai/DB-GPT/assets/13723926"
 "/3d14a2da-165e-4b2f-a921-325c20fe5ae9)"
 
+#: ../../getting_started/application/dashboard/dashboard.md:31
+#: ../../getting_started/application/dashboard/dashboard.md:35
+#: 00597e1268544d97a3de368b04d5dcf8 350d04e4b7204823b7a03c0a7606c951
+msgid "db plugins demonstration"
+msgstr ""
+
 #: ../../getting_started/application/dashboard/dashboard.md:34
-#: ed0f008525334a36a900b82339591095
+#: b48cc911c1614def9e4738d35e8b754c
 msgid "5.Adjust and modify your report"
 msgstr "5.调整"
 
-#: ../../getting_started/application/dashboard/dashboard.md:36
-#: 8fc26117a2e1484b9452cfaf8c7f208b
+#: ../../getting_started/application/dashboard/dashboard.md:35
+#: b0442bbc0f6c4c33914814ac92fc4b13
 msgid ""
-"![upload](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/cb802b94"
-"-041b-44b4-b6ec-891bf8da52a4)"
+"![db plugins "
+"demonstration](../../../../assets/chat_dashboard/chat_dashboard_2.png)"
 msgstr ""
-"![upload](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/cb802b94"
-"-041b-44b4-b6ec-891bf8da52a4)"
 
-#: ../../getting_started/application/dashboard/dashboard.md:36
-#: 6d12166c3c574651a854534cc8c7e997
-msgid "upload"
-msgstr "upload"
+#~ msgid ""
+#~ "![upload](https://github.com/eosphoros-ai/DB-"
+#~ "GPT/assets/13723926/cb802b94-041b-44b4-b6ec-891bf8da52a4)"
+#~ msgstr ""
+#~ "![upload](https://github.com/eosphoros-ai/DB-"
+#~ "GPT/assets/13723926/cb802b94-041b-44b4-b6ec-891bf8da52a4)"
+
+#~ msgid "upload"
+#~ msgstr "upload"
 
diff --git a/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/kbqa/kbqa.po b/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/kbqa/kbqa.po
index d33fe192a..9c23f670b 100644
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/kbqa/kbqa.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/application/kbqa/kbqa.po
@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-08-29 20:30+0800\n"
+"POT-Creation-Date: 2023-08-29 21:14+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -20,109 +20,117 @@ msgstr ""
 "Generated-By: Babel 2.12.1\n"
 
 #: ../../getting_started/application/kbqa/kbqa.md:1
-#: 1a06a61cf9d042d780ec19d9385594e9
+#: 4b44ec7d6b3b492489b84bab4471fe46
 msgid "KBQA"
 msgstr ""
 
 #: ../../getting_started/application/kbqa/kbqa.md:3
-#: 96d298acd0de48b3ae06134bc2bbc214
+#: c4217f8786e24f5190354d129b21dff5
+msgid ""
+"![chat_knowledge](https://github.com/eosphoros-ai/DB-"
+"GPT/assets/13723926/bc343c94-df3e-41e5-90d5-23b68c768c59)"
+msgstr ""
+
+#: ../../getting_started/application/kbqa/kbqa.md:3
+#: ../../getting_started/application/kbqa/kbqa.md:7
+#: 2f02ab2494b54fff87e7d1e310f38119 dc0349e48d5e4d89b1f9f353813c9f06
+msgid "chat_knowledge"
+msgstr "chat_knowledge"
+
+#: ../../getting_started/application/kbqa/kbqa.md:5
+#: 149c4c9e15004aaf992c5896deb9e541
 msgid ""
 "DB-GPT supports a knowledge question-answering module, which aims to "
 "create an intelligent expert in the field of databases and provide "
 "professional knowledge-based answers to database practitioners."
 msgstr " DB-GPT支持知识问答模块，知识问答的初衷是打造DB领域的智能专家，为数据库从业人员解决专业的知识问题回答"
 
-#: ../../getting_started/application/kbqa/kbqa.md:5
-#: d1ea2c61f0c34ba294af01c4e7f5a57e
+#: ../../getting_started/application/kbqa/kbqa.md:7
+#: c7e103a20a2e4989aab8a750cdc4dbf4
 msgid ""
 "![chat_knowledge](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/6e55f2e5-94f7-4906-aed6-097db5c6c721)"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:5
-#: ef5384441b5a40dc92613dc6e2574406
-msgid "chat_knowledge"
-msgstr "chat_knowledge"
-
-#: ../../getting_started/application/kbqa/kbqa.md:7
-#: ../../getting_started/application/kbqa/kbqa.md:10
-#: 4959ed3310614273bf1f092119bd556d d6592a16245b49fb89daee4864c1c448
+#: ../../getting_started/application/kbqa/kbqa.md:9
+#: ../../getting_started/application/kbqa/kbqa.md:12
+#: 3ddf012fb6d74eb1be1a0fd0ada9ddf6 e29bffef26fb44ac978d6cbe6584f48f
 msgid "KBQA abilities"
 msgstr "KBQA现有能力"
 
-#: ../../getting_started/application/kbqa/kbqa.md:11
-#: b476c161c24f472395ec4c97bc769f4d
+#: ../../getting_started/application/kbqa/kbqa.md:13
+#: 87cf02966b574d6db8baf0839b13e1e7
 msgid "Knowledge Space."
 msgstr "知识空间"
 
-#: ../../getting_started/application/kbqa/kbqa.md:12
-#: 7f85e2cda7a2424db23ba57c7dab9595
+#: ../../getting_started/application/kbqa/kbqa.md:14
+#: 2777488125234408aa7156a69fcfacef
 msgid "Multi Source Knowledge Source Embedding."
 msgstr "多数据源Embedding"
 
-#: ../../getting_started/application/kbqa/kbqa.md:13
-#: 33f69a1bf9fb463c99cb5d5d20ec73d1
+#: ../../getting_started/application/kbqa/kbqa.md:15
+#: c50f2de4ea6f4aedb7d4fd674ee3f6f7
 msgid "Embedding Argument Adjust"
 msgstr "Embedding参数自定义"
 
-#: ../../getting_started/application/kbqa/kbqa.md:14
-#: dc51e39242f342ddbe58ffa174beb6ab
+#: ../../getting_started/application/kbqa/kbqa.md:16
+#: f8a7af83e94e45239bd0efdb06eb320b
 msgid "Chat Knowledge"
 msgstr "知识问答"
 
-#: ../../getting_started/application/kbqa/kbqa.md:15
-#: a6dad0b121c54b3ea20c70a5db70a620
+#: ../../getting_started/application/kbqa/kbqa.md:17
+#: e6025e23178f4f58a6d4c75a6bc1d036
 msgid "Multi Vector DB"
 msgstr "多向量数据库管理"
 
-#: ../../getting_started/application/kbqa/kbqa.md:19
-#: 674b836c5b724239bbddd82bad862277
+#: ../../getting_started/application/kbqa/kbqa.md:21
+#: 0780e1d27af244429186caa866772c06
 msgid ""
 "If your DB type is Sqlite, there is nothing to do to build KBQA service "
 "database schema."
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:21
-#: ebeabfa4e0b4449eae8c3415a34c6c65
+#: ../../getting_started/application/kbqa/kbqa.md:23
+#: 38584aba054f4520a0b1d9b00d6abf06
 msgid ""
 "If your DB type is Mysql or other DBTYPE, you will build kbqa service "
 "database schema."
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:23
-#: 71163cedcdf64a5aac842bae688f4e23
+#: ../../getting_started/application/kbqa/kbqa.md:25
+#: 9ef800860afe4728b2103286864ed3fb
 msgid "Mysql"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:24
-#: da70cf9689db4434b95285c2b3610181
+#: ../../getting_started/application/kbqa/kbqa.md:26
+#: 3b30239fd457457eb707821794e786db
 msgid ""
 "$ mysql -h127.0.0.1 -uroot -paa12345678 < "
 "./assets/schema/knowledge_management.sql"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:26
-#: 3b4ddf0ec10b4851abb9dffc23d1a0ee
+#: ../../getting_started/application/kbqa/kbqa.md:28
+#: 1cd533c2f0254f8d8d10bafe5811a279
 msgid "or"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:28
-#: d100bbdc602c4ac79ffe90c867727983
+#: ../../getting_started/application/kbqa/kbqa.md:30
+#: 2b57e7d9a70f427e81122fe8d7d3c50b
 msgid "execute DBGPT/assets/schema/knowledge_management.sql"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:31
-#: d55e49f983e940108df5b91a9fb655b8
+#: ../../getting_started/application/kbqa/kbqa.md:33
+#: 45a0c8c8ff0a4b48ac2d66b4713c4108
 msgid "Steps to KBQA In DB-GPT"
 msgstr "怎样一步一步使用KBQA"
 
-#: ../../getting_started/application/kbqa/kbqa.md:33
-#: 3c7b3d6af58b4dca803a1bb31601067e
+#: ../../getting_started/application/kbqa/kbqa.md:35
+#: 2ff844b9a29f4717909d091a57d58fe8
 msgid "1.Create Knowledge Space"
 msgstr "1.首先创建知识空间"
 
-#: ../../getting_started/application/kbqa/kbqa.md:34
-#: baa2fb6ab666407cbfc1c89021259930
+#: ../../getting_started/application/kbqa/kbqa.md:36
+#: 081e1d1ef5bb42ddbd7330dd3ac1d38e
 #, fuzzy
 msgid ""
 "If you are using Knowledge Space for the first time, you need to create a"
@@ -131,18 +139,18 @@ msgid ""
 "GPT/assets/13723926/a93e597b-c392-465f-89d5-b55621d068a8)"
 msgstr "如果你是第一次使用，先创建知识空间，指定名字,拥有者和描述信息"
 
-#: ../../getting_started/application/kbqa/kbqa.md:34
-#: 48890c22982840eabe3e39b80d26fb90
+#: ../../getting_started/application/kbqa/kbqa.md:36
+#: 4a393bf0f50647d4b0cfc64db80847eb
 msgid "create_space"
 msgstr "create_space"
 
-#: ../../getting_started/application/kbqa/kbqa.md:39
-#: 2d271dabf8d0492e921795d68a764e03
+#: ../../getting_started/application/kbqa/kbqa.md:41
+#: 96303597bc364952b7249e805486e73f
 msgid "2.Create Knowledge Document"
 msgstr "2.上传知识"
 
-#: ../../getting_started/application/kbqa/kbqa.md:40
-#: 5ed95d36b0c147bebde38f4a6f55e5a3
+#: ../../getting_started/application/kbqa/kbqa.md:42
+#: 765f93f2b668491cb6824ea4706cb449
 msgid ""
 "DB-GPT now support Multi Knowledge Source, including Text, WebUrl, and "
 "Document(PDF, Markdown, Word, PPT, HTML and CSV). After successfully "
@@ -156,215 +164,215 @@ msgstr ""
 "and "
 "CSV)。上传文档成功后后台会自动将文档内容进行读取，切片，然后导入到向量数据库中，当然你也可以手动进行同步，你也可以点击详情查看具体的文档切片内容"
 
-#: ../../getting_started/application/kbqa/kbqa.md:42
-#: 36d3223b83614b49a92b0017d5c8ce82
+#: ../../getting_started/application/kbqa/kbqa.md:44
+#: a0eddeecc620479483bf50857da39ffd
 msgid "2.1 Choose Knowledge Type:"
 msgstr "2.1 选择知识类型"
 
-#: ../../getting_started/application/kbqa/kbqa.md:43
-#: 5a2b383ffec14ad2a1598b093426e9e7
+#: ../../getting_started/application/kbqa/kbqa.md:45
+#: 44de66f399324454b389d5c348af94e9
 msgid ""
 "![document](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/5b8173da-f444-4607-9d12-14bcab8179d0)"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:43
-#: b1c5c73905934de4ac8cea00e482840a
+#: ../../getting_started/application/kbqa/kbqa.md:45
+#: 1ae65290b99d490bb72b060084ecc726
 msgid "document"
 msgstr "document"
 
-#: ../../getting_started/application/kbqa/kbqa.md:45
-#: c214c2780b0545a3a3edbd97f69829ed
+#: ../../getting_started/application/kbqa/kbqa.md:47
+#: d8720434626444b593bb3b06b50dc70f
 msgid "2.2 Upload Document:"
 msgstr "2.2上传文档"
 
-#: ../../getting_started/application/kbqa/kbqa.md:46
-#: 732b8e32de8247249c9c908c258ba133
+#: ../../getting_started/application/kbqa/kbqa.md:48
+#: 2d4bcbeb391a47b89454b06cb041dff2
 msgid ""
 "![upload](https://github.com/eosphoros-ai/DB-GPT/assets/13723926"
 "/91b338fc-d3b2-476e-9396-3f6b4f16a890)"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:46
-#: ../../getting_started/application/kbqa/kbqa.md:50
-#: ../../getting_started/application/kbqa/kbqa.md:55
-#: ../../getting_started/application/kbqa/kbqa.md:68
-#: 4498b802e7724ad4b2b8edc044abd7fe 59633ce8e91c4e8b9f31cddee14a3f91
-#: f5c26d53dc584543912b24b8b8bc31ea f905664e67224a778d7c3ef0de7c42a8
+#: ../../getting_started/application/kbqa/kbqa.md:48
+#: ../../getting_started/application/kbqa/kbqa.md:52
+#: ../../getting_started/application/kbqa/kbqa.md:57
+#: ../../getting_started/application/kbqa/kbqa.md:70
+#: 58b32cb59a6242679f4a1e5fc7ca819f 81041a1f25b64b19a7f662ed55029224
+#: 8891e61f67014355b74c17d013c09cca f0e9c548494f4045a3dc92e993f4cfe7
 msgid "upload"
 msgstr "upload"
 
-#: ../../getting_started/application/kbqa/kbqa.md:49
-#: aa694e12c6884d0fbb5679af0535b05f
+#: ../../getting_started/application/kbqa/kbqa.md:51
+#: 645bf91a4f6a428a9e99ca29599c0722
 msgid "3.Chat With Knowledge"
 msgstr "3.知识问答"
 
-#: ../../getting_started/application/kbqa/kbqa.md:50
-#: 0c0cdbabb3934655a65c1c4304837efb
+#: ../../getting_started/application/kbqa/kbqa.md:52
+#: 85077af67bd740c1b3b02996dc287a80
 msgid ""
 "![upload](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/a8281be7-1454-467d-81c9-15ef108aac10)"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:52
-#: ce53a33431714d31b56eb0450a1363f4
+#: ../../getting_started/application/kbqa/kbqa.md:54
+#: 42d5776030ad4109810a0cb18e19de37
 msgid "4.Adjust Space arguments"
 msgstr "4.调整知识参数"
 
-#: ../../getting_started/application/kbqa/kbqa.md:53
-#: b37255e6cd6b433e8eeb01d73c9ccf19
+#: ../../getting_started/application/kbqa/kbqa.md:55
+#: a8ea23895a4b4312b1c1e072865f8b90
 msgid ""
 "Each knowledge space supports argument customization, including the "
 "relevant arguments for vector retrieval and the arguments for knowledge "
 "question-answering prompts."
 msgstr "每一个知识空间都支持参数自定义, 包括向量召回的相关参数以及知识问答Promp参数"
 
-#: ../../getting_started/application/kbqa/kbqa.md:54
-#: 3af4c2d8d2bf410698c73d339d0d1779
+#: ../../getting_started/application/kbqa/kbqa.md:56
+#: 2f5c087e4f7a49828aa797fafff237f0
 msgid "4.1 Embedding"
 msgstr "4.1 Embedding"
 
-#: ../../getting_started/application/kbqa/kbqa.md:55
-#: fdd136a1fe654751a22def62bdca853f
+#: ../../getting_started/application/kbqa/kbqa.md:57
+#: 47087bf391b642f3ba73e461d2d132a0
 msgid ""
 "Embedding Argument ![upload](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/f1221bd5-d049-4ceb-96e6-8709e76e502e)"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:59
-#: 8566534562574811bc08375b741dfcc9
+#: ../../getting_started/application/kbqa/kbqa.md:61
+#: 1ed384ba0501423184a4c977d86b8b3a
 msgid "Embedding arguments"
 msgstr "Embedding arguments"
 
-#: ../../getting_started/application/kbqa/kbqa.md:60
-#: 87fdcd70759b43cb9d9a7929247c34a6
+#: ../../getting_started/application/kbqa/kbqa.md:62
+#: 848962be69a348ffab3dd48839fb100a
 msgid "topk:the top k vectors based on similarity score."
 msgstr "topk:相似性检索出tok条文档"
 
-#: ../../getting_started/application/kbqa/kbqa.md:61
-#: c9fc1f2052c2437e9c4654f8053f02b5
+#: ../../getting_started/application/kbqa/kbqa.md:63
+#: 0880963aeb9c426187809a7086c224a8
 msgid "recall_score:set a threshold score for the retrieval of similar vectors."
 msgstr "recall_score:向量检索相关度衡量指标分数"
 
-#: ../../getting_started/application/kbqa/kbqa.md:62
-#: 11e837b098ee41ef9d5791b5d27f4891
+#: ../../getting_started/application/kbqa/kbqa.md:64
+#: a6ead8ae58164749b83e5c972537fe8b
 msgid "recall_type:recall type."
 msgstr "recall_type:召回类型"
 
-#: ../../getting_started/application/kbqa/kbqa.md:63
-#: 01d10823d12c454cad589b37c56b7b2b
+#: ../../getting_started/application/kbqa/kbqa.md:65
+#: 70d900b0948849d080effcdfc79bb685
 msgid "model:A model used to create vector representations of text or other data."
 msgstr "model:embdding模型"
 
-#: ../../getting_started/application/kbqa/kbqa.md:64
-#: 5fab346c27f24da783b4f30c55f8e291
+#: ../../getting_started/application/kbqa/kbqa.md:66
+#: 489a58835a5d4c98ad5f6f904f7af370
 msgid "chunk_size:The size of the data chunks used in processing."
 msgstr "chunk_size:文档切片阈值大小"
 
-#: ../../getting_started/application/kbqa/kbqa.md:65
-#: 3a031f1b6d014167aed24584d7fba187
+#: ../../getting_started/application/kbqa/kbqa.md:67
+#: b42781f2340c478f86137147fd4a6c91
 msgid "chunk_overlap:The amount of overlap between adjacent data chunks."
 msgstr "chunk_overlap:文本块之间的最大重叠量。保留一些重叠可以保持文本块之间的连续性（例如使用滑动窗口）"
 
-#: ../../getting_started/application/kbqa/kbqa.md:67
-#: b14bb51708d644c5a2e1fbbcc53f62c3
+#: ../../getting_started/application/kbqa/kbqa.md:69
+#: 5f027d4a10394e7da3d4b50fc2663f82
 msgid "4.2 Prompt"
 msgstr "4.2 Prompt"
 
-#: ../../getting_started/application/kbqa/kbqa.md:68
-#: f9d61953773a470ab12a3eb5ef00ad9e
+#: ../../getting_started/application/kbqa/kbqa.md:70
+#: 9ad62d8626584e80a82fcef239c0f546
 msgid ""
 "Prompt Argument ![upload](https://github.com/eosphoros-ai/DB-"
 "GPT/assets/13723926/9918c9c3-ed64-4804-9e05-fa7d7d177bec)"
 msgstr ""
 
-#: ../../getting_started/application/kbqa/kbqa.md:72
-#: fe9923b1f26647718443428ae520bb88
+#: ../../getting_started/application/kbqa/kbqa.md:74
+#: ec0717b8d210410f9894d2a4f51642e1
 msgid "Prompt arguments"
 msgstr "Prompt arguments"
 
-#: ../../getting_started/application/kbqa/kbqa.md:73
-#: 7de3b80bc5864407b34a66cd655c3af8
+#: ../../getting_started/application/kbqa/kbqa.md:75
+#: 7cf68eacd5ae4151abdefe44feb239e1
 msgid ""
 "scene:A contextual parameter used to define the setting or environment in"
 " which the prompt is being used."
 msgstr "scene:上下文环境的场景定义"
 
-#: ../../getting_started/application/kbqa/kbqa.md:74
-#: 4902e2e4a2c14cf9b29ca2084960e964
+#: ../../getting_started/application/kbqa/kbqa.md:76
+#: 2d9293acfb1a495c9b08261e957b2395
 msgid ""
 "template:A pre-defined structure or format for the prompt, which can help"
 " ensure that the AI system generates responses that are consistent with "
 "the desired style or tone."
 msgstr "template:预定义的提示结构或格式，可以帮助确保AI系统生成与所期望的风格或语气一致的回复。"
 
-#: ../../getting_started/application/kbqa/kbqa.md:75
-#: ad60c0ba862443ed80bcdf5895e6b2c1
+#: ../../getting_started/application/kbqa/kbqa.md:77
+#: 307dd62261214e4e84beb7f19b3e2f26
 msgid "max_token:The maximum number of tokens or words allowed in a prompt."
 msgstr "max_token: prompt token最大值"
 
-#: ../../getting_started/application/kbqa/kbqa.md:77
-#: 1a381bf794b4437c844c71abe0ca1f85
+#: ../../getting_started/application/kbqa/kbqa.md:79
+#: 07b797731fa74738acb3e1fb4c03deac
 msgid "5.Change Vector Database"
 msgstr "5.Change Vector Database"
 
-#: ../../getting_started/application/kbqa/kbqa.md:79
-#: 567b9c154d6a48b29536600b324ceb8b
+#: ../../getting_started/application/kbqa/kbqa.md:81
+#: 43fa40ced23842b48007b4264c1423c0
 msgid "Vector Store SETTINGS"
 msgstr "Vector Store SETTINGS"
 
-#: ../../getting_started/application/kbqa/kbqa.md:80
-#: a54cfb386b3244b998c520ca6499883c
+#: ../../getting_started/application/kbqa/kbqa.md:82
+#: 0ed4e0c6a81e4265b443a2c6d05d440b
 msgid "Chroma"
 msgstr "Chroma"
 
-#: ../../getting_started/application/kbqa/kbqa.md:81
-#: 6cea4f4289c649d49101b2f37f14eae4
+#: ../../getting_started/application/kbqa/kbqa.md:83
+#: 8ef2d15ffd0c4919bdbfdb52443021eb
 msgid "VECTOR_STORE_TYPE=Chroma"
 msgstr "VECTOR_STORE_TYPE=Chroma"
 
-#: ../../getting_started/application/kbqa/kbqa.md:82
-#: f3c494223e994ba0beb32abc8df19388
+#: ../../getting_started/application/kbqa/kbqa.md:84
+#: 08504aaae0014bd9992345f036989198
 msgid "MILVUS"
 msgstr "MILVUS"
 
-#: ../../getting_started/application/kbqa/kbqa.md:83
-#: e710aa4a2b184618bfc57f955f6e5b41
+#: ../../getting_started/application/kbqa/kbqa.md:85
+#: aa30fe77dc3f46bfb153b81e0cbdfb97
 msgid "VECTOR_STORE_TYPE=Milvus"
 msgstr "VECTOR_STORE_TYPE=Milvus"
 
-#: ../../getting_started/application/kbqa/kbqa.md:84
-#: ec6e4c1215f94776b47a5b035f3e82ed
+#: ../../getting_started/application/kbqa/kbqa.md:86
+#: e14c1646e5ca4677a471645c13dca835
 msgid "MILVUS_URL=127.0.0.1"
 msgstr "MILVUS_URL=127.0.0.1"
 
-#: ../../getting_started/application/kbqa/kbqa.md:85
-#: 14b5fd2ddf5d417a8d12f9dd0de77c4f
+#: ../../getting_started/application/kbqa/kbqa.md:87
+#: 0f0614f951934fd6abfb0fd45e0b79e7
 msgid "MILVUS_PORT=19530"
 msgstr "MILVUS_PORT=19530"
 
-#: ../../getting_started/application/kbqa/kbqa.md:86
-#: 558fbd783bf647b59af485cf501867ca
+#: ../../getting_started/application/kbqa/kbqa.md:88
+#: 4dafbbd894e4469e80414b54bde69193
 msgid "MILVUS_USERNAME"
 msgstr "MILVUS_USERNAME"
 
-#: ../../getting_started/application/kbqa/kbqa.md:87
-#: d7778707f4c840979a5a91430b947af8
+#: ../../getting_started/application/kbqa/kbqa.md:89
+#: 1759ec4d744e42a5a928c6abcc2dd2ac
 msgid "MILVUS_PASSWORD"
 msgstr "MILVUS_PASSWORD"
 
-#: ../../getting_started/application/kbqa/kbqa.md:88
-#: a6bcecc6451749048616031cbc1f07b6
+#: ../../getting_started/application/kbqa/kbqa.md:90
+#: d44bcea1db4f4388bc2ae7968e541761
 msgid "MILVUS_SECURE="
 msgstr "MILVUS_SECURE="
 
-#: ../../getting_started/application/kbqa/kbqa.md:90
-#: acfde2a941b141d28189c4f63f803234
+#: ../../getting_started/application/kbqa/kbqa.md:92
+#: f33218e0880f4d888438d3333f4a0895
 msgid "WEAVIATE"
 msgstr "WEAVIATE"
 
-#: ../../getting_started/application/kbqa/kbqa.md:91
-#: 59d8f6f31a5549799e52851eab72bfc2
+#: ../../getting_started/application/kbqa/kbqa.md:93
+#: 42a2102b236447ff83820d3a1602c3f2
 msgid "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network"
 msgstr "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.networkc"
 
diff --git 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
index 3ed1a27fc..b1fe805c8 100644
--- 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: 2023-08-29 20:30+0800\n"
+"POT-Creation-Date: 2023-08-29 20:50+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
-#: 7f17a8fdda104de18433b228ec3c1935
+#: 0baefc753798469588ea011c12a0bfd3
 msgid "Installation FAQ"
 msgstr "Installation FAQ"
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:5
-#: dc734d91ec464177834ab2e2df25f70a
+#: 013bf01a02c842ee8bc576f85d127e22
 #, 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
-#: dd04e05135ee4065b44e6196041fd15f
+#: 2729928139484def827143c17f2d968c
 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
-#: 159d77d65f014357ae4caa5aeba32080 7a5250f10d104e73a64012a89fb00e6f
+#: 6e8bf02d7117454fbcc28c7ec27e055a acd2186c0320466f95b500dade75591b
 msgid "or"
 msgstr "或者"
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:27
-#: 15af207c532541a2906a260266d8d2ca
+#: c5aab9455827416084a1ea6792263add
 msgid ""
 "Q2: sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) unable to"
 " open database file"
@@ -55,68 +55,68 @@ msgstr ""
 " open database file"
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:29
-#: b45fd323f5c84a428393e2d0e749ab17
+#: 29880cfc6c7f4f6fb14a9cbb9eed07ad
 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
-#: 468efa45ffe147ebb3a7bf737823f9da
+#: 36264030f5cd41bebd17beae12d9be51
 msgid "Q3: The model keeps getting killed."
 msgstr "Q3: The model keeps getting killed."
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:33
-#: ca4bb900b69740bbb40c7cb78bd8ba00
+#: 0cbf6ae0fee14d239cb1cc6ddba134d7
 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
-#: 13d52bc8a91a4e209d0b90f68f1be853
+#: 6f4ce365d20843529195aa6970d6074e
 msgid "Q4: How to access website on the public network"
 msgstr ""
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:37
-#: 5f0c0e894fdb477eba928f9c946a9bd8
+#: 9f4a119e64c74a0693fa067cd35cd833
 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
-#: c30ab098c2e547df81038814f870dec4
+#: 4c09cfb493ba41fb8590954b986e949d
 msgid "Open `url` with your browser to see the website."
 msgstr ""
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:50
-#: d298adc56dce463d8deb3d3550bc382c
+#: 7d905a99d1c547eb95d9c619c70bf221
 msgid "Q5: (Windows) execute `pip install -e .` error"
 msgstr ""
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:52
-#: a4b683c41fed443a8016b56c24235612
+#: fe26218168c4447a8dc89e436cdd1000
 msgid "The error log like the following:"
 msgstr ""
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:71
-#: ccbb33427cba40fca68b075cb796c670
+#: d15615f7798d4dc0ad49d9b28926fe32
 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
-#: b9535d65d65f4a368f7b0ee6f14c7da8
+#: 60ef06d3f99c44c1b568ec7c652905ee
 msgid "Q6: `Torch not compiled with CUDA enabled`"
 msgstr ""
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:82
-#: f9cf565e02b240b4a4044293122e9910
+#: 830e63627d2c48b8987ed20db3405c41
 msgid "Install [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit-archive)"
 msgstr ""
 
 #: ../../getting_started/faq/deploy/deploy_faq.md:83
-#: 6a15c0284228430381f56ac3bc825361
+#: 50a1c244ddf747d797825158550026b9
 msgid ""
 "Reinstall PyTorch [start-locally](https://pytorch.org/get-started/locally"
 "/#start-locally) with CUDA support."
diff --git a/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy/deploy.po b/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy/deploy.po
index bb015b2d3..ce1dafd57 100644
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy/deploy.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy/deploy.po
@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-08-29 20:30+0800\n"
+"POT-Creation-Date: 2023-08-29 20:50+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -20,34 +20,34 @@ msgstr ""
 "Generated-By: Babel 2.12.1\n"
 
 #: ../../getting_started/install/deploy/deploy.md:1
-#: 963de2c147e4491085e40a367ede1cb3
+#: b4f766ca21d241e2849ee0a277a0e8f0
 msgid "Installation From Source"
 msgstr "源码安装"
 
 #: ../../getting_started/install/deploy/deploy.md:3
-#: 3597fef8c1c24663ba9ddf0240dd8a1e
+#: 9cf72ef201ba4c7a99da8d7de9249cf4
 msgid ""
 "This tutorial gives you a quick walkthrough about use DB-GPT with you "
 "environment and data."
 msgstr "本教程为您提供了关于如何使用DB-GPT的使用指南。"
 
 #: ../../getting_started/install/deploy/deploy.md:5
-#: e9bd2165f24e41c2bebb4fed1672fd54
+#: b488acb9552043df96e9f01277375b56
 msgid "Installation"
 msgstr "安装"
 
 #: ../../getting_started/install/deploy/deploy.md:7
-#: 7a52cf49d60a4e76a43d8e534dcac6b8
+#: e1eb3aafea0c4b82b8d8163b947677dd
 msgid "To get started, install DB-GPT with the following steps."
 msgstr "请按照以下步骤安装DB-GPT"
 
 #: ../../getting_started/install/deploy/deploy.md:9
-#: 4dbc9d0146bb4574b31222a14c45eb46
+#: 4139c4e62e874dc58136b1f8fe0715fe
 msgid "1. Hardware Requirements"
 msgstr "1. 硬件要求"
 
 #: ../../getting_started/install/deploy/deploy.md:10
-#: eee7223178704420a179781df476e855
+#: c34a204cfa6e4973bfd94e683195c17b
 msgid ""
 "As our project has the ability to achieve ChatGPT performance of over "
 "85%, there are certain hardware requirements. However, overall, the "
@@ -56,176 +56,176 @@ msgid ""
 msgstr "由于我们的项目有能力达到85%以上的ChatGPT性能，所以对硬件有一定的要求。但总体来说，我们在消费级的显卡上即可完成项目的部署使用，具体部署的硬件说明如下:"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 21613161531642fb8d62d589b8d4feaa
+#: 3a92203e861b42c9af3d4b687d83de5e
 msgid "GPU"
 msgstr "GPU"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: cf5a8b7a75034011b7305d8bd09cf69c e8b55944bb9d4b91976027b3a2ae09d0
+#: 6050741571574eb8b9e498a5b3a7e347 c0a7e2aecb4b48949c3e5a4d479ee7b5
 msgid "VRAM Size"
 msgstr "显存"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 36641aaf9b81420fae3c2a2d89816d8a
+#: 247159f568e4476ca6c5e78015c7a8f0
 msgid "Performance"
 msgstr "Performance"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: ebc46f5c3f944ca6944774ac264ac801
+#: 871113cbc58743ef989a366b76e8c645
 msgid "RTX 4090"
 msgstr "RTX 4090"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: c387fa1e47ec4ae4bb145fbd4c18cd99 efbe071097b4421dbf06080d4ab1ec70
+#: 81327b7e9a984ec99cae779743d174df c237f392162c42d28ec694d17c3f281c
 msgid "24 GB"
 msgstr "24 GB"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 48d5632d53e0413d937bd4c13716591a
+#: 6e19f23bae05467ba03f1ebb194e0c03
 msgid "Smooth conversation inference"
 msgstr "Smooth conversation inference"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 5d7a590b885c4f128716da6347d91304
+#: 714a48b2c4a943819819a6af034f1998
 msgid "RTX 3090"
 msgstr "RTX 3090"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 93a35c5359e9432b9fac149e67087b4b
+#: 06dae55d443c48b1b3fbab85222c3adb
 msgid "Smooth conversation inference, better than V100"
 msgstr "Smooth conversation inference, better than V100"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: ec6d393791ae49eea9b2ff79f803e76c
+#: 5d50db167b244d65a8be1dab4acda37d
 msgid "V100"
 msgstr "V100"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 7da6411bc1c642e9a1063e988044e9f2 852dac8854514958b45f7f125c11f625
+#: 0d72262c85d148d8b1680d1d9f8fa2c9 e10db632889444a78e123773a30f23cf
 msgid "16 GB"
 msgstr "16 GB"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 1a3c78ad04114d5ebf25edba7ebdfcb7 b8ed26b4da564660bd70f0a3af1282a8
+#: 1c0379e653cf46f19d83535c568c54c8 aee8eb48e7804572af351dcfaea5b0fb
 msgid "Conversation inference possible, noticeable stutter"
 msgstr "Conversation inference possible, noticeable stutter"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 36603d7af55742eebc2f023fdf798f43
+#: 5bc90343dcef48c197438f01efe52bfc
 msgid "T4"
 msgstr "T4"
 
 #: ../../getting_started/install/deploy/deploy.md:19
-#: 0a4d0daf5d44421893db967825c0e158
+#: c9b5f973d19645d39b1892c00526afa7
 msgid ""
 "if your VRAM Size is not enough, DB-GPT supported 8-bit quantization and "
 "4-bit quantization."
 msgstr "如果你的显存不够，DB-GPT支持8-bit和4-bit量化版本"
 
 #: ../../getting_started/install/deploy/deploy.md:21
-#: 3523d76dc2a8414495ad46f72c304226
+#: 5e488271eede411d882f62ec8524dd4a
 msgid ""
 "Here are some of the VRAM size usage of the models we tested in some "
 "common scenarios."
 msgstr "这里是量化版本的相关说明"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 8ff21b833bf64962901e2e7a52e1322a
+#: 2cc65f16fa364088bedd0e58b6871ec8
 msgid "Model"
 msgstr "Model"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: be429d17a47643c797d989148d62583a
+#: d0e1a0d418f74e4b9f5922b17f0c8fcf
 msgid "Quantize"
 msgstr "Quantize"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 2ec73c552480461dada4f44763c4623e c51b0f85b34845798d926db31eaf720c
+#: 460b418ab7eb402eae7a0f86d1fda4bf 5e456423a9fa4c0392b08d32f3082f6f
 msgid "vicuna-7b-v1.5"
 msgstr "vicuna-7b-v1.5"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 2550147d36074525b23021a14dc55b24 5200cf5ca316459184cd247285adeb9c
-#: 9698f16cfa3d4ac589e7741e2371766c a3c90ef3728240a9927da25688ca500b
-#: c197d7bfe2be4f29995d6e6882a73c36 c8742a66fae049f9b2c6d333dd3fc209
-#: ed4e5c0cc67c4cd3acbb45def0dbac67
+#: 0f290c12b9324a07affcfd66804b82d7 29c81ce163e749b99035942a3b18582a
+#: 3a4f4325774d452f8c174cac5fe8de47 584f986a1afb4086a0382a9f7e79c55f
+#: 994c744ac67249f4a43b3bba360c0bbf aa9c82f660454143b9212842ffe0e0d6
+#: ac7b00313284410b9253c4a768a30f0c
 msgid "4-bit"
 msgstr "4-bit"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 1985bf309e324843aa849c38c9819b03 998c11e1c9b846d596c4423a22a438c8
-#: ffe2badbf75b4f119e22481b47866cc5
+#: 27401cbb0f2542e2aaa449a586aad2d1 2a1d2d10001f4d9f9b9961c28c592280
+#: b69a59c6e4a7458c91be814a98502632
 msgid "8 GB"
 msgstr "8 GB"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 23fed1f7361b46139294f979144f55b9 44b5316ad4be45acaca850ac350613dd
-#: 5d2642a53e444757b176c8ff86504f45 5e9a0cf9bab54b6ea805dd4c9b209b51
-#: 6a2ffb34d35a4d64bcb18d88b6ed3e83 b70e17fc9a184074ac4bc641312fc8e8
-#: bb6bd13b7d09417ea26949cf385d037c
+#: 0a15518df1b94492b610e47f3c7bb4f6 1f1852ceae0b4c21a020dc9ef4f8b20b
+#: 89ad803f6bd24b5d9708a6d4bd48a54f ac7c222678d34637a03546dcb5949668
+#: b12e1599bdcb4d27ad4e4a83f12de916 c80ba4ddc1634093842a6f284b7b22bb
+#: f63b900e4b844b3196c4c221b36d31f7
 msgid "8-bit"
 msgstr "8-bit"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 0718757036b04690bd6fa98959ae41d3 2401f442291c4fd8a7fdf69d1745b604
-#: 3c3af4923aa5498ca85d87610712f9ff 620ef43ffb5441a7ac0bfcd920729518
-#: bf626548d1624794ad4e16f0acbdf59f e24c281f31b44b89bb1a9151b7e0ba9a
+#: 02f72ed48b784b05b2fcaf4ea33fcba8 17285314376044bf9d9a82f9001f39dc
+#: 403178173a784bdf8d02fe856849a434 4875c6b595484091b622602d9ef0d3e8
+#: 4b11125d4b0c40c488bffb130f4f2b9f e2418c76e7e04101821f29650d111a4a
 msgid "12 GB"
 msgstr "12 GB"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 685bc5ce8e4a411a8f59026674b5967d 8223632d5da5462b977c3bd9cb2731a2
+#: 01dfd16f70cf4128a49ca7bc79f77042 a615efffecb24addba759d05ef61a1c0
 msgid "vicuna-13b-v1.5"
 msgstr "vicuna-13b-v1.5"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 09e37f82a825411191ab74a634706866 80138163ba034d819eeb165384392655
-#: da076416fa8c4fb7b28939ca7c76d06b
+#: 412ddfa6e6fb4567984f757cf74b3bfc 529650341d96466a93153d58ddef0ec9
+#: 6176929d59bb4e31a37cbba8a81a489f
 msgid "20 GB"
 msgstr "20 GB"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 4551174e7f8449bd93fb14de039ed400 9879cd654383482784992f410ba478aa
+#: 566b7aa7bc88421a9364cef6bfbeae48 ae32a218d07e44c796ca511972ea2cb0
 msgid "llama-2-7b"
 msgstr "llama-2-7b"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 0a74ee29547445e4a1389386249528a4 af6fa6d9dec54179808820fda8b8210b
+#: 1ac748eb518b4017accb98873fe1a8e5 528109c765e54b3caf284e7794abd468
 msgid "llama-2-13b"
 msgstr "llama-2-13b"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 1aadc9ec7645467596e991f770e5bce5 32aa71dcf6d9497ba48af4c2c192e3ef
+#: dfb5c0fa9e82423ab1de9256b3b3f215 f861be75871d40849f896859d0b8be4c
 msgid "llama-2-70b"
 msgstr "llama-2-70b"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 1e63e7f32ec74f4e8290254ce348c50d
+#: 5568529a82cd4c49812ab2fd46ff9bf0
 msgid "48 GB"
 msgstr "48 GB"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: d5416570171e49a88a75161f4e5f0c77
+#: 4ba730f4faa64df9a0a9f72cb3eb0c88
 msgid "80 GB"
 msgstr "80 GB"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 598393baadb7468ca649db8de42fd413 f6aaa22133ac4721b6740ab75c43819d
+#: 47221748d6d5417abc25e28b6905bc6f 6023d535095a4cb9a99343c2dfddc927
 msgid "baichuan-7b"
 msgstr "baichuan-7b"
 
 #: ../../getting_started/install/deploy/deploy.md
-#: 454e6b05fc2f4f318afc7d7e5f4477b9 ebd9204f511949d695b20caa8d2b5701
+#: 55011d4e0bed451dbdda75cb8b258fa5 bc296e4bd582455ca64afc74efb4ebc8
 msgid "baichuan-13b"
 msgstr "baichuan-13b"
 
 #: ../../getting_started/install/deploy/deploy.md:40
-#: a74a45bb031c41a9a88fab4023791430
+#: 4bfd52634a974776933c93227f419cdb
 msgid "2. Install"
 msgstr "2. Install"
 
 #: ../../getting_started/install/deploy/deploy.md:45
-#: 480a54d6f3b944b2a26414561ccd5cf4
+#: 647f09001d4c4124bed11da272306946
 msgid ""
 "We use Sqlite as default database, so there is no need for database "
 "installation.  If you choose to connect to other databases, you can "
@@ -240,12 +240,12 @@ msgstr ""
 " Miniconda](https://docs.conda.io/en/latest/miniconda.html)"
 
 #: ../../getting_started/install/deploy/deploy.md:54
-#: 8d9d99b9b3f6444f8e2b289ff0b3d1cf
+#: bf9fcf320ca94dbd855016088800b1a9
 msgid "Before use DB-GPT Knowledge"
 msgstr "在使用知识库之前"
 
 #: ../../getting_started/install/deploy/deploy.md:60
-#: 3ba68f5b12134958ad3495fc03e6261f
+#: e0cb6cb46a474c4ca16edf73c82b58ca
 msgid ""
 "Once the environment is installed, we have to create a new folder "
 "\"models\" in the DB-GPT project, and then we can put all the models "
@@ -253,27 +253,27 @@ msgid ""
 msgstr "如果你已经安装好了环境需要创建models, 然后到huggingface官网下载模型"
 
 #: ../../getting_started/install/deploy/deploy.md:63
-#: ae6612ce4b6845cfa9396fcad5549bd0
+#: 03b1bf35528d4cdeb735047aa840d6fe
 msgid "Notice make sure you have install git-lfs"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:65
-#: fbfa0caf0615484bbe861b327a67c847
+#: f8183907e7c044f695f86943b412d84a
 msgid "centos:yum install git-lfs"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:67
-#: ca10fedecab243fba8a0d11b14ccddde
+#: 3bc042bd5cac4007afc9f68e7b5044fe
 msgid "ubuntu:app-get install git-lfs"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:69
-#: a3026601a2304ce3a38e162cb7f44d2f
+#: 5915ed1290e84ed9b6782c6733d88891
 msgid "macos:brew install git-lfs"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:86
-#: ffda61cebb534429bfa1d3a375647077
+#: 104f1e75b0a54300af440ca3b64217a3
 msgid ""
 "The model files are large and will take a long time to download. During "
 "the download, let's configure the .env file, which needs to be copied and"
@@ -281,7 +281,7 @@ msgid ""
 msgstr "模型文件很大，需要很长时间才能下载。在下载过程中，让我们配置.env文件，它需要从。env.template中复制和创建。"
 
 #: ../../getting_started/install/deploy/deploy.md:88
-#: f30593a4496c498d807bc1bf48fc333e
+#: 228c6729c23f4e17b0475b834d7edb01
 msgid ""
 "if you want to use openai llm service, see [LLM Use FAQ](https://db-"
 "gpt.readthedocs.io/en/latest/getting_started/faq/llm/llm_faq.html)"
@@ -290,19 +290,19 @@ msgstr ""
 "gpt.readthedocs.io/en/latest/getting_started/faq/llm/llm_faq.html)"
 
 #: ../../getting_started/install/deploy/deploy.md:91
-#: adbf4130afb442e0b2ebe9ecadc27927
+#: c444514ba77b46468721888fe7df9e74
 msgid "cp .env.template .env"
 msgstr "cp .env.template .env"
 
 #: ../../getting_started/install/deploy/deploy.md:94
-#: 67a0efdf4138465b84f50946c50aef33
+#: 1514e937757e461189b369da73884a6c
 msgid ""
 "You can configure basic parameters in the .env file, for example setting "
 "LLM_MODEL to the model to be used"
 msgstr "您可以在.env文件中配置基本参数，例如将LLM_MODEL设置为要使用的模型。"
 
 #: ../../getting_started/install/deploy/deploy.md:96
-#: ec7328fea11344b8ac6b821a1cd10531
+#: 4643cdf76bd947fdb86fc4691b98935c
 msgid ""
 "([Vicuna-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5) based on "
 "llama-2 has been released, we recommend you set `LLM_MODEL=vicuna-"
@@ -313,37 +313,37 @@ msgstr ""
 "目前Vicuna-v1.5模型(基于llama2)已经开源了，我们推荐你使用这个模型通过设置LLM_MODEL=vicuna-13b-v1.5"
 
 #: ../../getting_started/install/deploy/deploy.md:98
-#: 386d91268dc54f3a92172758afe25d3e
+#: acf91810f12b4ad0bd830299eb24850f
 msgid "3. Run"
 msgstr "3. Run"
 
 #: ../../getting_started/install/deploy/deploy.md:100
-#: 4672d31b78dc44719ad41f05fe0bf103
+#: ea82d67451724c2399f8903ea3c52dff
 msgid "**(Optional) load examples into SQLlite**"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:105
-#: 174bb3d5c82c41ad92fa2147dbfe0bdc
+#: a00987ec21364389b7feec58b878c2a1
 msgid "On windows platform:"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:110
-#: aa25742904354373a10b8aaa62fa6005
+#: db5c000e6abe4e1cb94e6f4f14247eb7
 msgid "1.Run db-gpt server"
 msgstr "1.Run db-gpt server"
 
 #: ../../getting_started/install/deploy/deploy.md:116
-#: 86a196e04cd1459ab83c0402b6c73c25
+#: dbeecff230174132b85d1d4549d3c07e
 msgid "Open http://localhost:5000 with your browser to see the product."
 msgstr "打开浏览器访问http://localhost:5000"
 
 #: ../../getting_started/install/deploy/deploy.md:119
-#: e53c6021747e48298a9a94b33161aba2
+#: 22d6321e6226472e878a95d3c8a9aad8
 msgid "If you want to access an external LLM service, you need to"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:121
-#: a5d7891ca43a4da8a60e925cfdff829b
+#: 561dfe9a864540d6ac582f0977b2c9ad
 msgid ""
 "1.set the variables LLM_MODEL=YOUR_MODEL_NAME, "
 "MODEL_SERVER=YOUR_MODEL_SERVER（eg:http://localhost:5000） in the .env "
@@ -351,12 +351,12 @@ msgid ""
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:123
-#: adc8ccbdda9743aab58a3fdb8aa593fd
+#: 55ceca48e40147a99ab4d23392349156
 msgid "2.execute dbgpt_server.py in light mode"
 msgstr ""
 
 #: ../../getting_started/install/deploy/deploy.md:126
-#: 29fb5c398fd94f5eaed6382ec7332097
+#: 02d42956a2734c739ad1cb9ce59142ce
 msgid ""
 "If you want to learn about dbgpt-webui, read https://github./csunny/DB-"
 "GPT/tree/new-page-framework/datacenter"
@@ -365,13 +365,13 @@ msgstr ""
 "framework/datacenter"
 
 #: ../../getting_started/install/deploy/deploy.md:132
-#: d5a6113dc2844430bde6d1e62ae70eb9
+#: d813eb43b97445a08e058d336249e6f6
 #, fuzzy
 msgid "Multiple GPUs"
 msgstr "4. Multiple GPUs"
 
 #: ../../getting_started/install/deploy/deploy.md:134
-#: 15d02416586344d19adfc39f6d05ee9f
+#: 0ac795f274d24de7b37f9584763e113d
 msgid ""
 "DB-GPT will use all available gpu by default. And you can modify the "
 "setting `CUDA_VISIBLE_DEVICES=0,1` in `.env` file to use the specific gpu"
@@ -379,32 +379,32 @@ msgid ""
 msgstr "DB-GPT默认加载可利用的gpu，你也可以通过修改 在`.env`文件 `CUDA_VISIBLE_DEVICES=0,1`来指定gpu IDs"
 
 #: ../../getting_started/install/deploy/deploy.md:136
-#: d6875130c3ba4bbf80a046a77c815f26
+#: 2be557e2b5414d478d375bce0474558d
 msgid ""
 "Optionally, you can also specify the gpu ID to use before the starting "
 "command, as shown below:"
 msgstr "你也可以指定gpu ID启动"
 
 #: ../../getting_started/install/deploy/deploy.md:146
-#: b2d5855d7cf946a1a00ec55e0328b1a6
+#: 222f1ebb5cb64675a0c319552d14303e
 msgid ""
 "You can modify the setting `MAX_GPU_MEMORY=xxGib` in `.env` file to "
 "configure the maximum memory used by each GPU."
 msgstr "同时你可以通过在.env文件设置`MAX_GPU_MEMORY=xxGib`修改每个GPU的最大使用内存"
 
 #: ../../getting_started/install/deploy/deploy.md:148
-#: 385caf97c7d149b1bb1852198c8e04de
+#: fb92349f9fe049d5b23b9ead17caf895
 #, fuzzy
 msgid "Not Enough Memory"
 msgstr "5. Not Enough Memory"
 
 #: ../../getting_started/install/deploy/deploy.md:150
-#: 30ec48dfe9f44ef88e55f7218b2d3967
+#: 30a1105d728a474c9cd14638feab4b59
 msgid "DB-GPT supported 8-bit quantization and 4-bit quantization."
 msgstr "DB-GPT 支持 8-bit quantization 和 4-bit quantization."
 
 #: ../../getting_started/install/deploy/deploy.md:152
-#: dad6fbec89104dd9b11ae6778942bf69
+#: eb2e576379434bfa828c98ee374149f5
 msgid ""
 "You can modify the setting `QUANTIZE_8bit=True` or `QUANTIZE_4bit=True` "
 "in `.env` file to use quantization(8-bit quantization is enabled by "
@@ -412,7 +412,7 @@ msgid ""
 msgstr "你可以通过在.env文件设置`QUANTIZE_8bit=True` or `QUANTIZE_4bit=True`"
 
 #: ../../getting_started/install/deploy/deploy.md:154
-#: d6eebf82de5b410a979e978e489d5317
+#: eeaecfd77d8546a6afc1357f9f1684bf
 msgid ""
 "Llama-2-70b with 8-bit quantization can run with 80 GB of VRAM, and 4-bit"
 " quantization can run with 48 GB of VRAM."
diff --git a/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/docker/docker.po b/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/docker/docker.po
index bc3a18a54..219f0fd86 100644
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/docker/docker.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/docker/docker.po
@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-08-29 20:30+0800\n"
+"POT-Creation-Date: 2023-08-29 20:50+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -20,46 +20,46 @@ msgstr ""
 "Generated-By: Babel 2.12.1\n"
 
 #: ../../getting_started/install/docker/docker.md:1
-#: 6330986214f9407b89928b1fbce7c0e6
+#: b1f8f6a0b8974ea09a5fe2812f31d941
 msgid "Docker Install"
 msgstr "Docker 安装"
 
 #: ../../getting_started/install/docker/docker.md:4
-#: bddc5010a8cf437eaaf8bf56a65e8cf7
+#: d9145d02ed984d45b33eb46117a2484b
 msgid "Docker (Experimental)"
 msgstr "Docker (Experimental)"
 
 #: ../../getting_started/install/docker/docker.md:6
-#: c6ee3554954f44da81d89038f4b04d2f
+#: 7d2a5e4016f543748b80dedcee36f3c6
 #, fuzzy
 msgid "1. Preparing docker images"
 msgstr "1.构建Docker镜像"
 
 #: ../../getting_started/install/docker/docker.md:8
-#: 868f0199d9054609a545fdc75171560d
+#: 1cb08cc1662f45579b82f0d402c39cc3
 msgid ""
 "**Pull docker image from the [Eosphoros AI Docker "
 "Hub](https://hub.docker.com/u/eosphorosai)**"
 msgstr ""
 
 #: ../../getting_started/install/docker/docker.md:14
-#: c6ee3554954f44da81d89038f4b04d2f
+#: 23781bc56d394d07927186c6cf619a91
 #, fuzzy
 msgid "**(Optional) Building Docker image**"
 msgstr "1.构建Docker镜像"
 
 #: ../../getting_started/install/docker/docker.md:20
-#: 7d10f8ae3cba4f13a011c7f0dc2ef479
+#: 77a31390bd024d5f87f8d8ec386a23ae
 msgid "Review images by listing them:"
 msgstr "Review images by listing them:"
 
 #: ../../getting_started/install/docker/docker.md:26
-#: 9116b39c10394d4fb0dee3a0ed431eca
+#: e5f6c40d68f346e1bbb57a5f7ac2f10b
 msgid "Output should look something like the following:"
 msgstr "输出日志应该长这样:"
 
 #: ../../getting_started/install/docker/docker.md:33
-#: 80faced8a2fb482ab12baddec9ac21b8
+#: b26892bf338c484ba8ed34f09c0fda23
 msgid ""
 "`eosphorosai/dbgpt` is the base image, which contains the project's base "
 "dependencies and a sqlite database. `eosphorosai/dbgpt-allinone` build "
@@ -67,25 +67,25 @@ msgid ""
 msgstr ""
 
 #: ../../getting_started/install/docker/docker.md:35
-#: 50e3fa230dbf474fbd756a52169ce1c4
+#: 7aabb767dcd8439ea7ca14fd8deccb87
 msgid "You can pass some parameters to docker/build_all_images.sh."
 msgstr "你也可以docker/build_all_images.sh构建的时候指定参数"
 
 #: ../../getting_started/install/docker/docker.md:43
-#: 83eb1b3c3f8f4158879e32ef4e4046ba
+#: 36a85e7aca484e5cb0656dea8dc3568c
 msgid ""
 "You can execute the command `bash docker/build_all_images.sh --help` to "
 "see more usage."
 msgstr "可以指定命令`bash docker/build_all_images.sh --help`查看如何使用"
 
 #: ../../getting_started/install/docker/docker.md:45
-#: 893ed5c6fe854265a3d9a3a77a0c385f
+#: c0d04891ed784cd8a8403ea395c56a45
 #, fuzzy
 msgid "2. Run docker container"
 msgstr "2. Run all in one docker container"
 
 #: ../../getting_started/install/docker/docker.md:47
-#: e18a4483b9c242b187a9bc61746f2d24
+#: 7d5cb8366aa849b684fe5c3805213d0d
 #, fuzzy
 msgid "**Run with local model and SQLite database**"
 msgstr "**Run with local model**"
@@ -93,13 +93,14 @@ msgstr "**Run with local model**"
 #: ../../getting_started/install/docker/docker.md:61
 #: ../../getting_started/install/docker/docker.md:88
 #: ../../getting_started/install/docker/docker.md:123
-#: 90fda1321aa2468aa681431e36800913
+#: 2ef66d0c87cf4ab48f9bbf4473071b43 9b594d33ef9f472d9fccfe1bd07d5564
+#: f86c8364bd9948b29224c6ef0e1d6a83
 msgid "Open http://localhost:5000 with your browser to see the product."
 msgstr "打开浏览器访问http://localhost:5000"
 
 #: ../../getting_started/install/docker/docker.md:64
 #: ../../getting_started/install/docker/docker.md:91
-#: d9ced1b042494210b961204d5f0a5dea
+#: a462082e866f46a8b99a4d95e6fa5b83 d262fdeb9f9c4156898875db75997874
 #, fuzzy
 msgid ""
 "`-e LLM_MODEL=vicuna-13b-v1.5`, means we use vicuna-13b-v1.5 as llm "
@@ -108,7 +109,7 @@ msgstr "`-e LLM_MODEL=vicuna-13b` 指定llm model is vicuna-13b "
 
 #: ../../getting_started/install/docker/docker.md:65
 #: ../../getting_started/install/docker/docker.md:92
-#: 1e7e2121ae6047eea27f6f3e8a2c730b
+#: c8c172873ff145aeb4f0f9cb04c209a8 f1b2e1f27cd24ed9ae233445f3fe1301
 msgid ""
 "`-v /data/models:/app/models`, means we mount the local model file "
 "directory `/data/models` to the docker container directory `/app/models`,"
@@ -119,23 +120,23 @@ msgstr ""
 
 #: ../../getting_started/install/docker/docker.md:67
 #: ../../getting_started/install/docker/docker.md:94
-#: 77b7fa4ee51b44718145d8d3bf65e59e
+#: 432463d5993a4e6eb34497390d89e891 da8df3262b834b359c080e84b25e431e
 msgid "You can see log with command:"
 msgstr "你也可以通过命令查看日志"
 
 #: ../../getting_started/install/docker/docker.md:73
-#: 23495e4399574a91bd04f7cca44748db
+#: a4963b927a87455c90a4fbb1d3814a09
 #, fuzzy
 msgid "**Run with local model and MySQL database**"
 msgstr "**Run with local model**"
 
 #: ../../getting_started/install/docker/docker.md:100
-#: 2a8088830699426c9ab4cc890ab8d7bd
+#: 81ecd658f7c54070bcb47838d3a9f533
 msgid "**Run with openai interface**"
 msgstr "**Run with openai interface**"
 
 #: ../../getting_started/install/docker/docker.md:119
-#: fd5f1772a3db4fa0929d84ea3451ce4e
+#: 2c01b849a0fe4b4d9554a9adf9cbf8fc
 msgid ""
 "`-e LLM_MODEL=proxyllm`, means we use proxy llm(openai interface, "
 "fastchat interface...)"
@@ -144,7 +145,7 @@ msgstr ""
 "interface..."
 
 #: ../../getting_started/install/docker/docker.md:120
-#: 7c9b301bd1a145b1ab622c18df7e7310
+#: 262af25e0ec748e3a8b12274004624bb
 msgid ""
 "`-v /data/models/text2vec-large-chinese:/app/models/text2vec-large-"
 "chinese`, means we mount the local text2vec model to the docker "
diff --git a/pilot/commands/disply_type/show_chart_gen.py b/pilot/commands/disply_type/show_chart_gen.py
index ec3559e27..27f1639d5 100644
--- a/pilot/commands/disply_type/show_chart_gen.py
+++ b/pilot/commands/disply_type/show_chart_gen.py
@@ -9,7 +9,7 @@ import os
 import matplotlib
 import seaborn as sns
 
-# matplotlib.use("Agg")
+matplotlib.use("Agg")
 import matplotlib.pyplot as plt
 from matplotlib.font_manager import FontManager
 
diff --git a/pilot/scene/chat_data/chat_excel/excel_learning/test.py b/pilot/scene/chat_data/chat_excel/excel_learning/test.py
index ecdd03867..2d90f169d 100644
--- a/pilot/scene/chat_data/chat_excel/excel_learning/test.py
+++ b/pilot/scene/chat_data/chat_excel/excel_learning/test.py
@@ -3,8 +3,15 @@ import duckdb
 import pandas as pd
 import matplotlib
 import seaborn as sns
+import uuid
+from pandas import DataFrame
 
 import matplotlib.pyplot as plt
+import matplotlib.ticker as mtick
+from matplotlib import font_manager
+from matplotlib.font_manager import FontManager
+
+matplotlib.use("Agg")
 import time
 from fsspec import filesystem
 import spatial
@@ -12,42 +19,145 @@ import spatial
 from pilot.scene.chat_data.chat_excel.excel_reader import ExcelReader
 
 
+def data_pre_classification(df: DataFrame):
+    ## Data pre-classification
+    columns = df.columns.tolist()
+
+    number_columns = []
+    non_numeric_colums = []
+
+    # 收集数据分类小于10个的列
+    non_numeric_colums_value_map = {}
+    numeric_colums_value_map = {}
+    for column_name in columns:
+        if pd.to_numeric(df[column_name], errors="coerce").notna().all():
+            number_columns.append(column_name)
+            unique_values = df[column_name].unique()
+            numeric_colums_value_map.update({column_name: len(unique_values)})
+        else:
+            non_numeric_colums.append(column_name)
+            unique_values = df[column_name].unique()
+            non_numeric_colums_value_map.update({column_name: len(unique_values)})
+
+    if len(non_numeric_colums) <= 0:
+        sorted_colums_value_map = dict(
+            sorted(numeric_colums_value_map.items(), key=lambda x: x[1])
+        )
+        numeric_colums_sort_list = list(sorted_colums_value_map.keys())
+        x_column = number_columns[0]
+        hue_column = numeric_colums_sort_list[0]
+        y_column = numeric_colums_sort_list[1]
+    elif len(number_columns) <= 0:
+        raise ValueError("Have No numeric Column！")
+    else:
+        # 数字和非数字都存在多列，放弃部分数字列
+        y_column = number_columns[0]
+        x_column = non_numeric_colums[0]
+        # if len(non_numeric_colums) > 1:
+        #
+        # else:
+
+        # non_numeric_colums_sort_list.remove(non_numeric_colums[0])
+        # hue_column = non_numeric_colums_sort_list
+    return x_column, y_column, hue_column
+
+
 if __name__ == "__main__":
     # connect = duckdb.connect("/Users/tuyang.yhj/Downloads/example.xlsx")
+    #
+
+    # fonts = fm.findSystemFonts()
+    # for font in fonts:
+    #     if 'Hei' in font:
+    #         print(font)
+
+    # fm = FontManager()
+    # mat_fonts = set(f.name for f in fm.ttflist)
+    # for i in mat_fonts:
+    #     print(i)
+    # print(len(mat_fonts))
+    # 获取系统中的默认中文字体名称
+    # default_font = fm.fontManager.defaultFontProperties.get_family()
+
     #
     excel_reader = ExcelReader("/Users/tuyang.yhj/Downloads/example.xlsx")
-
-    # colunms, datas = excel_reader.run( "SELECT CONCAT(Year, '-', Quarter) AS QuarterYear, SUM(Sales) AS TotalSales FROM example GROUP BY QuarterYear ORDER BY QuarterYear")
-    colunms, datas = excel_reader.run(
-        """ SELECT Year, SUM(Sales) AS Total_Sales FROM example GROUP BY Year ORDER BY Year; """
-    )
+    #
+    # # colunms, datas = excel_reader.run( "SELECT CONCAT(Year, '-', Quarter) AS QuarterYear, SUM(Sales) AS TotalSales FROM example GROUP BY QuarterYear ORDER BY QuarterYear")
+    # # colunms, datas = excel_reader.run( """ SELECT Year, SUM(Sales) AS Total_Sales FROM example GROUP BY Year ORDER BY Year; """)
     df = excel_reader.get_df_by_sql_ex(
-        "SELECT Country, SUM(Profit) AS Total_Profit FROM example GROUP BY Country;"
+        """ SELECT Segment, Country, SUM(Sales) AS Total_Sales, SUM(Profit) AS Total_Profit FROM example GROUP BY Segment, Country """
     )
-    columns = df.columns.tolist()
-    plt.rcParams["font.family"] = ["sans-serif"]
-    rc = {"font.sans-serif": "SimHei", "axes.unicode_minus": False}
-    sns.set_style(rc={"font.sans-serif": "Microsoft Yahei"})
-    sns.set(context="notebook", style="ticks", color_codes=True, rc=rc)
-    sns.set_palette("Set3")  # 设置颜色主题
 
-    # fig, ax = plt.pie(df[columns[1]], labels=df[columns[0]], autopct='%1.1f%%', startangle=90)
+    x, y, hue = data_pre_classification(df)
+    print(x, y, hue)
+
+    columns = df.columns.tolist()
+    font_names = [
+        "Heiti TC",
+        "Songti SC",
+        "STHeiti Light",
+        "Microsoft YaHei",
+        "SimSun",
+        "SimHei",
+        "KaiTi",
+    ]
+    fm = FontManager()
+    mat_fonts = set(f.name for f in fm.ttflist)
+    can_use_fonts = []
+    for font_name in font_names:
+        if font_name in mat_fonts:
+            can_use_fonts.append(font_name)
+    if len(can_use_fonts) > 0:
+        plt.rcParams["font.sans-serif"] = can_use_fonts
+
+    rc = {"font.sans-serif": can_use_fonts}
+    plt.rcParams["axes.unicode_minus"] = False  # 解决无法显示符号的问题
+    sns.set(font="Heiti TC", font_scale=0.8)  # 解决Seaborn中文显示问题
+    sns.set_palette("Set3")  # 设置颜色主题
+    sns.set_style("dark")
+    sns.color_palette("hls", 10)
+    sns.hls_palette(8, l=0.5, s=0.7)
+    sns.set(context="notebook", style="ticks", rc=rc)
+    # sns.set_palette("Set3")  # 设置颜色主题
+    # sns.set_style("dark")
+    # sns.color_palette("hls", 10)
+    # sns.hls_palette(8, l=.5, s=.7)
+    # sns.set(context='notebook', style='ticks', rc=rc)
+
     fig, ax = plt.subplots(figsize=(8, 5), dpi=100)
-    plt.subplots_adjust(top=0.9)
-    ax = df.plot(
-        kind="pie",
-        y=columns[1],
-        ax=ax,
-        labels=df[columns[0]].values,
-        startangle=90,
-        autopct="%1.1f%%",
-    )
-    # 手动设置 labels 的位置和大小
-    ax.legend(
-        loc="center left", bbox_to_anchor=(-1, 0.5, 0, 0), labels=None, fontsize=10
-    )
-    plt.axis("equal")  # 使饼图为正圆形
-    plt.show()
+    # plt.ticklabel_format(style='plain')
+    # ax = df.plot(kind='bar', ax=ax)
+    # sns.barplot(df, x=x, y=y, hue= "Country", ax=ax)
+    sns.catplot(data=df, x=x, y=y, hue="Country", kind="bar")
+    # 设置 y 轴刻度格式为普通数字格式
+    ax.yaxis.set_major_formatter(mtick.FuncFormatter(lambda x, _: "{:,.0f}".format(x)))
+
+    # fonts = font_manager.findSystemFonts()
+    # font_path = ""
+    # for font in fonts:
+    #     if "Heiti" in font:
+    #         font_path = font
+    # my_font = font_manager.FontProperties(fname=font_path)
+    # plt.title("测试", fontproperties=my_font)
+    # plt.ylabel(columns[1], fontproperties=my_font)
+    # plt.xlabel(columns[0], fontproperties=my_font)
+
+    chart_name = "bar_" + str(uuid.uuid1()) + ".png"
+    chart_path = chart_name
+    plt.savefig(chart_path, bbox_inches="tight", dpi=100)
+
+    # sns.set(context="notebook", style="ticks", color_codes=True)
+    # sns.set_palette("Set3")  # 设置颜色主题
+    #
+    # # fig, ax = plt.pie(df[columns[1]], labels=df[columns[0]], autopct='%1.1f%%', startangle=90)
+    # fig, ax = plt.subplots(figsize=(8, 5), dpi=100)
+    # plt.subplots_adjust(top=0.9)
+    # ax = df.plot(kind='pie', y=columns[1], ax=ax, labels=df[columns[0]].values, startangle=90, autopct='%1.1f%%')
+    # # 手动设置 labels 的位置和大小
+    # ax.legend(loc='center left', bbox_to_anchor=(-1, 0.5, 0,0), labels=None, fontsize=10)
+    # plt.axis('equal')  # 使饼图为正圆形
+    # plt.show()
+
     #
     #
     # def csv_colunm_foramt(val):
diff --git a/pilot/scene/chat_db/auto_execute/prompt.py b/pilot/scene/chat_db/auto_execute/prompt.py
index e284ce1a9..a2737aa4f 100644
--- a/pilot/scene/chat_db/auto_execute/prompt.py
+++ b/pilot/scene/chat_db/auto_execute/prompt.py
@@ -21,7 +21,7 @@ Be careful to not query for columns that do not exist. Also, pay attention to wh
 
 Question: {input}
 
-Rrespond in JSON format as following format:
+Respond in JSON format as following format:
 {response}
 Ensure the response is correct json and can be parsed by Python json.loads
 """