diff --git a/docker/base/Dockerfile b/docker/base/Dockerfile
index 63486e260..e4fad9697 100644
--- a/docker/base/Dockerfile
+++ b/docker/base/Dockerfile
@@ -28,7 +28,9 @@ WORKDIR /app
 # RUN pip3 install -i $PIP_INDEX_URL ".[all]"
 
 RUN pip3 install --upgrade pip -i $PIP_INDEX_URL \
-    && pip3 install -i $PIP_INDEX_URL ".[$DB_GPT_INSTALL_MODEL]"
+    && pip3 install -i $PIP_INDEX_URL ".[$DB_GPT_INSTALL_MODEL]" \
+    # install openai for proxyllm
+    && pip3 install -i $PIP_INDEX_URL ".[openai]"
 
 RUN (if [ "${LANGUAGE}" = "zh" ]; \
         # language is zh, download zh_core_web_sm from github
diff --git a/docs/getting_started/install/deploy.rst b/docs/getting_started/install/deploy.rst
index 4d7d0d211..075a07403 100644
--- a/docs/getting_started/install/deploy.rst
+++ b/docs/getting_started/install/deploy.rst
@@ -57,6 +57,12 @@ If you are low hardware requirements you can install DB-GPT by Using third-part
 
     .. tab:: OpenAI
 
+        Installing Dependencies
+
+        .. code-block::
+
+          pip install -e ".[openai]"
+
         Download embedding model
 
         .. code-block:: shell
@@ -69,7 +75,7 @@ If you are low hardware requirements you can install DB-GPT by Using third-part
             or
             git clone https://huggingface.co/moka-ai/m3e-large
 
-        Configure LLM_MODEL and PROXY_API_URL and API_KEY in `.env` file
+        Configure LLM_MODEL, PROXY_API_URL and API_KEY in `.env` file
 
         .. code-block:: shell
 
@@ -291,7 +297,7 @@ If you are low hardware requirements you can install DB-GPT by Using third-part
 
         **1. Download a pre-converted model file.**
 
-        Suppose you want to use [Vicuna 13B v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5), you can download the file already converted from [TheBloke/vicuna-13B-v1.5-GGUF](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF), only one file is needed. Download it to the `models` directory and rename it to `ggml-model-q4_0.gguf`.
+        Suppose you want to use `Vicuna 13B v1.5 <https://huggingface.co/lmsys/vicuna-13b-v1.5>`_ , you can download the file already converted from `TheBloke/vicuna-13B-v1.5-GGUF <https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF>`_ , only one file is needed. Download it to the `models` directory and rename it to `ggml-model-q4_0.gguf`.
 
         .. code-block::
 
@@ -299,7 +305,7 @@ If you are low hardware requirements you can install DB-GPT by Using third-part
 
         **2. Convert It Yourself**
 
-        You can convert the model file yourself according to the instructions in [llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp#prepare-data--run), and put the converted file in the models directory and rename it to `ggml-model-q4_0.gguf`.
+        You can convert the model file yourself according to the instructions in `llama.cpp#prepare-data--run <https://github.com/ggerganov/llama.cpp#prepare-data--run>`_ , and put the converted file in the models directory and rename it to `ggml-model-q4_0.gguf`.
 
         **Installing Dependencies**
 
diff --git a/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy.po b/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy.po
index 2947c34c8..f4c85b8b4 100644
--- a/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy.po
@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: DB-GPT 👏👏 0.4.0\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-11-04 15:08+0800\n"
+"POT-Creation-Date: 2023-11-06 19:38+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -19,27 +19,27 @@ msgstr ""
 "Content-Transfer-Encoding: 8bit\n"
 "Generated-By: Babel 2.12.1\n"
 
-#: ../../getting_started/install/deploy.rst:4 bb7e1a7b70624a3d91804c5ce2d5216b
+#: ../../getting_started/install/deploy.rst:4 f3ea3305f122460aaa11999edc4b5de6
 msgid "Installation From Source"
 msgstr "源码安装"
 
-#: ../../getting_started/install/deploy.rst:6 7524477e8b8a456b8e2b942621a6b225
+#: ../../getting_started/install/deploy.rst:6 bb941f2bd56d4eb48f7c4f75ebd74176
 msgid "To get started, install DB-GPT with the following steps."
 msgstr "按照以下步骤进行安装"
 
-#: ../../getting_started/install/deploy.rst:10 871cdb0a7e004668b518168461d76945
+#: ../../getting_started/install/deploy.rst:10 27a1e092c1f945ceb9946ebdaf89b600
 msgid "1.Preparation"
 msgstr "1.准备"
 
-#: ../../getting_started/install/deploy.rst:11 d845f48ec05a4bb7a5b0f95a0644029d
+#: ../../getting_started/install/deploy.rst:11 5c5bfbdc74a14c3b9b1f1ed66617cac8
 msgid "**Download DB-GPT**"
 msgstr "**下载DB-GPT项目**"
 
-#: ../../getting_started/install/deploy.rst:17 85df7bb2b73141058ba0ca5a73e46701
+#: ../../getting_started/install/deploy.rst:17 3065ee2f34f9417598a37fd699a4863e
 msgid "**Install Miniconda**"
 msgstr "**安装Miniconda**"
 
-#: ../../getting_started/install/deploy.rst:19 b7b3e120ded344d09fb2d7a3a7903497
+#: ../../getting_started/install/deploy.rst:19 f9f3a653ffb8447284686aa37a7bb79a
 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 "
@@ -50,386 +50,397 @@ msgid ""
 "<https://docs.conda.io/en/latest/miniconda.html>`_"
 msgstr ""
 "目前使用Sqlite作为默认数据库，因此DB-"
-"GPT快速部署不需要部署相关数据库服务。如果你想使用其他数据库，需要先部署相关数据库服务。我们目前使用Miniconda进行python环境和包依赖管理[安装"
-" Miniconda](https://docs.conda.io/en/latest/miniconda.html)"
+"GPT快速部署不需要部署相关数据库服务。如果你想使用其他数据库，需要先部署相关数据库服务。我们目前使用Miniconda进行python环境和包依赖管理。`如何安装"
+" Miniconda <https://docs.conda.io/en/latest/miniconda.html>`_ 。"
 
-#: ../../getting_started/install/deploy.rst:36 a5e34db6a6b8450c8a1f35377a1dc93b
+#: ../../getting_started/install/deploy.rst:36 a2cd2fdd1d16421f9cbe341040b153b6
 msgid "2.Deploy LLM Service"
 msgstr "2.部署LLM服务"
 
-#: ../../getting_started/install/deploy.rst:37 5c49829b086e4d5fbcb5a971a34fa3b5
+#: ../../getting_started/install/deploy.rst:37 180a121e3c994a92a917ace80bf12386
 msgid ""
 "DB-GPT can be deployed on servers with low hardware requirements or on "
 "servers with high hardware requirements."
 msgstr "DB-GPT可以部署在对硬件要求不高的服务器，也可以部署在对硬件要求高的服务器"
 
-#: ../../getting_started/install/deploy.rst:39 7c2f7e2b49054d17850942bef9570c45
+#: ../../getting_started/install/deploy.rst:39 395608515c0348d5849030b58da7b659
 msgid ""
 "If you are low hardware requirements you can install DB-GPT by Using "
 "third-part LLM REST API Service OpenAI, Azure, tongyi."
-msgstr "Low hardware requirements模式适用于对接第三方模型服务的api,比如OpenAI, 通义千问, 文心.cpp。"
+msgstr "低硬件要求模式适用于对接第三方模型服务的 API，比如 OpenAI、通义千问、 文心一言等。"
 
-#: ../../getting_started/install/deploy.rst:43 8c392e63073a47698e38456c5994ff25
+#: ../../getting_started/install/deploy.rst:43 e29297e61e2e4d05ba88f0e1c2b1f365
 msgid "As our project has the ability to achieve OpenAI performance of over 85%,"
 msgstr "使用OpenAI服务可以让DB-GPT准确率达到85%"
 
-#: ../../getting_started/install/deploy.rst:48 148f8d85c02345219ac535003fe05fca
+#: ../../getting_started/install/deploy.rst:48 d0d70d51e8684c2891c58a6da4941a52
 msgid "Notice make sure you have install git-lfs"
 msgstr "确认是否已经安装git-lfs"
 
-#: ../../getting_started/install/deploy.rst:50 7f719273d1ff4d888376030531a560c4
+#: ../../getting_started/install/deploy.rst:50 0d2781fd38eb467ebad2a3c310a344e6
 msgid "centos:yum install git-lfs"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:52 f5c2035bca214e3fbef2b70be0e76247
+#: ../../getting_started/install/deploy.rst:52 1574ea24ad6443409070aa3a1f7abe87
 msgid "ubuntu:apt-get install git-lfs"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:54 cb1b52b9323e4e9fbccfd3c42067a568
+#: ../../getting_started/install/deploy.rst:54 ad86473d5c87447091c713f45cbfed0e
 msgid "macos:brew install git-lfs"
 msgstr ""
 
 #: ../../getting_started/install/deploy.rst:58
-#: ../../getting_started/install/deploy.rst:223
-#: 9c601ee0c06646d58cbd2c2fff342cb5 d3fe6c712b4145d0856487c65057c2a0
+#: ../../getting_started/install/deploy.rst:229
+#: 3dd1e40f33924faab63634907a7f6511 dce32420face4ab2b99caf7f3900ede9
 msgid "OpenAI"
 msgstr "OpenAI"
 
-#: ../../getting_started/install/deploy.rst:60
-#: ../../getting_started/install/deploy.rst:207
-#: 5e0e84bd11084d158e18b702022aaa96 6a9c9830e5184eac8b6b7425780f4a3e
+#: ../../getting_started/install/deploy.rst:60 1f66400540114de2820761ef80137805
+msgid "Installing Dependencies"
+msgstr "安装依赖"
+
+#: ../../getting_started/install/deploy.rst:66
+#: ../../getting_started/install/deploy.rst:213
+#: 31b856a6fc094334a37914c046cb1bb1 42b2f6d36ca4487f8e31d59bba123fca
 msgid "Download embedding model"
-msgstr "下载embedding model"
+msgstr "下载 embedding 模型"
 
-#: ../../getting_started/install/deploy.rst:72
-#: ../../getting_started/install/deploy.rst:231
-#: 953d6931627641b985588abf8b6ad9fd d52e287164ca44f79709f4645a1bb774
-msgid "Configure LLM_MODEL and PROXY_API_URL and API_KEY in `.env` file"
-msgstr "在`.env`文件设置LLM_MODEL and PROXY_API_URL and API_KEY"
+#: ../../getting_started/install/deploy.rst:78 f970fb69e47c40d7bda381ec6f045829
+msgid "Configure LLM_MODEL, PROXY_API_URL and API_KEY in `.env` file"
+msgstr "在 `.env` 文件中设置 LLM_MODEL、PROXY_API_URL 和 API_KEY"
 
-#: ../../getting_started/install/deploy.rst:82
-#: ../../getting_started/install/deploy.rst:282
-#: 6dc89616c0bf46a898a49606d1349039 e30b7458fc0d46e8bcf0ec61a2be2e19
+#: ../../getting_started/install/deploy.rst:88
+#: ../../getting_started/install/deploy.rst:288
+#: 6ca04c88fc60480db2ebdc9b234a0bbb 709cfe74c45c4eff83a7d77bb30b4a2b
 msgid "Make sure your .env configuration is not overwritten"
-msgstr "认.env文件不会被覆盖\""
+msgstr "确保你的 .env 文件不会被覆盖"
 
-#: ../../getting_started/install/deploy.rst:85 7adce7ac878d4b1ab9249d840d302520
+#: ../../getting_started/install/deploy.rst:91 147aea0d753f44588f4a0c56002334ab
 msgid "Vicuna"
 msgstr "Vicuna"
 
-#: ../../getting_started/install/deploy.rst:86 44a32c4cd0b140838b49f739d68ff42d
+#: ../../getting_started/install/deploy.rst:92 6a0bd60c4ca2478cb0f3d85aff70cd3b
 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-"
 "13b-v1.5` to try this model)"
 msgstr ""
+"基于 llama-2 的模型 `Vicuna-v1.5 <https://huggingface.co/lmsys/vicuna-"
+"13b-v1.5>`_ 已经发布，我们推荐你通过配置 `LLM_MODEL=vicuna-13b-v1.5` 来尝试这个模型"
 
-#: ../../getting_started/install/deploy.rst:88 f4991de79c434961b0ee777cf42dc491
+#: ../../getting_started/install/deploy.rst:94 6a111c2ef31f41d4b737cf8b6f36fb16
 msgid "vicuna-v1.5 hardware requirements"
-msgstr ""
+msgstr "vicuna-v1.5 的硬件要求"
 
-#: ../../getting_started/install/deploy.rst:92
-#: ../../getting_started/install/deploy.rst:137
-#: 596405ba21d046c993c18d0bcaf95048 ca993a5f1b194707bbe3d5d6e9d670d8
+#: ../../getting_started/install/deploy.rst:98
+#: ../../getting_started/install/deploy.rst:143
+#: dc24c0238ce141df8bdce26cc0e2ddbb e04f1ea4b36940f3a28b66cdff7b702e
 msgid "Model"
-msgstr ""
-
-#: ../../getting_started/install/deploy.rst:93
-#: ../../getting_started/install/deploy.rst:138
-#: 8437bb47daa94ca8a43b0eadc1286842 d040d964198d4c95afa6dd0d86586cc2
-msgid "Quantize"
-msgstr ""
-
-#: ../../getting_started/install/deploy.rst:94
-#: ../../getting_started/install/deploy.rst:139
-#: 453bc4416d89421699d90d940498b9ac 5de996bb955f4c6ca8d5651985ced255
-msgid "VRAM Size"
-msgstr ""
-
-#: ../../getting_started/install/deploy.rst:95
-#: ../../getting_started/install/deploy.rst:98 077d52b8588e4ddd956acb7ff86bc458
-#: fcf0ca75422343d19b12502fb7746f08
-msgid "vicuna-7b-v1.5"
-msgstr ""
-
-#: ../../getting_started/install/deploy.rst:96
-#: ../../getting_started/install/deploy.rst:102
-#: ../../getting_started/install/deploy.rst:141
-#: ../../getting_started/install/deploy.rst:147
-#: 799b310b76454f79a261300253a9bb75 bd98df81ec8941b69c7d1de107154b1b
-#: ca71731754f545d589e506cb53e6f042 d4023553e4384cc4955ef5bf4dc4d05b
-msgid "4-bit"
-msgstr ""
-
-#: ../../getting_started/install/deploy.rst:97
-#: ../../getting_started/install/deploy.rst:142
-#: adfc22d9c6394046bb632831a4a3b066 e4e7762c714a49828da630a5f9d641dc
-msgid "8 GB"
-msgstr ""
+msgstr "模型"
 
 #: ../../getting_started/install/deploy.rst:99
-#: ../../getting_started/install/deploy.rst:105
 #: ../../getting_started/install/deploy.rst:144
-#: ../../getting_started/install/deploy.rst:150
-#: 0d6bd1c4a6464df38723de978c09e8bc 106e20f7727f43d280b7560dc0f19bbc
-#: 5a95691d1d134638bffa478daf2577a0 f8add03506244306b1ac6e10c5a2bc1f
-msgid "8-bit"
-msgstr ""
+#: b6473e65ca1a437a84226531be4da26d e0a2f7580685480aa13ca462418764d3
+msgid "Quantize"
+msgstr "量化"
 
 #: ../../getting_started/install/deploy.rst:100
-#: ../../getting_started/install/deploy.rst:103
 #: ../../getting_started/install/deploy.rst:145
-#: ../../getting_started/install/deploy.rst:148
-#: 03222e6a682e406bb56c21025412fbe5 2eb88af3efb74fb79899d7818a79d177
-#: 9705b9d7d2084f0b8867f6aeec66251b bca6e5151e244a318f4c2078c3f82118
-msgid "12 GB"
-msgstr ""
+#: 56471c3b174d4adf9e8cb5bebaa300a6 d82297b8b9c148c3906d8ee4ed10d8a0
+msgid "VRAM Size"
+msgstr "显存"
 
 #: ../../getting_started/install/deploy.rst:101
 #: ../../getting_started/install/deploy.rst:104
-#: 1596cbb77c954d1db00e2fa283d66a9a c6e8dc1600d14ee5a47f45f75ec709f4
-msgid "vicuna-13b-v1.5"
+#: 1214432602fe47a28479ce3e21a7d88b 51838e72e42248f199653f1bf08c8155
+msgid "vicuna-7b-v1.5"
+msgstr ""
+
+#: ../../getting_started/install/deploy.rst:102
+#: ../../getting_started/install/deploy.rst:108
+#: ../../getting_started/install/deploy.rst:147
+#: ../../getting_started/install/deploy.rst:153
+#: a64439f4e6f64c42bb76fbb819556784 ed95f498641e4a0f976318df608a1d67
+#: fc400814509048b4a1cbe1e07c539285 ff7a8cb2cce8438cb6cb0d80dabfc2b5
+msgid "4-bit"
+msgstr ""
+
+#: ../../getting_started/install/deploy.rst:103
+#: ../../getting_started/install/deploy.rst:148
+#: 2726e8a278c34e6db59147e9f66f2436 5feab5755a41403c9d641da697de4651
+msgid "8 GB"
+msgstr ""
+
+#: ../../getting_started/install/deploy.rst:105
+#: ../../getting_started/install/deploy.rst:111
+#: ../../getting_started/install/deploy.rst:150
+#: ../../getting_started/install/deploy.rst:156
+#: 1984406682da4da3ad7b275e44085d07 2f027d838d0c46409e54c066d7983aae
+#: 5c5878fe64944872b6769f075fedca05 e2507408a9c5423988e17b7029b487e4
+msgid "8-bit"
 msgstr ""
 
 #: ../../getting_started/install/deploy.rst:106
+#: ../../getting_started/install/deploy.rst:109
 #: ../../getting_started/install/deploy.rst:151
-#: 00ee98593b7f4b29b5d97fa5a323bfa1 0169214dcf8d46c791b3482c81283fa0
+#: ../../getting_started/install/deploy.rst:154
+#: 332f50702c7b46e79ea0af5cbf86c6d5 381d23253cfd40109bacefca6a179f91
+#: aafe2423c25546e789e4804e3fd91d1d cc56990a58e941d6ba023cbd4dca0357
+msgid "12 GB"
+msgstr ""
+
+#: ../../getting_started/install/deploy.rst:107
+#: ../../getting_started/install/deploy.rst:110
+#: 1f14e2fa6d41493cb208f55eddff9773 6457f6307d8546beb5f2fb69c30922d8
+msgid "vicuna-13b-v1.5"
+msgstr ""
+
+#: ../../getting_started/install/deploy.rst:112
+#: ../../getting_started/install/deploy.rst:157
+#: e24d3a36b5ce4cfe861dce2d1c4db592 f2e66b2da7954aaab0ee526b25a371f5
 msgid "20 GB"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:122
-#: ../../getting_started/install/deploy.rst:169
-#: ../../getting_started/install/deploy.rst:195
-#: 852f800e380c44d3b1b5bdaa881406b7 89ddd6c4a4874f4f8b7f051d797e364a
-#: a2b4436f8fcb44ada3b5bf5c1099e646
+#: ../../getting_started/install/deploy.rst:128
+#: ../../getting_started/install/deploy.rst:175
+#: ../../getting_started/install/deploy.rst:201
+#: 1719c11f92874c47a87c00c634b9fad8 4596fcbe415d42fdbb29b92964fae070
+#: e639ae6076a64b7b9de08527966e4550
 msgid "The model files are large and will take a long time to download."
-msgstr ""
+msgstr "这个模型权重文件比较大，需要花费较长时间来下载。"
 
-#: ../../getting_started/install/deploy.rst:124
-#: ../../getting_started/install/deploy.rst:171
-#: ../../getting_started/install/deploy.rst:197
-#: 18ccf7acdf3045588a19866c0161f44b 3d3d93649ec943c8b2b725807e969cbf
-#: 6205975466f54d8fbf8e30b58df6b9c2
+#: ../../getting_started/install/deploy.rst:130
+#: ../../getting_started/install/deploy.rst:177
+#: ../../getting_started/install/deploy.rst:203
+#: 4ec1492d389f403ebd9dd805fcaac68e ac6c68e2bf9b47c694ea8e0506014b10
+#: e39be72282e64760903aaba45f8effb8
 msgid "**Configure LLM_MODEL in `.env` file**"
-msgstr ""
+msgstr "**在 `.env` 文件中配置 LLM_MODEL**"
 
-#: ../../getting_started/install/deploy.rst:131
-#: ../../getting_started/install/deploy.rst:228
-#: 022addaea4ea432584b8a27ea83a9dc4 7a95d25c58d2491e855dff42f6d3a686
+#: ../../getting_started/install/deploy.rst:137
+#: ../../getting_started/install/deploy.rst:234
+#: 7ce4e2253ef24a7ea890ade04ce36682 b9d5bf4fa09649c4a098503132ce7c0c
 msgid "Baichuan"
-msgstr ""
+msgstr "百川"
 
-#: ../../getting_started/install/deploy.rst:133
-#: b5374f6d0ca44ee9bd984c0198515861
+#: ../../getting_started/install/deploy.rst:139
+#: ffdad6a70558457fa825bad4d811100d
 msgid "Baichuan hardware requirements"
-msgstr ""
-
-#: ../../getting_started/install/deploy.rst:140
-#: ../../getting_started/install/deploy.rst:143
-#: 6a5e6034c185455d81e8ba5349dbc191 9d0109817c524747909417924bb0bd31
-msgid "baichuan-7b"
-msgstr ""
+msgstr "百川 的硬件要求"
 
 #: ../../getting_started/install/deploy.rst:146
 #: ../../getting_started/install/deploy.rst:149
-#: b3300ed57f0c4ed98816652ea4a5c3c8 d57e98b46fb14f649d6ac8df27edcfd8
+#: 59d9b64f54d34971a68e93e3101def06 a66ce354d8f143ce920303241cd8947e
+msgid "baichuan-7b"
+msgstr ""
+
+#: ../../getting_started/install/deploy.rst:152
+#: ../../getting_started/install/deploy.rst:155
+#: c530662259ca4ec5b03a18e4b690e17a fa3af65ecca54daab961f55729bbc40e
 msgid "baichuan-13b"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:173
-#: ac684ccbea7d4f5380c43ad02a1b7231
+#: ../../getting_started/install/deploy.rst:179
+#: efd73637994a4b7c97ef3557e1f3161c
 msgid "please rename Baichuan path to \"baichuan2-13b\" or \"baichuan2-7b\""
 msgstr "将Baichuan模型目录修改为\"baichuan2-13b\" 或 \"baichuan2-7b\""
 
-#: ../../getting_started/install/deploy.rst:179
-#: d2e283112ed1440b93510c331922b37c
+#: ../../getting_started/install/deploy.rst:185
+#: 435a3f0d0fe84b49a7305e2c0f51a5df
 msgid "ChatGLM"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:199
-#: ae30d065461e446e86b02d3903108a02
-msgid "please rename chatglm model path to \"chatglm2-6b\""
-msgstr "将chatglm模型目录修改为\"chatglm2-6b\""
-
 #: ../../getting_started/install/deploy.rst:205
-#: 81a8983e89c4400abc20080c86865c02
+#: 165e23d3d40d4756b5a6a2580d015213
+msgid "please rename chatglm model path to \"chatglm2-6b\""
+msgstr "将 chatglm 模型目录修改为\"chatglm2-6b\""
+
+#: ../../getting_started/install/deploy.rst:211
+#: b651ebb5e0424b8992bc8b49d2280bee
 msgid "Other LLM API"
-msgstr ""
+msgstr "其它模型 API"
 
-#: ../../getting_started/install/deploy.rst:219
-#: 3df3d5e0e4f64813a7ca2adccd056c4a
+#: ../../getting_started/install/deploy.rst:225
+#: 4eabdc25f4a34676b3ece620c88d866f
 msgid "Now DB-GPT support LLM REST API TYPE:"
-msgstr "目前DB-GPT支持的大模型REST API类型:"
+msgstr "目前DB-GPT支持的大模型 REST API 类型:"
 
-#: ../../getting_started/install/deploy.rst:224
-#: 4f7cb7a3f324410d8a34ba96d7c9536a
+#: ../../getting_started/install/deploy.rst:230
+#: d361963cc3404e5ca55a823f1f1f545c
 msgid "Azure"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:225
-#: ee6cbe48a8094637b6b8a049446042c6
+#: ../../getting_started/install/deploy.rst:231
+#: 3b0f17c74aaa4bbd9db935973fa1c36b
 msgid "Aliyun tongyi"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:226
-#: a3d9c061b0f440258be88cc3143b1887
+#: ../../getting_started/install/deploy.rst:232
+#: 7c4c457a499943b8804e31046551006d
 msgid "Baidu wenxin"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:227
-#: 176001fb6eaf448f9eca1abd256b3ef4
+#: ../../getting_started/install/deploy.rst:233
+#: ac1880a995184295acf07fff987d7c56
 msgid "Zhipu"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:229
-#: 17fecc140be2474ea1566d44641a27c0
+#: ../../getting_started/install/deploy.rst:235
+#: 6927500d7d3445b7b1981da1df4e1666
 msgid "Bard"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:284
-#: bc34832cec754984a40c4d01526f0f83
+#: ../../getting_started/install/deploy.rst:237
+#: 419d564de18c485780d9336b852735b6
+msgid "Configure LLM_MODEL and PROXY_API_URL and API_KEY in `.env` file"
+msgstr "在`.env`文件设置 LLM_MODEL、PROXY_API_URL和 API_KEY"
+
+#: ../../getting_started/install/deploy.rst:290
+#: 71d5203682e24e2e896e4b9913471f78
 msgid "llama.cpp"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:286
-#: aa4b14e726dc447f92dec48f38a3d770
+#: ../../getting_started/install/deploy.rst:292
+#: 36a2b82f711a4c0f9491aca9c84d3c91
 msgid ""
 "DB-GPT already supports `llama.cpp "
 "<https://github.com/ggerganov/llama.cpp>`_ via `llama-cpp-python "
 "<https://github.com/abetlen/llama-cpp-python>`_ ."
 msgstr ""
-"DB-GPT 已经支持了 `llama.cpp <https://github.com/ggerganov/llama.cpp>`_ via "
-"`llama-cpp-python <https://github.com/abetlen/llama-cpp-python>`_ ."
+"DB-GPT 已经通过 `llama-cpp-python <https://github.com/abetlen/llama-cpp-"
+"python>`_ 支持了 `llama.cpp <https://github.com/ggerganov/llama.cpp>`_ 。"
 
-#: ../../getting_started/install/deploy.rst:288
-#: e97a868ad05b48ee8d25017457c1b7ee
+#: ../../getting_started/install/deploy.rst:294
+#: 439064115dca4ae08d8e60041f2ffe17
 msgid "**Preparing Model Files**"
-msgstr "**准备Model文件**"
+msgstr "**准备模型文件**"
 
-#: ../../getting_started/install/deploy.rst:290
-#: 8efc7824082545a4a98ebbd6b12fa00f
+#: ../../getting_started/install/deploy.rst:296
+#: 7291d6fa20b34942926e7765c01f25c9
 msgid ""
 "To use llama.cpp, you need to prepare a gguf format model file, and there"
 " are two common ways to obtain it, you can choose either:"
-msgstr "使用 llama.cpp，你需要准备 gguf 格式的文件，你可以通过以下两种方法获取"
+msgstr "为了使用 llama.cpp，你需要准备 gguf 格式的文件，你可以通过以下两种方法获取"
 
-#: ../../getting_started/install/deploy.rst:292
-#: 5b9f3a35779c4f89a4b9051904c5f7d8
+#: ../../getting_started/install/deploy.rst:298
+#: 45752f3f5dd847469da0c5edddc530fa
 msgid "**1. Download a pre-converted model file.**"
 msgstr "**1.下载已转换的模型文件.**"
 
-#: ../../getting_started/install/deploy.rst:294
-#: e15f33a2e5fc4caaa9ad2e10cabf9d32
+#: ../../getting_started/install/deploy.rst:300
+#: c451db2157ff49b2b4992aed9907ddfa
 msgid ""
-"Suppose you want to use [Vicuna 13B v1.5](https://huggingface.co/lmsys"
-"/vicuna-13b-v1.5), you can download the file already converted from "
-"[TheBloke/vicuna-13B-v1.5-GGUF](https://huggingface.co/TheBloke/vicuna-"
-"13B-v1.5-GGUF), only one file is needed. Download it to the `models` "
+"Suppose you want to use `Vicuna 13B v1.5 <https://huggingface.co/lmsys"
+"/vicuna-13b-v1.5>`_ , you can download the file already converted from "
+"`TheBloke/vicuna-13B-v1.5-GGUF <https://huggingface.co/TheBloke/vicuna-"
+"13B-v1.5-GGUF>`_ , only one file is needed. Download it to the `models` "
 "directory and rename it to `ggml-model-q4_0.gguf`."
 msgstr ""
-"假设您想使用[Vicuna 13B v1.5](https://huggingface.co/lmsys/vicuna-"
-"13b-v1.5)您可以从[TheBloke/vicuna-"
-"13B-v1.5-GGUF](https://huggingface.co/TheBloke/vicuna-"
-"13B-v1.5-GGUF)下载已转换的文件，只需要一个文件。将其下载到models目录并将其重命名为 `ggml-"
+"假设您想使用 `Vicuna 13B v1.5 <https://huggingface.co/lmsys/vicuna-"
+"13b-v1.5>`_ 您可以从 `TheBloke/vicuna-"
+"13B-v1.5-GGUF <https://huggingface.co/TheBloke/vicuna-"
+"13B-v1.5-GGUF>`_ 下载已转换的文件，只需要一个文件。将其下载到models目录并将其重命名为 `ggml-"
 "model-q4_0.gguf`。"
 
-#: ../../getting_started/install/deploy.rst:300
-#: 81ab603cd9b94cabb48add9541590b8b
+#: ../../getting_started/install/deploy.rst:306
+#: f5b92b51622b43d398b3dc13a5892c29
 msgid "**2. Convert It Yourself**"
 msgstr "**2. 自行转换**"
 
-#: ../../getting_started/install/deploy.rst:302
-#: f9b46aa70a0842d6acc7e837c8b27778
+#: ../../getting_started/install/deploy.rst:308
+#: 8838ae6dcecf44ecad3fd963980c8eb3
 msgid ""
 "You can convert the model file yourself according to the instructions in "
-"[llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp"
-"#prepare-data--run), and put the converted file in the models directory "
-"and rename it to `ggml-model-q4_0.gguf`."
+"`llama.cpp#prepare-data--run <https://github.com/ggerganov/llama.cpp"
+"#prepare-data--run>`_ , and put the converted file in the models "
+"directory and rename it to `ggml-model-q4_0.gguf`."
 msgstr ""
-"您可以根据[llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp"
-"#prepare-data--run)中的说明自行转换模型文件，并把转换后的文件放在models目录中，并重命名为`ggml-"
+"您可以根据 `llama.cpp#prepare-data--run <https://github.com/ggerganov/llama.cpp"
+"#prepare-data--run>`_ 中的说明自行转换模型文件，并把转换后的文件放在models目录中，并重命名为`ggml-"
 "model-q4_0.gguf`。"
 
-#: ../../getting_started/install/deploy.rst:304
-#: 5278c05568dd4ad688bcc181e45caa18
+#: ../../getting_started/install/deploy.rst:310
+#: 3fe28d6e5eaa4bdf9c5c44a914c3577c
 msgid "**Installing Dependencies**"
 msgstr "**安装依赖**"
 
-#: ../../getting_started/install/deploy.rst:306
-#: bd67bf651a9a4096a37e73851b5fad98
+#: ../../getting_started/install/deploy.rst:312
+#: bdc10d2e88cc4c3f84a8c4a8dc2037a9
 msgid ""
 "llama.cpp is an optional dependency in DB-GPT, and you can manually "
 "install it using the following command:"
 msgstr "llama.cpp在DB-GPT中是可选安装项, 你可以通过以下命令进行安装"
 
-#: ../../getting_started/install/deploy.rst:313
-#: 71ed6ae4d0aa4d3ca27ebfffc42a5095
+#: ../../getting_started/install/deploy.rst:319
+#: 9c136493448b43b5b27f66af74ff721e
 msgid "**3.Modifying the Configuration File**"
 msgstr "**3.修改配置文件**"
 
-#: ../../getting_started/install/deploy.rst:315
-#: a0a2fdb799524ef4938df2c306536e2a
+#: ../../getting_started/install/deploy.rst:321
+#: c835a7dee1dd409fb861e7b886c6dc5b
 msgid "Next, you can directly modify your `.env` file to enable llama.cpp."
 msgstr "修改`.env`文件使用llama.cpp"
 
-#: ../../getting_started/install/deploy.rst:322
-#: ../../getting_started/install/deploy.rst:390
-#: 03694cbb7dfa432cb32116925357f008
+#: ../../getting_started/install/deploy.rst:328
+#: ../../getting_started/install/deploy.rst:396
+#: 296e6d08409544918fee0c31b1bf195c a81e5d882faf4722b0e10d53f635f53c
 msgid ""
 "Then you can run it according to `Run <https://db-"
 "gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html#run>`_"
 msgstr ""
-"然后你可以根据[运行](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-"
-"cn/zh_CN/latest/getting_started/install/deploy/deploy.html#run)来运行"
+"然后你可以根据 `运行 <https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-"
+"cn/zh_CN/latest/getting_started/install/deploy/deploy.html#run>`_ 来运行。"
 
-#: ../../getting_started/install/deploy.rst:325
-#: c9bbc15ea2fc4562bdf87a4e099600a0
+#: ../../getting_started/install/deploy.rst:331
+#: 0f7f487ee11a4e01a95f7c504f0469ba
 msgid "**More Configurations**"
 msgstr "**更多配置文件**"
 
-#: ../../getting_started/install/deploy.rst:327
-#: 9beff887d8554d1dac169de93625c1b2
+#: ../../getting_started/install/deploy.rst:333
+#: b0f9964497f64fb5b3740099232cd72b
 msgid ""
 "In DB-GPT, the model configuration can be done through  `{model "
 "name}_{config key}`."
 msgstr "在DB-GPT中，模型配置可以通过`{模型名称}_{配置名}` 来配置。"
 
-#: ../../getting_started/install/deploy.rst:329
-#: 6cad64bcc9f141de85479203b21f7f9e
+#: ../../getting_started/install/deploy.rst:335
+#: 7c225de4fe9d4dd3a3c2b2a33802e656
 msgid "More Configurations"
 msgstr "**更多配置文件**"
 
-#: ../../getting_started/install/deploy.rst:333
-#: de97b0d5b59c4bfabbd47b7e1766cc70
+#: ../../getting_started/install/deploy.rst:339
+#: 5cc1671910314796a9ce0b5107d3c9fe
 msgid "Environment Variable Key"
 msgstr "环境变量Key"
 
-#: ../../getting_started/install/deploy.rst:334
-#: 76afa3655f644576b54b4422bad3fcad
+#: ../../getting_started/install/deploy.rst:340
+#: 4359ed4e11bb47ad89a605cbf9016cd5
 msgid "Default"
 msgstr "默认值"
 
-#: ../../getting_started/install/deploy.rst:335
-#: 0dcabfeeb4874e08ba53d4b4aa6a1d73
+#: ../../getting_started/install/deploy.rst:341
+#: 5cf0efc6d1014665bb9dbdae96bf2726
 msgid "Description"
 msgstr "描述"
 
-#: ../../getting_started/install/deploy.rst:336
-#: c1670aec27cf4c068d825456817d7667
+#: ../../getting_started/install/deploy.rst:342
+#: e7c291f80a9a40fa90d642901eca02c6
 msgid "llama_cpp_prompt_template"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:337
-#: ../../getting_started/install/deploy.rst:340
+#: ../../getting_started/install/deploy.rst:343
 #: ../../getting_started/install/deploy.rst:346
 #: ../../getting_started/install/deploy.rst:352
 #: ../../getting_started/install/deploy.rst:358
-#: 49c8f875066f49c6aac195805f88e4a9
+#: ../../getting_started/install/deploy.rst:364
+#: 07dc7fc4e51e4d9faf8e5221bcf03ee0 549f3c57a2e9427880e457e653ce1182
+#: 7ad961957f7b49d08e4aff347749b78d c1eab368175c4fa88fe0b471919523b2
+#: e2e0bf9903484972b6d20e6837010029
 msgid "None"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:338
-#: bb31e19533e5434b832d5975bf579dc3
+#: ../../getting_started/install/deploy.rst:344
+#: 6b5044a2009f432c92fcd65db42506d8
 msgid ""
 "Prompt template name, now support: zero_shot, vicuna_v1.1,alpaca,llama-2"
 ",baichuan-chat,internlm-chat, If None, the prompt template is "
@@ -438,183 +449,183 @@ msgstr ""
 "Prompt template 现在可以支持`zero_shot, vicuna_v1.1,alpaca,llama-2,baichuan-"
 "chat,internlm-chat`, 如果是None, 可以根据模型路径来自动获取模型 Prompt template"
 
-#: ../../getting_started/install/deploy.rst:339
-#: 38ed23e19e2a47cf8fbacb035cfe1292
+#: ../../getting_started/install/deploy.rst:345
+#: e01c860441ad43b88c0a8d012f97d2d8
 msgid "llama_cpp_model_path"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:341
-#: eb069fdfdfeb4b17b723ee6733ba50c2
+#: ../../getting_started/install/deploy.rst:347
+#: 1cb68d772e454812a1a0c6de4950b8ce
 msgid "Model path"
 msgstr "模型路径"
 
-#: ../../getting_started/install/deploy.rst:342
-#: 348d3ff3e4f44ceb99aadead11f5cca5
+#: ../../getting_started/install/deploy.rst:348
+#: 6dac03820edb4fbd8a0856405e84c5bc
 msgid "llama_cpp_n_gpu_layers"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:343
-#: 007deecf593b4553b6ca8df3e9240a28
+#: ../../getting_started/install/deploy.rst:349
+#: 8cd5607b7941427f9a342ca7a00e5778
 msgid "1000000000"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:344
-#: 4da435c417f0482581895bf4d052a6a1
+#: ../../getting_started/install/deploy.rst:350
+#: 61c9297656da434aa7ac2b49cf61ea9d
 msgid ""
 "Number of layers to offload to the GPU, Set this to 1000000000 to offload"
 " all layers to the GPU. If your GPU VRAM is not enough, you can set a low"
 " number, eg: 10"
 msgstr "要将多少网络层转移到GPU上，将其设置为1000000000以将所有层转移到GPU上。如果您的 GPU 内存不足，可以设置较低的数字，例如：10。"
 
-#: ../../getting_started/install/deploy.rst:345
-#: 4f186505ea81467590cf817d116e6879
+#: ../../getting_started/install/deploy.rst:351
+#: 8c2d2182557a483aa2fda590c24faaf3
 msgid "llama_cpp_n_threads"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:347
-#: b94dc2fb2cd14a4a8f38ba95b05fbb5b
+#: ../../getting_started/install/deploy.rst:353
+#: cc442f61ffc442ecbd98c1e7f5598e1a
 msgid ""
 "Number of threads to use. If None, the number of threads is automatically"
 " determined"
 msgstr "要使用的线程数量。如果为None，则线程数量将自动确定。"
 
-#: ../../getting_started/install/deploy.rst:348
-#: 867f2357430440eba4e749a8a39bff18
+#: ../../getting_started/install/deploy.rst:354
+#: 8d5e917d86f048348106e6923638a0c2
 msgid "llama_cpp_n_batch"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:349
-#: 78516f7b23264147bae11e13426097eb
+#: ../../getting_started/install/deploy.rst:355
+#: ee2719a0a8cd4a77846cffd8e675638f
 msgid "512"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:350
-#: c2ec97ffef3e4a70afef6634e78801a2
+#: ../../getting_started/install/deploy.rst:356
+#: 845b354315384762a611ad2daa539d57
 msgid "Maximum number of prompt tokens to batch together when calling llama_eval"
 msgstr "在调用llama_eval时，批处理在一起的prompt tokens的最大数量"
 
-#: ../../getting_started/install/deploy.rst:351
-#: 29ad3c5ab7134da49d6fca3b42d734d6
+#: ../../getting_started/install/deploy.rst:357
+#: a95e788bfa5f46f3bcd6356dfd9f87eb
 msgid "llama_cpp_n_gqa"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:353
-#: e5bc322b0c824465b1adbd162838a3b7
+#: ../../getting_started/install/deploy.rst:359
+#: 23ad9b5f34b5440bb90b2b21bab25763
 msgid "Grouped-query attention. Must be 8 for llama-2 70b."
 msgstr "对于 llama-2 70B 模型，Grouped-query attention 必须为8。"
 
-#: ../../getting_started/install/deploy.rst:354
-#: 43e7d412238a4f0ba8227938d9fa4172
+#: ../../getting_started/install/deploy.rst:360
+#: 9ce25b7966fc40ec8be47ecfaf5f9994
 msgid "llama_cpp_rms_norm_eps"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:355
-#: 6328db04645b4b089593291e2ca13f79
+#: ../../getting_started/install/deploy.rst:361
+#: 58365f0d36af447ba976213646018431
 msgid "5e-06"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:356
-#: 6c8bf631cece42fa86954f5cf2d75503
+#: ../../getting_started/install/deploy.rst:362
+#: d00b742a759140b795ba5949f1ce9a36
 msgid "5e-6 is a good value for llama-2 models."
 msgstr "对于llama-2模型来说，5e-6是一个不错的值。"
 
-#: ../../getting_started/install/deploy.rst:357
-#: 22ebee39fe8b4cc18378447cac67e631
+#: ../../getting_started/install/deploy.rst:363
+#: b9972e9b19354f55a5e6d9c50513a620
 msgid "llama_cpp_cache_capacity"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:359
-#: 4dc98bede90f4237829f65513e4adf61
+#: ../../getting_started/install/deploy.rst:365
+#: 3c98c5396dd74db8b6d70fc50fa0754f
 msgid "Maximum cache capacity. Examples: 2000MiB, 2GiB"
 msgstr "模型缓存最大值. 例如: 2000MiB, 2GiB"
 
-#: ../../getting_started/install/deploy.rst:360
-#: bead617b5af943dab0bc1209823d3c22
+#: ../../getting_started/install/deploy.rst:366
+#: 4277e155992c4442b69d665d6269bed6
 msgid "llama_cpp_prefer_cpu"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:361
-#: 8efb44f1cfc54b1a8b3ca8ea138113ee
+#: ../../getting_started/install/deploy.rst:367
+#: 049169c1210a4ecabb25702ed813ea0a
 msgid "False"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:362
-#: b854e6a44c8348ceb72ac382b73ceec5
+#: ../../getting_started/install/deploy.rst:368
+#: 60a39e93e7874491a93893de78b7d37e
 msgid ""
 "If a GPU is available, it will be preferred by default, unless "
 "prefer_cpu=False is configured."
 msgstr "如果有可用的GPU，默认情况下会优先使用GPU，除非配置了 prefer_cpu=False。"
 
-#: ../../getting_started/install/deploy.rst:365
-#: 41b0440eb0074e5fa8c87dd404efe0ce
+#: ../../getting_started/install/deploy.rst:371
+#: 7c86780fbf634de8873afd439389cf89
 msgid "vllm"
 msgstr ""
 
-#: ../../getting_started/install/deploy.rst:367
-#: 6fc445675bf74b2ea2fe0c7f2a64db69
+#: ../../getting_started/install/deploy.rst:373
+#: e2827892e43d420c85b8b83c4855d197
 msgid "vLLM is a fast and easy-to-use library for LLM inference and serving."
-msgstr "\"vLLM 是一个快速且易于使用的 LLM 推理和服务的库。"
+msgstr "vLLM 是一个快速且易于使用的 LLM 推理和服务的库。"
 
-#: ../../getting_started/install/deploy.rst:369
-#: aab5f913d29445c4b345180b8793ebc7
+#: ../../getting_started/install/deploy.rst:375
+#: 81bbfa3876a74244acc82d295803fdd4
 msgid "**Running vLLM**"
 msgstr "**运行vLLM**"
 
-#: ../../getting_started/install/deploy.rst:371
-#: a9560d697821404cb0abdabf9f479645
+#: ../../getting_started/install/deploy.rst:377
+#: 75bc518b444c417ba4d9c15246549327
 msgid "**1.Installing Dependencies**"
 msgstr "**1.安装依赖**"
 
-#: ../../getting_started/install/deploy.rst:373
-#: b008224d4f314e5c988335262c95a42e
+#: ../../getting_started/install/deploy.rst:379
+#: 725c620b0a5045c1a64a3b2a2e9b48f3
 msgid ""
 "vLLM is an optional dependency in DB-GPT, and you can manually install it"
 " using the following command:"
 msgstr "vLLM 在 DB-GPT 是一个可选依赖, 你可以使用下面的命令手动安装它："
 
-#: ../../getting_started/install/deploy.rst:379
-#: 7dc0c8e996124177935a4e0d9ef19837
+#: ../../getting_started/install/deploy.rst:385
+#: 6f4b540107764f3592cc07cf170e4911
 msgid "**2.Modifying the Configuration File**"
 msgstr "**2.修改配置文件**"
 
-#: ../../getting_started/install/deploy.rst:381
-#: 49667576b44c46bf87d5bf4d207dd63a
+#: ../../getting_started/install/deploy.rst:387
+#: b8576a1572674c4890e09b73e02cf0e8
 msgid "Next, you can directly modify your .env file to enable vllm."
 msgstr "你可以直接修改你的 `.env` 文件"
 
-#: ../../getting_started/install/deploy.rst:388
-#: f16a78f0ee6545babab0d66f12654c0a
+#: ../../getting_started/install/deploy.rst:394
+#: b006745f3aee4651aaa0cf79081b5d7f
 msgid ""
 "You can view the models supported by vLLM `here "
 "<https://vllm.readthedocs.io/en/latest/models/supported_models.html"
 "#supported-models>`_"
 msgstr ""
-"你可以在 "
-"[这里](https://vllm.readthedocs.io/en/latest/models/supported_models.html"
-"#supported-models) 查看 vLLM 支持的模型。"
+"你可以在 `这里 "
+"<https://vllm.readthedocs.io/en/latest/models/supported_models.html"
+"#supported-models>`_ 查看 vLLM 支持的模型。"
 
-#: ../../getting_started/install/deploy.rst:397
-#: f7ae366723e9494d8177eeb963ba0ed9
+#: ../../getting_started/install/deploy.rst:403
+#: bc8057ee75e14737bf8fca3ceb555dac
 msgid "3.Prepare sql example(Optional)"
 msgstr "3.准备 sql example(可选)"
 
-#: ../../getting_started/install/deploy.rst:398
-#: d302aac8ddb346598fc9d73e0f6c2cbc
+#: ../../getting_started/install/deploy.rst:404
+#: 9b0b9112237c4b3aaa1dd5d704ea32e6
 msgid "**(Optional) load examples into SQLite**"
-msgstr "**(可选) load examples into SQLite**"
+msgstr "**(可选) 加载样例数据到 SQLite 数据库中**"
 
-#: ../../getting_started/install/deploy.rst:405
-#: ae2a315e40854f27a074f2c0f2506014
+#: ../../getting_started/install/deploy.rst:411
+#: 0815e13b96264ffcba1526c82ba2e7c8
 msgid "On windows platform:"
-msgstr ""
+msgstr "在 Windows 平台："
 
-#: ../../getting_started/install/deploy.rst:412
-#: 36b4b7a813844af3a4ec8062b39059a3
+#: ../../getting_started/install/deploy.rst:418
+#: 577a4167ecac4fa88586961f225f0487
 msgid "4.Run db-gpt server"
 msgstr "4.运行db-gpt server"
 
-#: ../../getting_started/install/deploy.rst:418
-#: e56f15e563484027b7efb2147c9b71a7
+#: ../../getting_started/install/deploy.rst:424
+#: a9f96b064b674f80824257b4b0a18e2a
 msgid "**Open http://localhost:5000 with your browser to see the product.**"
 msgstr "打开浏览器访问http://localhost:5000"
 
@@ -633,3 +644,9 @@ msgstr "打开浏览器访问http://localhost:5000"
 #~ " LLM model."
 #~ msgstr ""
 
+#~ msgid "百川"
+#~ msgstr ""
+
+#~ msgid "百川 硬件要求"
+#~ msgstr ""
+
diff --git a/docs/locales/zh_CN/LC_MESSAGES/index.po b/docs/locales/zh_CN/LC_MESSAGES/index.po
index d210535e7..1badfc0e4 100644
--- a/docs/locales/zh_CN/LC_MESSAGES/index.po
+++ b/docs/locales/zh_CN/LC_MESSAGES/index.po
@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: DB-GPT 0.3.0\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-10-25 23:56+0800\n"
+"POT-Creation-Date: 2023-11-06 19:00+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -19,31 +19,27 @@ msgstr ""
 "Content-Transfer-Encoding: 8bit\n"
 "Generated-By: Babel 2.12.1\n"
 
-#: ../../index.rst:34 ../../index.rst:45 71dd3acc56354242aad5a920c2805328
+#: ../../index.rst:34 ../../index.rst:45 8bc3a47457a34995816985436034e233
 msgid "Getting Started"
 msgstr "开始"
 
-#: ../../index.rst:60 ../../index.rst:81 0f2fc16a44b043019556f5f3e0d0e2c0
+#: ../../index.rst:60 ../../index.rst:81 1a4e8a5dc7754967a0af9fb3d2e53017
 msgid "Modules"
 msgstr "模块"
 
-#: ../../index.rst:95 ../../index.rst:111 2624521b920a4b3b9eac3fec76635ab8
-msgid "Use Cases"
-msgstr "示例"
-
-#: ../../index.rst:125 ../../index.rst:128 accec2bb9c5149f184a87e03955d6b22
+#: ../../index.rst:96 ../../index.rst:99 c815772ae8514f0c9b26911b0dd73f54
 msgid "Reference"
 msgstr "参考"
 
-#: ../../index.rst:138 ../../index.rst:144 26278dabd4944d1a9f14330e83935162
+#: ../../index.rst:109 ../../index.rst:115 dabe4c3409df489f84e4ec588f2b34a5
 msgid "Resources"
 msgstr "资源"
 
-#: ../../index.rst:7 9277d505dda74ae0862cd09d05cf5e63
+#: ../../index.rst:7 7626b01b253546ac83ca0cf130dfa091
 msgid "Welcome to DB-GPT!"
 msgstr "欢迎来到DB-GPT中文文档"
 
-#: ../../index.rst:8 9fa76a01965746978a00ac411fca13a8
+#: ../../index.rst:8 6037e5e0d7f7428ba92315a91ccfd53f
 msgid ""
 "As large models are released and iterated upon, they are becoming "
 "increasingly intelligent. However, in the process of using large models, "
@@ -61,7 +57,7 @@ msgstr ""
 "，我们启动了DB-"
 "GPT项目，为所有基于数据库的场景构建一个完整的私有大模型解决方案。该方案“”支持本地部署，既可应用于“独立私有环境”，又可根据业务模块进行“独立部署”和“隔离”，确保“大模型”的能力绝对私有、安全、可控。"
 
-#: ../../index.rst:10 b12b6f91c5664f61aa9e4d7cd500b922
+#: ../../index.rst:10 ab2a181d517047e6992171786c83f8e3
 msgid ""
 "**DB-GPT** is an experimental open-source project that uses localized GPT"
 " large models to interact with your data and environment. With this "
@@ -71,39 +67,39 @@ msgstr ""
 "DB-GPT 是一个开源的以数据库为基础的GPT实验项目，使用本地化的GPT大模型与您的数据和环境进行交互，无数据泄露风险100% 私密，100%"
 " 安全。"
 
-#: ../../index.rst:12 7032e17191394f7090141927644fb512
+#: ../../index.rst:12 9cfb7515430d49af8a1ca47f60264a58
 msgid "**Features**"
 msgstr "特性"
 
-#: ../../index.rst:13 5a7a8e5eace34d5f9a4f779bf5122928
+#: ../../index.rst:13 2a1f84e455c84d9ca66c65f92e5b0d78
 msgid ""
 "Currently, we have released multiple key features, which are listed below"
 " to demonstrate our current capabilities:"
 msgstr "目前我们已经发布了多种关键的特性，这里一一列举展示一下当前发布的能力。"
 
-#: ../../index.rst:15 5d0f67aacb8b4bc893a306ccbd6a3778
+#: ../../index.rst:15 43de30ce92da4c3cbe43ae4e4c9f1869
 msgid "SQL language capabilities - SQL generation - SQL diagnosis"
 msgstr "SQL语言能力 - SQL生成 - SQL诊断"
 
-#: ../../index.rst:19 556eaf756fec431ca5c453208292ab4f
+#: ../../index.rst:19 edfeef5284e7426a9e551e782bc5702c
 msgid ""
 "Private domain Q&A and data processing - Database knowledge Q&A - Data "
 "processing"
 msgstr "私有领域问答与数据处理 - 数据库知识问答 - 数据处理"
 
-#: ../../index.rst:23 5148ad898ec041858eddbeaa646d3f1b
+#: ../../index.rst:23 7a42f17049b943f88dd8f17baa440144
 msgid ""
 "Plugins - Support custom plugin execution tasks and natively support the "
 "Auto-GPT plugin, such as:"
 msgstr "插件模型 - 支持自定义插件执行任务，并原生支持Auto-GPT插件，例如:* SQL自动执行，获取查询结果 * 自动爬取学习知识"
 
-#: ../../index.rst:26 34c7ff33bc1c401480603a5197ecb1c4
+#: ../../index.rst:26 8b48d7b60bbc439da50a624c4048e6f6
 msgid ""
 "Unified vector storage/indexing of knowledge base - Support for "
 "unstructured data such as PDF, Markdown, CSV, and WebURL"
 msgstr "知识库统一向量存储/索引 - 非结构化数据支持包括PDF、MarkDown、CSV、WebURL"
 
-#: ../../index.rst:29 9d7095e5b08249e6bb5c724929537e6c
+#: ../../index.rst:29 97df482893924bd18e9a101922e7c374
 #, fuzzy
 msgid ""
 "Multi LLMs Support - Supports multiple large language models, currently "
@@ -111,63 +107,63 @@ msgid ""
 "codet5p"
 msgstr "多模型支持 - 支持多种大语言模型, 当前已支持Vicuna(7b,13b), ChatGLM-6b(int4, int8)"
 
-#: ../../index.rst:35 caa368eab40e4efb953865740a3c9018
+#: ../../index.rst:35 1ef26ead30ed4b7fb966c8a17307cdc5
 msgid ""
 "How to get started using DB-GPT to interact with your data and "
 "environment."
 msgstr "开始使用DB-GPT与您的数据环境进行交互。"
 
-#: ../../index.rst:36 34cecad11f8b4a3e96bfa0a31814e3d2
+#: ../../index.rst:36 3b44ab3576944bf6aa221f35bc051f4e
 #, fuzzy
 msgid "`Quickstart Guide <./getting_started/getting_started.html>`_"
 msgstr "`使用指南 <./getting_started/getting_started.html>`_"
 
-#: ../../index.rst:38 892598cdc16d45c68383033b08b7233f
+#: ../../index.rst:38 430cb239cdce42a0b62db46aba3f3bdb
 msgid "Concepts and terminology"
 msgstr "相关概念"
 
-#: ../../index.rst:40 887cc43a3a134aba96eb7ca11e5ca86f
+#: ../../index.rst:40 ded4d9f80066498e90ba6214520013f7
 #, fuzzy
 msgid "`Concepts and Terminology  <./getting_started/concepts.html>`_"
 msgstr "`相关概念 <./getting_started/concepts.html>`_"
 
-#: ../../index.rst:42 133e25c7dce046b1ab262489ecb60b4a
+#: ../../index.rst:42 cd662e53621e474d901146813c750044
 msgid "Coming soon..."
 msgstr ""
 
-#: ../../index.rst:44 a9e0812d32714a6f81ed75aa70f0c20e
+#: ../../index.rst:44 15edba57f1de44af8aff76735a2593de
 msgid "`Tutorials <.getting_started/tutorials.html>`_"
 msgstr "`教程 <.getting_started/tutorials.html>`_"
 
-#: ../../index.rst:62 4fccfd3082174f58926a9811f39e4d96
+#: ../../index.rst:62 779454b29d8e4e6eb21497025922d1b8
 msgid ""
 "These modules are the core abstractions with which we can interact with "
 "data and environment smoothly."
 msgstr "这些模块是我们可以与数据和环境顺利地进行交互的核心组成。"
 
-#: ../../index.rst:63 ecac40207ada454e9a68356f575dbca9
+#: ../../index.rst:63 bcd0e8c88c7b4807a91dd442416bec19
 msgid ""
 "It's very important for DB-GPT, DB-GPT also provide standard, extendable "
 "interfaces."
 msgstr "DB-GPT还提供了标准的、可扩展的接口。"
 
-#: ../../index.rst:65 9d852bed582449e89dc13312ddf29eed
+#: ../../index.rst:65 1e785dc6925045e8ba106cf4a3b17cac
 msgid ""
 "The docs for each module contain quickstart examples, how to guides, "
 "reference docs, and conceptual guides."
 msgstr "每个模块的文档都包含快速入门的例子、操作指南、参考文档和相关概念等内容。"
 
-#: ../../index.rst:67 3167446539de449aba2de694fe901bcf
+#: ../../index.rst:67 9c9fddd14bfd40339889f5d1f0b04163
 msgid "The modules are as follows"
 msgstr "组成模块如下："
 
-#: ../../index.rst:69 442683a5f154429da87f452e49bcbb5c
+#: ../../index.rst:69 4a19083cadd04b8e8b649a622e0ceccd
 msgid ""
 "`LLMs <./modules/llms.html>`_: Supported multi models management and "
 "integrations."
 msgstr "`LLMs <./modules/llms.html>`_:基于FastChat提供大模型的运行环境。支持多模型管理和集成。 "
 
-#: ../../index.rst:71 3cf320b6199e4ce78235bce8b1be60a2
+#: ../../index.rst:71 436a139225574aa5b066a1835d38238d
 msgid ""
 "`Prompts <./modules/prompts.html>`_: Prompt management, optimization, and"
 " serialization for multi database."
@@ -175,86 +171,41 @@ msgstr ""
 "`Prompt自动生成与优化 <./modules/prompts.html>`_: 自动化生成高质量的Prompt "
 "，并进行优化，提高系统的响应效率"
 
-#: ../../index.rst:73 4f29ed67ea2a4a3ca824ac8b8b33cae6
+#: ../../index.rst:73 6c53edfb2e494c5fba6efb5ade48c310
 msgid "`Plugins <./modules/plugins.html>`_: Plugins management, scheduler."
 msgstr "`Agent与插件： <./modules/plugins.html>`_:提供Agent和插件机制，使得用户可以自定义并增强系统的行为。"
 
-#: ../../index.rst:75 d651f9d93bb54b898ef97407501cc6cf
+#: ../../index.rst:75 6328760e8faf4e8296f3e1edd486316c
 #, fuzzy
 msgid ""
 "`Knowledge <./modules/knowledge.html>`_: Knowledge management, embedding,"
 " and search."
 msgstr "`知识库能力： <./modules/knowledge.html>`_: 支持私域知识库问答能力, "
 
-#: ../../index.rst:77 fd6dd2adcd844baa84602b650d89e507
+#: ../../index.rst:77 da272ccf56e3498d92009ac7101b0c45
 msgid ""
 "`Connections <./modules/connections.html>`_: Supported multi databases "
 "connection. management connections and interact with this."
 msgstr "`连接模块 <./modules/connections.html>`_: 用于连接不同的模块和数据源，实现数据的流转和交互 "
 
-#: ../../index.rst:79 7e388a9d8c044169923508ccdeb2d9a5
+#: ../../index.rst:79 1a0551f62d9d418a9dec267fbcb49af0
 #, fuzzy
 msgid "`Vector <./modules/vector.html>`_: Supported multi vector database."
 msgstr "`LLMs <./modules/llms.html>`_:基于FastChat提供大模型的运行环境。支持多模型管理和集成。 "
 
-#: ../../index.rst:97 9d37bf061a784d5ca92d1de33b0834f3
-msgid "Best Practices and built-in implementations for common DB-GPT use cases:"
-msgstr "DB-GPT用例的最佳实践和内置方法:"
-
-#: ../../index.rst:99 ba264bbe31d24c7887a30cbd5442e157
-msgid ""
-"`Sql generation and diagnosis "
-"<./use_cases/sql_generation_and_diagnosis.html>`_: SQL generation and "
-"diagnosis."
-msgstr "`Sql生成和诊断 <./use_cases/sql_generation_and_diagnosis.html>`_: Sql生成和诊断。"
-
-#: ../../index.rst:101 1166f6aeba064a3990d4b0caa87db274
-msgid ""
-"`knownledge Based QA <./use_cases/knownledge_based_qa.html>`_: A "
-"important scene for user to chat with database documents, codes, bugs and"
-" schemas."
-msgstr "`知识库问答 <./use_cases/knownledge_based_qa.html>`_:  用户与数据库文档、代码和bug聊天的重要场景\""
-
-#: ../../index.rst:103 b32610ada3a0440e9b029b8dffe7c79e
-msgid ""
-"`Chatbots <./use_cases/chatbots.html>`_: Language model love to chat, use"
-" multi models to chat."
-msgstr "`聊天机器人 <./use_cases/chatbots.html>`_: 使用多模型进行对话"
-
-#: ../../index.rst:105 d9348b8112df4839ab14a74a42b63715
-msgid ""
-"`Querying Database Data <./use_cases/query_database_data.html>`_: Query "
-"and Analysis data from databases and give charts."
-msgstr "`查询数据库数据 <./use_cases/query_database_data.html>`_:从数据库中查询和分析数据并给出图表。"
-
-#: ../../index.rst:107 ef978dc1f4254e5eb4ca487c31c03f7c
-msgid ""
-"`Interacting with apis <./use_cases/interacting_with_api.html>`_: "
-"Interact with apis, such as create a table, deploy a database cluster, "
-"create a database and so on."
-msgstr ""
-"`API交互 <./use_cases/interacting_with_api.html>`_: "
-"与API交互，例如创建表、部署数据库集群、创建数据库等。"
-
-#: ../../index.rst:109 49a549d7d38f493ba48e162785b4ac5d
-msgid ""
-"`Tool use with plugins <./use_cases/tool_use_with_plugin>`_: According to"
-" Plugin use tools to manage databases autonomoly."
-msgstr "`插件工具 <./use_cases/tool_use_with_plugin>`_: 根据插件使用工具自主管理数据库。"
-
-#: ../../index.rst:126 db86500484fa4f14918b0ad4e5a7326d
+#: ../../index.rst:97 9aceee0dbe1e4f7da499ac6aab23aea2
 msgid ""
 "Full documentation on all methods, classes, installation methods, and "
 "integration setups for DB-GPT."
 msgstr "关于DB-GPT的所有方法、类、安装方法和集成设置的完整文档。"
 
-#: ../../index.rst:140 a44abbb370a841658801bb2729fa62c9
+#: ../../index.rst:111 c9a729f4e1964894bae215793647ab75
 msgid ""
 "Additional resources we think may be useful as you develop your "
 "application!"
 msgstr "“我们认为在您开发应用程序时可能有用的其他资源!”"
 
-#: ../../index.rst:142 4d0da8471db240dba842949b6796be7a
+#: ../../index.rst:113 06e6e4b7776c405fa94ae7b59253162d
 msgid ""
 "`Discord <https://discord.gg/eZHE94MN>`_: if your have some problem or "
 "ideas, you can talk from discord."
@@ -272,3 +223,58 @@ msgstr "`Discord <https://discord.gg/eZHE94MN>`_:如果您有任何问题，可
 #~ msgid "Guides for how other companies/products can be used with DB-GPT"
 #~ msgstr "其他公司/产品如何与DB-GPT一起使用的方法指南"
 
+#~ msgid "Use Cases"
+#~ msgstr "示例"
+
+#~ msgid ""
+#~ "Best Practices and built-in "
+#~ "implementations for common DB-GPT use"
+#~ " cases:"
+#~ msgstr "DB-GPT用例的最佳实践和内置方法:"
+
+#~ msgid ""
+#~ "`Sql generation and diagnosis "
+#~ "<./use_cases/sql_generation_and_diagnosis.html>`_: SQL "
+#~ "generation and diagnosis."
+#~ msgstr "`Sql生成和诊断 <./use_cases/sql_generation_and_diagnosis.html>`_: Sql生成和诊断。"
+
+#~ msgid ""
+#~ "`knownledge Based QA "
+#~ "<./use_cases/knownledge_based_qa.html>`_: A important "
+#~ "scene for user to chat with "
+#~ "database documents, codes, bugs and "
+#~ "schemas."
+#~ msgstr ""
+#~ "`知识库问答 <./use_cases/knownledge_based_qa.html>`_:  "
+#~ "用户与数据库文档、代码和bug聊天的重要场景\""
+
+#~ msgid ""
+#~ "`Chatbots <./use_cases/chatbots.html>`_: Language "
+#~ "model love to chat, use multi "
+#~ "models to chat."
+#~ msgstr "`聊天机器人 <./use_cases/chatbots.html>`_: 使用多模型进行对话"
+
+#~ msgid ""
+#~ "`Querying Database Data "
+#~ "<./use_cases/query_database_data.html>`_: Query and "
+#~ "Analysis data from databases and give"
+#~ " charts."
+#~ msgstr "`查询数据库数据 <./use_cases/query_database_data.html>`_:从数据库中查询和分析数据并给出图表。"
+
+#~ msgid ""
+#~ "`Interacting with apis "
+#~ "<./use_cases/interacting_with_api.html>`_: Interact with"
+#~ " apis, such as create a table, "
+#~ "deploy a database cluster, create a "
+#~ "database and so on."
+#~ msgstr ""
+#~ "`API交互 <./use_cases/interacting_with_api.html>`_: "
+#~ "与API交互，例如创建表、部署数据库集群、创建数据库等。"
+
+#~ msgid ""
+#~ "`Tool use with plugins "
+#~ "<./use_cases/tool_use_with_plugin>`_: According to "
+#~ "Plugin use tools to manage databases "
+#~ "autonomoly."
+#~ msgstr "`插件工具 <./use_cases/tool_use_with_plugin>`_: 根据插件使用工具自主管理数据库。"
+
diff --git a/pilot/model/cluster/worker/manager.py b/pilot/model/cluster/worker/manager.py
index 2dcfb086e..d67519f59 100644
--- a/pilot/model/cluster/worker/manager.py
+++ b/pilot/model/cluster/worker/manager.py
@@ -1021,6 +1021,7 @@ def run_worker_manager(
         system_app,
         os.path.join(LOGDIR, worker_params.tracer_file),
         root_operation_name="DB-GPT-WorkerManager-Entry",
+        tracer_storage_cls=worker_params.tracer_storage_cls,
     )
 
     _start_local_worker(worker_manager, worker_params)
diff --git a/pilot/model/parameter.py b/pilot/model/parameter.py
index e21de1c42..79558e02c 100644
--- a/pilot/model/parameter.py
+++ b/pilot/model/parameter.py
@@ -88,6 +88,12 @@ class ModelControllerParameters(BaseParameters):
             "help": "The filename to store tracer span records",
         },
     )
+    tracer_storage_cls: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "The storage class to storage tracer span records",
+        },
+    )
 
 
 @dataclass
@@ -138,6 +144,12 @@ class ModelAPIServerParameters(BaseParameters):
             "help": "The filename to store tracer span records",
         },
     )
+    tracer_storage_cls: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "The storage class to storage tracer span records",
+        },
+    )
 
 
 @dataclass
@@ -226,6 +238,12 @@ class ModelWorkerParameters(BaseModelParameters):
             "help": "The filename to store tracer span records",
         },
     )
+    tracer_storage_cls: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "The storage class to storage tracer span records",
+        },
+    )
 
 
 @dataclass
diff --git a/pilot/model/proxy/llms/tongyi.py b/pilot/model/proxy/llms/tongyi.py
index 13031e96f..e101db47e 100644
--- a/pilot/model/proxy/llms/tongyi.py
+++ b/pilot/model/proxy/llms/tongyi.py
@@ -36,7 +36,10 @@ def tongyi_generate_stream(
         if message.role == ModelMessageRoleType.HUMAN:
             history.append({"role": "user", "content": message.content})
     for message in messages:
-        if message.role == ModelMessageRoleType.SYSTEM or message.role == ModelMessageRoleType.HUMAN:
+        if (
+            message.role == ModelMessageRoleType.SYSTEM
+            or message.role == ModelMessageRoleType.HUMAN
+        ):
             history.append({"role": "user", "content": message.content})
         # elif message.role == ModelMessageRoleType.HUMAN:
         #     history.append({"role": "user", "content": message.content})
diff --git a/pilot/server/base.py b/pilot/server/base.py
index 71faeb821..488c919c3 100644
--- a/pilot/server/base.py
+++ b/pilot/server/base.py
@@ -147,6 +147,12 @@ class WebWerverParameters(BaseParameters):
             "help": "The filename to store tracer span records",
         },
     )
+    tracer_storage_cls: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "The storage class to storage tracer span records",
+        },
+    )
     disable_alembic_upgrade: Optional[bool] = field(
         default=False,
         metadata={
diff --git a/pilot/server/dbgpt_server.py b/pilot/server/dbgpt_server.py
index e94526b9a..c26803cfd 100644
--- a/pilot/server/dbgpt_server.py
+++ b/pilot/server/dbgpt_server.py
@@ -195,7 +195,11 @@ 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, param.tracer_file))
+    initialize_tracer(
+        system_app,
+        os.path.join(LOGDIR, param.tracer_file),
+        tracer_storage_cls=param.tracer_storage_cls,
+    )
 
     with root_tracer.start_span(
         "run_webserver",
diff --git a/pilot/utils/tracer/__init__.py b/pilot/utils/tracer/__init__.py
index cdb536f79..6f77cfd6c 100644
--- a/pilot/utils/tracer/__init__.py
+++ b/pilot/utils/tracer/__init__.py
@@ -7,7 +7,11 @@ from pilot.utils.tracer.base import (
     SpanStorageType,
     TracerContext,
 )
-from pilot.utils.tracer.span_storage import MemorySpanStorage, FileSpanStorage
+from pilot.utils.tracer.span_storage import (
+    MemorySpanStorage,
+    FileSpanStorage,
+    SpanStorageContainer,
+)
 from pilot.utils.tracer.tracer_impl import (
     root_tracer,
     trace,
@@ -26,6 +30,7 @@ __all__ = [
     "TracerContext",
     "MemorySpanStorage",
     "FileSpanStorage",
+    "SpanStorageContainer",
     "root_tracer",
     "trace",
     "initialize_tracer",
diff --git a/pilot/utils/tracer/base.py b/pilot/utils/tracer/base.py
index e227d6314..625e9aabd 100644
--- a/pilot/utils/tracer/base.py
+++ b/pilot/utils/tracer/base.py
@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Dict, Callable, Optional
+from typing import Dict, Callable, Optional, List
 from dataclasses import dataclass
 from abc import ABC, abstractmethod
 from enum import Enum
@@ -121,6 +121,11 @@ class SpanStorage(BaseComponent, ABC):
     def append_span(self, span: Span):
         """Store the given span. This needs to be implemented by subclasses."""
 
+    def append_span_batch(self, spans: List[Span]):
+        """Store the span batch"""
+        for span in spans:
+            self.append_span(span)
+
 
 class Tracer(BaseComponent, ABC):
     """Abstract base class for tracing operations.
diff --git a/pilot/utils/tracer/span_storage.py b/pilot/utils/tracer/span_storage.py
index 3070fb834..57321a316 100644
--- a/pilot/utils/tracer/span_storage.py
+++ b/pilot/utils/tracer/span_storage.py
@@ -5,11 +5,12 @@ import datetime
 import threading
 import queue
 import logging
+from typing import Optional, List
+from concurrent.futures import Executor, ThreadPoolExecutor
 
 from pilot.component import SystemApp
 from pilot.utils.tracer.base import Span, SpanStorage
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -24,8 +25,81 @@ class MemorySpanStorage(SpanStorage):
             self.spans.append(span)
 
 
+class SpanStorageContainer(SpanStorage):
+    def __init__(
+        self,
+        system_app: SystemApp | None = None,
+        batch_size=10,
+        flush_interval=10,
+        executor: Executor = None,
+    ):
+        super().__init__(system_app)
+        if not executor:
+            executor = ThreadPoolExecutor(thread_name_prefix="trace_storage_sync_")
+        self.executor = executor
+        self.storages: List[SpanStorage] = []
+        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
+        self.last_flush_time = time.time()
+        self.flush_signal_queue = queue.Queue()
+        self.flush_thread = threading.Thread(
+            target=self._flush_to_storages, daemon=True
+        )
+        self.flush_thread.start()
+
+    def append_storage(self, storage: SpanStorage):
+        """Append sotrage to container
+
+        Args:
+            storage ([`SpanStorage`]): The storage to be append to current container
+        """
+        self.storages.append(storage)
+
+    def append_span(self, span: Span):
+        self.queue.put(span)
+        if self.queue.qsize() >= self.batch_size:
+            try:
+                self.flush_signal_queue.put_nowait(True)
+            except queue.Full:
+                pass  # If the signal queue is full, it's okay. The flush thread will handle it.
+
+    def _flush_to_storages(self):
+        while True:
+            interval = time.time() - self.last_flush_time
+            if interval < self.flush_interval:
+                try:
+                    self.flush_signal_queue.get(
+                        block=True, timeout=self.flush_interval - interval
+                    )
+                except Exception:
+                    # Timeout
+                    pass
+
+            spans_to_write = []
+            while not self.queue.empty():
+                spans_to_write.append(self.queue.get())
+            for s in self.storages:
+
+                def append_and_ignore_error(
+                    storage: SpanStorage, spans_to_write: List[SpanStorage]
+                ):
+                    try:
+                        storage.append_span_batch(spans_to_write)
+                    except Exception as e:
+                        logger.warn(
+                            f"Append spans to storage {str(storage)} failed: {str(e)}, span_data: {spans_to_write}"
+                        )
+
+                self.executor.submit(append_and_ignore_error, s, spans_to_write)
+            self.last_flush_time = time.time()
+
+
 class FileSpanStorage(SpanStorage):
-    def __init__(self, filename: str, batch_size=10, flush_interval=10):
+    def __init__(self, filename: str):
         super().__init__()
         self.filename = filename
         # Split filename into prefix and suffix
@@ -36,29 +110,18 @@ class FileSpanStorage(SpanStorage):
             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
-        self.last_flush_time = time.time()
-        self.flush_signal_queue = queue.Queue()
 
         if not os.path.exists(filename):
             # New file if not exist
             os.makedirs(os.path.dirname(filename), exist_ok=True)
             with open(filename, "a"):
                 pass
-        self.flush_thread = threading.Thread(target=self._flush_to_file, daemon=True)
-        self.flush_thread.start()
 
     def append_span(self, span: Span):
-        span_data = span.to_dict()
-        logger.debug(f"append span: {span_data}")
-        self.queue.put(span_data)
+        self._write_to_file([span])
 
-        if self.queue.qsize() >= self.batch_size:
-            try:
-                self.flush_signal_queue.put_nowait(True)
-            except queue.Full:
-                pass  # If the signal queue is full, it's okay. The flush thread will handle it.
+    def append_span_batch(self, spans: List[Span]):
+        self._write_to_file(spans)
 
     def _get_dated_filename(self, date: datetime.date) -> str:
         """Return the filename based on a specific date."""
@@ -73,31 +136,15 @@ class FileSpanStorage(SpanStorage):
                 os.rename(self.filename, self._get_dated_filename(self.last_date))
             self.last_date = current_date
 
-    def _write_to_file(self):
+    def _write_to_file(self, spans: List[Span]):
         self._roll_over_if_needed()
-        spans_to_write = []
-        while not self.queue.empty():
-            spans_to_write.append(self.queue.get())
 
         with open(self.filename, "a") as file:
-            for span_data in spans_to_write:
+            for span in spans:
+                span_data = span.to_dict()
                 try:
                     file.write(json.dumps(span_data, ensure_ascii=False) + "\n")
                 except Exception as e:
                     logger.warning(
                         f"Write span to file failed: {str(e)}, span_data: {span_data}"
                     )
-
-    def _flush_to_file(self):
-        while True:
-            interval = time.time() - self.last_flush_time
-            if interval < self.flush_interval:
-                try:
-                    self.flush_signal_queue.get(
-                        block=True, timeout=self.flush_interval - interval
-                    )
-                except Exception:
-                    # Timeout
-                    pass
-            self._write_to_file()
-            self.last_flush_time = time.time()
diff --git a/pilot/utils/tracer/tests/test_span_storage.py b/pilot/utils/tracer/tests/test_span_storage.py
index 9ca727995..6da0797fc 100644
--- a/pilot/utils/tracer/tests/test_span_storage.py
+++ b/pilot/utils/tracer/tests/test_span_storage.py
@@ -7,44 +7,53 @@ import time
 from unittest.mock import patch
 from datetime import datetime, timedelta
 
-from pilot.utils.tracer import SpanStorage, FileSpanStorage, Span, SpanType
+from pilot.utils.tracer import (
+    SpanStorage,
+    FileSpanStorage,
+    Span,
+    SpanType,
+    SpanStorageContainer,
+)
 
 
 @pytest.fixture
 def storage(request):
     if not request or not hasattr(request, "param"):
-        batch_size = 10
-        flush_interval = 10
         file_does_not_exist = False
     else:
-        batch_size = request.param.get("batch_size", 10)
-        flush_interval = request.param.get("flush_interval", 10)
         file_does_not_exist = request.param.get("file_does_not_exist", False)
 
     if file_does_not_exist:
         with tempfile.TemporaryDirectory() as tmp_dir:
             filename = os.path.join(tmp_dir, "non_existent_file.jsonl")
-            storage_instance = FileSpanStorage(
-                filename, batch_size=batch_size, flush_interval=flush_interval
-            )
+            storage_instance = FileSpanStorage(filename)
             yield storage_instance
     else:
         with tempfile.NamedTemporaryFile(delete=True) as tmp_file:
             filename = tmp_file.name
-            storage_instance = FileSpanStorage(
-                filename, batch_size=batch_size, flush_interval=flush_interval
-            )
+            storage_instance = FileSpanStorage(filename)
             yield storage_instance
 
 
+@pytest.fixture
+def storage_container(request):
+    if not request or not hasattr(request, "param"):
+        batch_size = 10
+        flush_interval = 10
+    else:
+        batch_size = request.param.get("batch_size", 10)
+        flush_interval = request.param.get("flush_interval", 10)
+    storage_container = SpanStorageContainer(
+        batch_size=batch_size, flush_interval=flush_interval
+    )
+    yield storage_container
+
+
 def read_spans_from_file(filename):
     with open(filename, "r") as f:
         return [json.loads(line) for line in f.readlines()]
 
 
-@pytest.mark.parametrize(
-    "storage", [{"batch_size": 1, "flush_interval": 5}], indirect=True
-)
 def test_write_span(storage: SpanStorage):
     span = Span("1", "a", SpanType.BASE, "b", "op1")
     storage.append_span(span)
@@ -55,9 +64,6 @@ def test_write_span(storage: SpanStorage):
     assert spans_in_file[0]["trace_id"] == "1"
 
 
-@pytest.mark.parametrize(
-    "storage", [{"batch_size": 1, "flush_interval": 5}], indirect=True
-)
 def test_incremental_write(storage: SpanStorage):
     span1 = Span("1", "a", SpanType.BASE, "b", "op1")
     span2 = Span("2", "c", SpanType.BASE, "d", "op2")
@@ -70,9 +76,6 @@ def test_incremental_write(storage: SpanStorage):
     assert len(spans_in_file) == 2
 
 
-@pytest.mark.parametrize(
-    "storage", [{"batch_size": 2, "flush_interval": 5}], indirect=True
-)
 def test_sync_and_async_append(storage: SpanStorage):
     span = Span("1", "a", SpanType.BASE, "b", "op1")
 
@@ -88,27 +91,7 @@ def test_sync_and_async_append(storage: SpanStorage):
     assert len(spans_in_file) == 2
 
 
-@pytest.mark.asyncio
-async def test_flush_policy(storage: SpanStorage):
-    span = Span("1", "a", SpanType.BASE, "b", "op1")
-
-    for _ in range(storage.batch_size - 1):
-        storage.append_span(span)
-
-    spans_in_file = read_spans_from_file(storage.filename)
-    assert len(spans_in_file) == 0
-
-    # Trigger batch write
-    storage.append_span(span)
-    await asyncio.sleep(0.1)
-
-    spans_in_file = read_spans_from_file(storage.filename)
-    assert len(spans_in_file) == storage.batch_size
-
-
-@pytest.mark.parametrize(
-    "storage", [{"batch_size": 2, "file_does_not_exist": True}], indirect=True
-)
+@pytest.mark.parametrize("storage", [{"file_does_not_exist": True}], indirect=True)
 def test_non_existent_file(storage: SpanStorage):
     span = Span("1", "a", SpanType.BASE, "b", "op1")
     span2 = Span("2", "c", SpanType.BASE, "d", "op2")
@@ -116,7 +99,7 @@ def test_non_existent_file(storage: SpanStorage):
     time.sleep(0.1)
 
     spans_in_file = read_spans_from_file(storage.filename)
-    assert len(spans_in_file) == 0
+    assert len(spans_in_file) == 1
 
     storage.append_span(span2)
     time.sleep(0.1)
@@ -126,9 +109,7 @@ def test_non_existent_file(storage: SpanStorage):
     assert spans_in_file[1]["trace_id"] == "2"
 
 
-@pytest.mark.parametrize(
-    "storage", [{"batch_size": 1, "file_does_not_exist": True}], indirect=True
-)
+@pytest.mark.parametrize("storage", [{"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)
@@ -167,3 +148,27 @@ def test_log_rollover(storage: SpanStorage):
     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"
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("storage_container", [{"batch_size": 5}], indirect=True)
+async def test_container_flush_policy(
+    storage_container: SpanStorageContainer, storage: FileSpanStorage
+):
+    storage_container.append_storage(storage)
+    span = Span("1", "a", SpanType.BASE, "b", "op1")
+
+    filename = storage.filename
+
+    for _ in range(storage_container.batch_size - 1):
+        storage_container.append_span(span)
+
+    spans_in_file = read_spans_from_file(filename)
+    assert len(spans_in_file) == 0
+
+    # Trigger batch write
+    storage_container.append_span(span)
+    await asyncio.sleep(0.1)
+
+    spans_in_file = read_spans_from_file(filename)
+    assert len(spans_in_file) == storage_container.batch_size
diff --git a/pilot/utils/tracer/tracer_impl.py b/pilot/utils/tracer/tracer_impl.py
index 2358863bf..6bbad084c 100644
--- a/pilot/utils/tracer/tracer_impl.py
+++ b/pilot/utils/tracer/tracer_impl.py
@@ -3,6 +3,7 @@ from contextvars import ContextVar
 from functools import wraps
 import asyncio
 import inspect
+import logging
 
 
 from pilot.component import SystemApp, ComponentType
@@ -15,6 +16,9 @@ from pilot.utils.tracer.base import (
     TracerContext,
 )
 from pilot.utils.tracer.span_storage import MemorySpanStorage
+from pilot.utils.module_utils import import_from_checked_string
+
+logger = logging.getLogger(__name__)
 
 
 class DefaultTracer(Tracer):
@@ -197,10 +201,11 @@ def initialize_tracer(
     system_app: SystemApp,
     tracer_filename: str,
     root_operation_name: str = "DB-GPT-Web-Entry",
+    tracer_storage_cls: str = None,
 ):
     if not system_app:
         return
-    from pilot.utils.tracer.span_storage import FileSpanStorage
+    from pilot.utils.tracer.span_storage import FileSpanStorage, SpanStorageContainer
 
     trace_context_var = ContextVar(
         "trace_context",
@@ -208,7 +213,15 @@ def initialize_tracer(
     )
     tracer = DefaultTracer(system_app)
 
-    system_app.register_instance(FileSpanStorage(tracer_filename))
+    storage_container = SpanStorageContainer(system_app)
+    storage_container.append_storage(FileSpanStorage(tracer_filename))
+
+    if tracer_storage_cls:
+        logger.info(f"Begin parse storage class {tracer_storage_cls}")
+        storage = import_from_checked_string(tracer_storage_cls, SpanStorage)
+        storage_container.append_storage(storage())
+
+    system_app.register_instance(storage_container)
     system_app.register_instance(tracer)
     root_tracer.initialize(system_app, trace_context_var)
     if system_app.app: