github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-13 05:55:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(core): Support custom trace storage (#782)

Browse Source 
- Support custom trace storage
- Modify install documents
This commit is contained in:
Aries-ckt 2023-11-06 20:04:53 +08:00 committed by GitHub
commit 64bc4a9899
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
14 changed files with 587 additions and 449 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docker/base/Dockerfile
View File

@ -28,7 +28,9 @@ WORKDIR /app
# RUN pip3 install -i $PIP_INDEX_URL ".[all]" # RUN pip3 install -i $PIP_INDEX_URL ".[all]"
RUN pip3 install --upgrade pip -i $PIP_INDEX_URL \ 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" ]; \ RUN (if [ "${LANGUAGE}" = "zh" ]; \
# language is zh, download zh_core_web_sm from github # language is zh, download zh_core_web_sm from github

12
docs/getting_started/install/deploy.rst
View File

@ -57,6 +57,12 @@ If you are low hardware requirements you can install DB-GPT by Using third-part
.. tab:: OpenAI .. tab:: OpenAI
Installing Dependencies
.. code-block::
pip install -e ".[openai]"
Download embedding model Download embedding model
.. code-block:: shell .. code-block:: shell
@ -69,7 +75,7 @@ If you are low hardware requirements you can install DB-GPT by Using third-part
or or
git clone https://huggingface.co/moka-ai/m3e-large 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 .. 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.** **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:: .. 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** **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** **Installing Dependencies**

569
docs/locales/zh_CN/LC_MESSAGES/getting_started/install/deploy.po
View File

@ -8,7 +8,7 @@ msgid ""
msgstr "" msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.4.0\n" "Project-Id-Version: DB-GPT 👏👏 0.4.0\n"
"Report-Msgid-Bugs-To: \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" "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n" "Language: zh_CN\n"
@ -19,27 +19,27 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n" "Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\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" msgid "Installation From Source"
msgstr "源码安装" 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." msgid "To get started, install DB-GPT with the following steps."
msgstr "按照以下步骤进行安装" 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" msgid "1.Preparation"
msgstr "1.准备" msgstr "1.准备"
#: ../../getting_started/install/deploy.rst:11 d845f48ec05a4bb7a5b0f95a0644029d #: ../../getting_started/install/deploy.rst:11 5c5bfbdc74a14c3b9b1f1ed66617cac8
msgid "**Download DB-GPT**" msgid "**Download DB-GPT**"
msgstr "**下载DB-GPT项目**" msgstr "**下载DB-GPT项目**"
#: ../../getting_started/install/deploy.rst:17 85df7bb2b73141058ba0ca5a73e46701 #: ../../getting_started/install/deploy.rst:17 3065ee2f34f9417598a37fd699a4863e
msgid "**Install Miniconda**" msgid "**Install Miniconda**"
msgstr "**安装Miniconda**" msgstr "**安装Miniconda**"
#: ../../getting_started/install/deploy.rst:19 b7b3e120ded344d09fb2d7a3a7903497 #: ../../getting_started/install/deploy.rst:19 f9f3a653ffb8447284686aa37a7bb79a
msgid "" msgid ""
"We use Sqlite as default database, so there is no need for database " "We use Sqlite as default database, so there is no need for database "
"installation. If you choose to connect to other databases, you can " "installation. If you choose to connect to other databases, you can "
@ -50,386 +50,397 @@ msgid ""
"<https://docs.conda.io/en/latest/miniconda.html>`_" "<https://docs.conda.io/en/latest/miniconda.html>`_"
msgstr "" msgstr ""
"目前使用Sqlite作为默认数据库，因此DB-" "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" "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)" " 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" msgid "2.Deploy LLM Service"
msgstr "2.部署LLM服务" msgstr "2.部署LLM服务"
#: ../../getting_started/install/deploy.rst:37 5c49829b086e4d5fbcb5a971a34fa3b5 #: ../../getting_started/install/deploy.rst:37 180a121e3c994a92a917ace80bf12386
msgid "" msgid ""
"DB-GPT can be deployed on servers with low hardware requirements or on " "DB-GPT can be deployed on servers with low hardware requirements or on "
"servers with high hardware requirements." "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" 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 "" msgid ""
"If you are low hardware requirements you can install DB-GPT by Using " "If you are low hardware requirements you can install DB-GPT by Using "
"third-part LLM REST API Service OpenAI, Azure, tongyi." "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%," 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%" 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" msgid "Notice make sure you have install git-lfs"
msgstr "确认是否已经安装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" msgid "centos:yum install git-lfs"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:52 f5c2035bca214e3fbef2b70be0e76247 #: ../../getting_started/install/deploy.rst:52 1574ea24ad6443409070aa3a1f7abe87
msgid "ubuntu:apt-get install git-lfs" msgid "ubuntu:apt-get install git-lfs"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:54 cb1b52b9323e4e9fbccfd3c42067a568 #: ../../getting_started/install/deploy.rst:54 ad86473d5c87447091c713f45cbfed0e
msgid "macos:brew install git-lfs" msgid "macos:brew install git-lfs"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:58 #: ../../getting_started/install/deploy.rst:58
#: ../../getting_started/install/deploy.rst:223 #: ../../getting_started/install/deploy.rst:229
#: 9c601ee0c06646d58cbd2c2fff342cb5 d3fe6c712b4145d0856487c65057c2a0 #: 3dd1e40f33924faab63634907a7f6511 dce32420face4ab2b99caf7f3900ede9
msgid "OpenAI" msgid "OpenAI"
msgstr "OpenAI" msgstr "OpenAI"
#: ../../getting_started/install/deploy.rst:60 #: ../../getting_started/install/deploy.rst:60 1f66400540114de2820761ef80137805
#: ../../getting_started/install/deploy.rst:207 msgid "Installing Dependencies"
#: 5e0e84bd11084d158e18b702022aaa96 6a9c9830e5184eac8b6b7425780f4a3e msgstr "安装依赖"
#: ../../getting_started/install/deploy.rst:66
#: ../../getting_started/install/deploy.rst:213
#: 31b856a6fc094334a37914c046cb1bb1 42b2f6d36ca4487f8e31d59bba123fca
msgid "Download embedding model" 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:78 f970fb69e47c40d7bda381ec6f045829
#: ../../getting_started/install/deploy.rst:231 msgid "Configure LLM_MODEL, PROXY_API_URL and API_KEY in `.env` file"
#: 953d6931627641b985588abf8b6ad9fd d52e287164ca44f79709f4645a1bb774 msgstr "在 `.env` 文件中设置 LLM_MODEL、PROXY_API_URL 和 API_KEY"
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:82 #: ../../getting_started/install/deploy.rst:88
#: ../../getting_started/install/deploy.rst:282 #: ../../getting_started/install/deploy.rst:288
#: 6dc89616c0bf46a898a49606d1349039 e30b7458fc0d46e8bcf0ec61a2be2e19 #: 6ca04c88fc60480db2ebdc9b234a0bbb 709cfe74c45c4eff83a7d77bb30b4a2b
msgid "Make sure your .env configuration is not overwritten" 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" msgid "Vicuna"
msgstr "Vicuna" msgstr "Vicuna"
#: ../../getting_started/install/deploy.rst:86 44a32c4cd0b140838b49f739d68ff42d #: ../../getting_started/install/deploy.rst:92 6a0bd60c4ca2478cb0f3d85aff70cd3b
msgid "" msgid ""
"`Vicuna-v1.5 <https://huggingface.co/lmsys/vicuna-13b-v1.5>`_ based on " "`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-" "llama-2 has been released, we recommend you set `LLM_MODEL=vicuna-"
"13b-v1.5` to try this model)" "13b-v1.5` to try this model)"
msgstr "" 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" 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:98
#: ../../getting_started/install/deploy.rst:137 #: ../../getting_started/install/deploy.rst:143
#: 596405ba21d046c993c18d0bcaf95048 ca993a5f1b194707bbe3d5d6e9d670d8 #: dc24c0238ce141df8bdce26cc0e2ddbb e04f1ea4b36940f3a28b66cdff7b702e
msgid "Model" msgid "Model"
msgstr "" msgstr "模型"
#: ../../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 ""
#: ../../getting_started/install/deploy.rst:99 #: ../../getting_started/install/deploy.rst:99
#: ../../getting_started/install/deploy.rst:105
#: ../../getting_started/install/deploy.rst:144 #: ../../getting_started/install/deploy.rst:144
#: ../../getting_started/install/deploy.rst:150 #: b6473e65ca1a437a84226531be4da26d e0a2f7580685480aa13ca462418764d3
#: 0d6bd1c4a6464df38723de978c09e8bc 106e20f7727f43d280b7560dc0f19bbc msgid "Quantize"
#: 5a95691d1d134638bffa478daf2577a0 f8add03506244306b1ac6e10c5a2bc1f msgstr "量化"
msgid "8-bit"
msgstr ""
#: ../../getting_started/install/deploy.rst:100 #: ../../getting_started/install/deploy.rst:100
#: ../../getting_started/install/deploy.rst:103
#: ../../getting_started/install/deploy.rst:145 #: ../../getting_started/install/deploy.rst:145
#: ../../getting_started/install/deploy.rst:148 #: 56471c3b174d4adf9e8cb5bebaa300a6 d82297b8b9c148c3906d8ee4ed10d8a0
#: 03222e6a682e406bb56c21025412fbe5 2eb88af3efb74fb79899d7818a79d177 msgid "VRAM Size"
#: 9705b9d7d2084f0b8867f6aeec66251b bca6e5151e244a318f4c2078c3f82118 msgstr "显存"
msgid "12 GB"
msgstr ""
#: ../../getting_started/install/deploy.rst:101 #: ../../getting_started/install/deploy.rst:101
#: ../../getting_started/install/deploy.rst:104 #: ../../getting_started/install/deploy.rst:104
#: 1596cbb77c954d1db00e2fa283d66a9a c6e8dc1600d14ee5a47f45f75ec709f4 #: 1214432602fe47a28479ce3e21a7d88b 51838e72e42248f199653f1bf08c8155
msgid "vicuna-13b-v1.5" 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 "" msgstr ""
#: ../../getting_started/install/deploy.rst:106 #: ../../getting_started/install/deploy.rst:106
#: ../../getting_started/install/deploy.rst:109
#: ../../getting_started/install/deploy.rst:151 #: ../../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" msgid "20 GB"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:122 #: ../../getting_started/install/deploy.rst:128
#: ../../getting_started/install/deploy.rst:169 #: ../../getting_started/install/deploy.rst:175
#: ../../getting_started/install/deploy.rst:195 #: ../../getting_started/install/deploy.rst:201
#: 852f800e380c44d3b1b5bdaa881406b7 89ddd6c4a4874f4f8b7f051d797e364a #: 1719c11f92874c47a87c00c634b9fad8 4596fcbe415d42fdbb29b92964fae070
#: a2b4436f8fcb44ada3b5bf5c1099e646 #: e639ae6076a64b7b9de08527966e4550
msgid "The model files are large and will take a long time to download." 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:130
#: ../../getting_started/install/deploy.rst:171 #: ../../getting_started/install/deploy.rst:177
#: ../../getting_started/install/deploy.rst:197 #: ../../getting_started/install/deploy.rst:203
#: 18ccf7acdf3045588a19866c0161f44b 3d3d93649ec943c8b2b725807e969cbf #: 4ec1492d389f403ebd9dd805fcaac68e ac6c68e2bf9b47c694ea8e0506014b10
#: 6205975466f54d8fbf8e30b58df6b9c2 #: e39be72282e64760903aaba45f8effb8
msgid "**Configure LLM_MODEL in `.env` file**" 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:137
#: ../../getting_started/install/deploy.rst:228 #: ../../getting_started/install/deploy.rst:234
#: 022addaea4ea432584b8a27ea83a9dc4 7a95d25c58d2491e855dff42f6d3a686 #: 7ce4e2253ef24a7ea890ade04ce36682 b9d5bf4fa09649c4a098503132ce7c0c
msgid "Baichuan" msgid "Baichuan"
msgstr "" msgstr "百川"
#: ../../getting_started/install/deploy.rst:133 #: ../../getting_started/install/deploy.rst:139
#: b5374f6d0ca44ee9bd984c0198515861 #: ffdad6a70558457fa825bad4d811100d
msgid "Baichuan hardware requirements" msgid "Baichuan hardware requirements"
msgstr "" msgstr "百川 的硬件要求"
#: ../../getting_started/install/deploy.rst:140
#: ../../getting_started/install/deploy.rst:143
#: 6a5e6034c185455d81e8ba5349dbc191 9d0109817c524747909417924bb0bd31
msgid "baichuan-7b"
msgstr ""
#: ../../getting_started/install/deploy.rst:146 #: ../../getting_started/install/deploy.rst:146
#: ../../getting_started/install/deploy.rst:149 #: ../../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" msgid "baichuan-13b"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:173 #: ../../getting_started/install/deploy.rst:179
#: ac684ccbea7d4f5380c43ad02a1b7231 #: efd73637994a4b7c97ef3557e1f3161c
msgid "please rename Baichuan path to \"baichuan2-13b\" or \"baichuan2-7b\"" 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\"" msgstr "将Baichuan模型目录修改为\"baichuan2-13b\" 或 \"baichuan2-7b\""
#: ../../getting_started/install/deploy.rst:179 #: ../../getting_started/install/deploy.rst:185
#: d2e283112ed1440b93510c331922b37c #: 435a3f0d0fe84b49a7305e2c0f51a5df
msgid "ChatGLM" msgid "ChatGLM"
msgstr "" 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 #: ../../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" msgid "Other LLM API"
msgstr "" msgstr "其它模型 API"
#: ../../getting_started/install/deploy.rst:219 #: ../../getting_started/install/deploy.rst:225
#: 3df3d5e0e4f64813a7ca2adccd056c4a #: 4eabdc25f4a34676b3ece620c88d866f
msgid "Now DB-GPT support LLM REST API TYPE:" 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 #: ../../getting_started/install/deploy.rst:230
#: 4f7cb7a3f324410d8a34ba96d7c9536a #: d361963cc3404e5ca55a823f1f1f545c
msgid "Azure" msgid "Azure"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:225 #: ../../getting_started/install/deploy.rst:231
#: ee6cbe48a8094637b6b8a049446042c6 #: 3b0f17c74aaa4bbd9db935973fa1c36b
msgid "Aliyun tongyi" msgid "Aliyun tongyi"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:226 #: ../../getting_started/install/deploy.rst:232
#: a3d9c061b0f440258be88cc3143b1887 #: 7c4c457a499943b8804e31046551006d
msgid "Baidu wenxin" msgid "Baidu wenxin"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:227 #: ../../getting_started/install/deploy.rst:233
#: 176001fb6eaf448f9eca1abd256b3ef4 #: ac1880a995184295acf07fff987d7c56
msgid "Zhipu" msgid "Zhipu"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:229 #: ../../getting_started/install/deploy.rst:235
#: 17fecc140be2474ea1566d44641a27c0 #: 6927500d7d3445b7b1981da1df4e1666
msgid "Bard" msgid "Bard"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:284 #: ../../getting_started/install/deploy.rst:237
#: bc34832cec754984a40c4d01526f0f83 #: 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" msgid "llama.cpp"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:286 #: ../../getting_started/install/deploy.rst:292
#: aa4b14e726dc447f92dec48f38a3d770 #: 36a2b82f711a4c0f9491aca9c84d3c91
msgid "" msgid ""
"DB-GPT already supports `llama.cpp " "DB-GPT already supports `llama.cpp "
"<https://github.com/ggerganov/llama.cpp>`_ via `llama-cpp-python " "<https://github.com/ggerganov/llama.cpp>`_ via `llama-cpp-python "
"<https://github.com/abetlen/llama-cpp-python>`_ ." "<https://github.com/abetlen/llama-cpp-python>`_ ."
msgstr "" msgstr ""
"DB-GPT 已经支持了 `llama.cpp <https://github.com/ggerganov/llama.cpp>`_ via " "DB-GPT 已经通过 `llama-cpp-python <https://github.com/abetlen/llama-cpp-"
"`llama-cpp-python <https://github.com/abetlen/llama-cpp-python>`_ ." "python>`_ 支持了 `llama.cpp <https://github.com/ggerganov/llama.cpp>`_ 。"
#: ../../getting_started/install/deploy.rst:288 #: ../../getting_started/install/deploy.rst:294
#: e97a868ad05b48ee8d25017457c1b7ee #: 439064115dca4ae08d8e60041f2ffe17
msgid "**Preparing Model Files**" msgid "**Preparing Model Files**"
msgstr "**准备Model文件**" msgstr "**准备模型文件**"
#: ../../getting_started/install/deploy.rst:290 #: ../../getting_started/install/deploy.rst:296
#: 8efc7824082545a4a98ebbd6b12fa00f #: 7291d6fa20b34942926e7765c01f25c9
msgid "" msgid ""
"To use llama.cpp, you need to prepare a gguf format model file, and there" "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:" " 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 #: ../../getting_started/install/deploy.rst:298
#: 5b9f3a35779c4f89a4b9051904c5f7d8 #: 45752f3f5dd847469da0c5edddc530fa
msgid "**1. Download a pre-converted model file.**" msgid "**1. Download a pre-converted model file.**"
msgstr "**1.下载已转换的模型文件.**" msgstr "**1.下载已转换的模型文件.**"
#: ../../getting_started/install/deploy.rst:294 #: ../../getting_started/install/deploy.rst:300
#: e15f33a2e5fc4caaa9ad2e10cabf9d32 #: c451db2157ff49b2b4992aed9907ddfa
msgid "" msgid ""
"Suppose you want to use [Vicuna 13B v1.5](https://huggingface.co/lmsys" "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 " "/vicuna-13b-v1.5>`_ , you can download the file already converted from "
"[TheBloke/vicuna-13B-v1.5-GGUF](https://huggingface.co/TheBloke/vicuna-" "`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` " "13B-v1.5-GGUF>`_ , only one file is needed. Download it to the `models` "
"directory and rename it to `ggml-model-q4_0.gguf`." "directory and rename it to `ggml-model-q4_0.gguf`."
msgstr "" msgstr ""
"假设您想使用[Vicuna 13B v1.5](https://huggingface.co/lmsys/vicuna-" "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>`_ 您可以从 `TheBloke/vicuna-"
"13B-v1.5-GGUF](https://huggingface.co/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-" "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`。" "model-q4_0.gguf`。"
#: ../../getting_started/install/deploy.rst:300 #: ../../getting_started/install/deploy.rst:306
#: 81ab603cd9b94cabb48add9541590b8b #: f5b92b51622b43d398b3dc13a5892c29
msgid "**2. Convert It Yourself**" msgid "**2. Convert It Yourself**"
msgstr "**2. 自行转换**" msgstr "**2. 自行转换**"
#: ../../getting_started/install/deploy.rst:302 #: ../../getting_started/install/deploy.rst:308
#: f9b46aa70a0842d6acc7e837c8b27778 #: 8838ae6dcecf44ecad3fd963980c8eb3
msgid "" msgid ""
"You can convert the model file yourself according to the instructions in " "You can convert the model file yourself according to the instructions in "
"[llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp" "`llama.cpp#prepare-data--run <https://github.com/ggerganov/llama.cpp"
"#prepare-data--run), and put the converted file in the models directory " "#prepare-data--run>`_ , and put the converted file in the models "
"and rename it to `ggml-model-q4_0.gguf`." "directory and rename it to `ggml-model-q4_0.gguf`."
msgstr "" msgstr ""
"您可以根据[llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp" "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-" "#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`。" "model-q4_0.gguf`。"
#: ../../getting_started/install/deploy.rst:304 #: ../../getting_started/install/deploy.rst:310
#: 5278c05568dd4ad688bcc181e45caa18 #: 3fe28d6e5eaa4bdf9c5c44a914c3577c
msgid "**Installing Dependencies**" msgid "**Installing Dependencies**"
msgstr "**安装依赖**" msgstr "**安装依赖**"
#: ../../getting_started/install/deploy.rst:306 #: ../../getting_started/install/deploy.rst:312
#: bd67bf651a9a4096a37e73851b5fad98 #: bdc10d2e88cc4c3f84a8c4a8dc2037a9
msgid "" msgid ""
"llama.cpp is an optional dependency in DB-GPT, and you can manually " "llama.cpp is an optional dependency in DB-GPT, and you can manually "
"install it using the following command:" "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" 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 #: ../../getting_started/install/deploy.rst:319
#: 71ed6ae4d0aa4d3ca27ebfffc42a5095 #: 9c136493448b43b5b27f66af74ff721e
msgid "**3.Modifying the Configuration File**" msgid "**3.Modifying the Configuration File**"
msgstr "**3.修改配置文件**" msgstr "**3.修改配置文件**"
#: ../../getting_started/install/deploy.rst:315 #: ../../getting_started/install/deploy.rst:321
#: a0a2fdb799524ef4938df2c306536e2a #: c835a7dee1dd409fb861e7b886c6dc5b
msgid "Next, you can directly modify your `.env` file to enable llama.cpp." msgid "Next, you can directly modify your `.env` file to enable llama.cpp."
msgstr "修改`.env`文件使用llama.cpp" msgstr "修改`.env`文件使用llama.cpp"
#: ../../getting_started/install/deploy.rst:322 #: ../../getting_started/install/deploy.rst:328
#: ../../getting_started/install/deploy.rst:390 #: ../../getting_started/install/deploy.rst:396
#: 03694cbb7dfa432cb32116925357f008 #: 296e6d08409544918fee0c31b1bf195c a81e5d882faf4722b0e10d53f635f53c
msgid "" msgid ""
"Then you can run it according to `Run <https://db-" "Then you can run it according to `Run <https://db-"
"gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html#run>`_" "gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html#run>`_"
msgstr "" msgstr ""
"然后你可以根据[运行](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-" "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" "cn/zh_CN/latest/getting_started/install/deploy/deploy.html#run>`_ 来运行。"
#: ../../getting_started/install/deploy.rst:325 #: ../../getting_started/install/deploy.rst:331
#: c9bbc15ea2fc4562bdf87a4e099600a0 #: 0f7f487ee11a4e01a95f7c504f0469ba
msgid "**More Configurations**" msgid "**More Configurations**"
msgstr "**更多配置文件**" msgstr "**更多配置文件**"
#: ../../getting_started/install/deploy.rst:327 #: ../../getting_started/install/deploy.rst:333
#: 9beff887d8554d1dac169de93625c1b2 #: b0f9964497f64fb5b3740099232cd72b
msgid "" msgid ""
"In DB-GPT, the model configuration can be done through `{model " "In DB-GPT, the model configuration can be done through `{model "
"name}_{config key}`." "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。" 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 #: ../../getting_started/install/deploy.rst:335
#: 6cad64bcc9f141de85479203b21f7f9e #: 7c225de4fe9d4dd3a3c2b2a33802e656
msgid "More Configurations" msgid "More Configurations"
msgstr "**更多配置文件**" msgstr "**更多配置文件**"
#: ../../getting_started/install/deploy.rst:333 #: ../../getting_started/install/deploy.rst:339
#: de97b0d5b59c4bfabbd47b7e1766cc70 #: 5cc1671910314796a9ce0b5107d3c9fe
msgid "Environment Variable Key" msgid "Environment Variable Key"
msgstr "环境变量Key" msgstr "环境变量Key"
#: ../../getting_started/install/deploy.rst:334 #: ../../getting_started/install/deploy.rst:340
#: 76afa3655f644576b54b4422bad3fcad #: 4359ed4e11bb47ad89a605cbf9016cd5
msgid "Default" msgid "Default"
msgstr "默认值" msgstr "默认值"
#: ../../getting_started/install/deploy.rst:335 #: ../../getting_started/install/deploy.rst:341
#: 0dcabfeeb4874e08ba53d4b4aa6a1d73 #: 5cf0efc6d1014665bb9dbdae96bf2726
msgid "Description" msgid "Description"
msgstr "描述" msgstr "描述"
#: ../../getting_started/install/deploy.rst:336 #: ../../getting_started/install/deploy.rst:342
#: c1670aec27cf4c068d825456817d7667 #: e7c291f80a9a40fa90d642901eca02c6
msgid "llama_cpp_prompt_template" msgid "llama_cpp_prompt_template"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:337 #: ../../getting_started/install/deploy.rst:343
#: ../../getting_started/install/deploy.rst:340
#: ../../getting_started/install/deploy.rst:346 #: ../../getting_started/install/deploy.rst:346
#: ../../getting_started/install/deploy.rst:352 #: ../../getting_started/install/deploy.rst:352
#: ../../getting_started/install/deploy.rst:358 #: ../../getting_started/install/deploy.rst:358
#: 49c8f875066f49c6aac195805f88e4a9 #: ../../getting_started/install/deploy.rst:364
#: 07dc7fc4e51e4d9faf8e5221bcf03ee0 549f3c57a2e9427880e457e653ce1182
#: 7ad961957f7b49d08e4aff347749b78d c1eab368175c4fa88fe0b471919523b2
#: e2e0bf9903484972b6d20e6837010029
msgid "None" msgid "None"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:338 #: ../../getting_started/install/deploy.rst:344
#: bb31e19533e5434b832d5975bf579dc3 #: 6b5044a2009f432c92fcd65db42506d8
msgid "" msgid ""
"Prompt template name, now support: zero_shot, vicuna_v1.1,alpaca,llama-2" "Prompt template name, now support: zero_shot, vicuna_v1.1,alpaca,llama-2"
",baichuan-chat,internlm-chat, If None, the prompt template is " ",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-" "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" "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 #: ../../getting_started/install/deploy.rst:345
#: 38ed23e19e2a47cf8fbacb035cfe1292 #: e01c860441ad43b88c0a8d012f97d2d8
msgid "llama_cpp_model_path" msgid "llama_cpp_model_path"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:341 #: ../../getting_started/install/deploy.rst:347
#: eb069fdfdfeb4b17b723ee6733ba50c2 #: 1cb68d772e454812a1a0c6de4950b8ce
msgid "Model path" msgid "Model path"
msgstr "模型路径" msgstr "模型路径"
#: ../../getting_started/install/deploy.rst:342 #: ../../getting_started/install/deploy.rst:348
#: 348d3ff3e4f44ceb99aadead11f5cca5 #: 6dac03820edb4fbd8a0856405e84c5bc
msgid "llama_cpp_n_gpu_layers" msgid "llama_cpp_n_gpu_layers"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:343 #: ../../getting_started/install/deploy.rst:349
#: 007deecf593b4553b6ca8df3e9240a28 #: 8cd5607b7941427f9a342ca7a00e5778
msgid "1000000000" msgid "1000000000"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:344 #: ../../getting_started/install/deploy.rst:350
#: 4da435c417f0482581895bf4d052a6a1 #: 61c9297656da434aa7ac2b49cf61ea9d
msgid "" msgid ""
"Number of layers to offload to the GPU, Set this to 1000000000 to offload" "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" " all layers to the GPU. If your GPU VRAM is not enough, you can set a low"
" number, eg: 10" " 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。" 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 #: ../../getting_started/install/deploy.rst:351
#: 4f186505ea81467590cf817d116e6879 #: 8c2d2182557a483aa2fda590c24faaf3
msgid "llama_cpp_n_threads" msgid "llama_cpp_n_threads"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:347 #: ../../getting_started/install/deploy.rst:353
#: b94dc2fb2cd14a4a8f38ba95b05fbb5b #: cc442f61ffc442ecbd98c1e7f5598e1a
msgid "" msgid ""
"Number of threads to use. If None, the number of threads is automatically" "Number of threads to use. If None, the number of threads is automatically"
" determined" " determined"
msgstr "要使用的线程数量。如果为None，则线程数量将自动确定。" 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 #: ../../getting_started/install/deploy.rst:354
#: 867f2357430440eba4e749a8a39bff18 #: 8d5e917d86f048348106e6923638a0c2
msgid "llama_cpp_n_batch" msgid "llama_cpp_n_batch"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:349 #: ../../getting_started/install/deploy.rst:355
#: 78516f7b23264147bae11e13426097eb #: ee2719a0a8cd4a77846cffd8e675638f
msgid "512" msgid "512"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:350 #: ../../getting_started/install/deploy.rst:356
#: c2ec97ffef3e4a70afef6634e78801a2 #: 845b354315384762a611ad2daa539d57
msgid "Maximum number of prompt tokens to batch together when calling llama_eval" 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" 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 #: ../../getting_started/install/deploy.rst:357
#: 29ad3c5ab7134da49d6fca3b42d734d6 #: a95e788bfa5f46f3bcd6356dfd9f87eb
msgid "llama_cpp_n_gqa" msgid "llama_cpp_n_gqa"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:353 #: ../../getting_started/install/deploy.rst:359
#: e5bc322b0c824465b1adbd162838a3b7 #: 23ad9b5f34b5440bb90b2b21bab25763
msgid "Grouped-query attention. Must be 8 for llama-2 70b." 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。" msgstr "对于 llama-2 70B 模型，Grouped-query attention 必须为8。"
#: ../../getting_started/install/deploy.rst:354 #: ../../getting_started/install/deploy.rst:360
#: 43e7d412238a4f0ba8227938d9fa4172 #: 9ce25b7966fc40ec8be47ecfaf5f9994
msgid "llama_cpp_rms_norm_eps" msgid "llama_cpp_rms_norm_eps"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:355 #: ../../getting_started/install/deploy.rst:361
#: 6328db04645b4b089593291e2ca13f79 #: 58365f0d36af447ba976213646018431
msgid "5e-06" msgid "5e-06"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:356 #: ../../getting_started/install/deploy.rst:362
#: 6c8bf631cece42fa86954f5cf2d75503 #: d00b742a759140b795ba5949f1ce9a36
msgid "5e-6 is a good value for llama-2 models." 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。" msgstr "对于llama-2模型来说，5e-6是一个不错的值。"
#: ../../getting_started/install/deploy.rst:357 #: ../../getting_started/install/deploy.rst:363
#: 22ebee39fe8b4cc18378447cac67e631 #: b9972e9b19354f55a5e6d9c50513a620
msgid "llama_cpp_cache_capacity" msgid "llama_cpp_cache_capacity"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:359 #: ../../getting_started/install/deploy.rst:365
#: 4dc98bede90f4237829f65513e4adf61 #: 3c98c5396dd74db8b6d70fc50fa0754f
msgid "Maximum cache capacity. Examples: 2000MiB, 2GiB" msgid "Maximum cache capacity. Examples: 2000MiB, 2GiB"
msgstr "模型缓存最大值. 例如: 2000MiB, 2GiB" msgstr "模型缓存最大值. 例如: 2000MiB, 2GiB"
#: ../../getting_started/install/deploy.rst:360 #: ../../getting_started/install/deploy.rst:366
#: bead617b5af943dab0bc1209823d3c22 #: 4277e155992c4442b69d665d6269bed6
msgid "llama_cpp_prefer_cpu" msgid "llama_cpp_prefer_cpu"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:361 #: ../../getting_started/install/deploy.rst:367
#: 8efb44f1cfc54b1a8b3ca8ea138113ee #: 049169c1210a4ecabb25702ed813ea0a
msgid "False" msgid "False"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:362 #: ../../getting_started/install/deploy.rst:368
#: b854e6a44c8348ceb72ac382b73ceec5 #: 60a39e93e7874491a93893de78b7d37e
msgid "" msgid ""
"If a GPU is available, it will be preferred by default, unless " "If a GPU is available, it will be preferred by default, unless "
"prefer_cpu=False is configured." "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。" 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 #: ../../getting_started/install/deploy.rst:371
#: 41b0440eb0074e5fa8c87dd404efe0ce #: 7c86780fbf634de8873afd439389cf89
msgid "vllm" msgid "vllm"
msgstr "" msgstr ""
#: ../../getting_started/install/deploy.rst:367 #: ../../getting_started/install/deploy.rst:373
#: 6fc445675bf74b2ea2fe0c7f2a64db69 #: e2827892e43d420c85b8b83c4855d197
msgid "vLLM is a fast and easy-to-use library for LLM inference and serving." 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 #: ../../getting_started/install/deploy.rst:375
#: aab5f913d29445c4b345180b8793ebc7 #: 81bbfa3876a74244acc82d295803fdd4
msgid "**Running vLLM**" msgid "**Running vLLM**"
msgstr "**运行vLLM**" msgstr "**运行vLLM**"
#: ../../getting_started/install/deploy.rst:371 #: ../../getting_started/install/deploy.rst:377
#: a9560d697821404cb0abdabf9f479645 #: 75bc518b444c417ba4d9c15246549327
msgid "**1.Installing Dependencies**" msgid "**1.Installing Dependencies**"
msgstr "**1.安装依赖**" msgstr "**1.安装依赖**"
#: ../../getting_started/install/deploy.rst:373 #: ../../getting_started/install/deploy.rst:379
#: b008224d4f314e5c988335262c95a42e #: 725c620b0a5045c1a64a3b2a2e9b48f3
msgid "" msgid ""
"vLLM is an optional dependency in DB-GPT, and you can manually install it" "vLLM is an optional dependency in DB-GPT, and you can manually install it"
" using the following command:" " 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：" 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 #: ../../getting_started/install/deploy.rst:385
#: 7dc0c8e996124177935a4e0d9ef19837 #: 6f4b540107764f3592cc07cf170e4911
msgid "**2.Modifying the Configuration File**" msgid "**2.Modifying the Configuration File**"
msgstr "**2.修改配置文件**" msgstr "**2.修改配置文件**"
#: ../../getting_started/install/deploy.rst:381 #: ../../getting_started/install/deploy.rst:387
#: 49667576b44c46bf87d5bf4d207dd63a #: b8576a1572674c4890e09b73e02cf0e8
msgid "Next, you can directly modify your .env file to enable vllm." 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" msgstr "你可以直接修改你的 `.env` 文件"
#: ../../getting_started/install/deploy.rst:388 #: ../../getting_started/install/deploy.rst:394
#: f16a78f0ee6545babab0d66f12654c0a #: b006745f3aee4651aaa0cf79081b5d7f
msgid "" msgid ""
"You can view the models supported by vLLM `here " "You can view the models supported by vLLM `here "
"<https://vllm.readthedocs.io/en/latest/models/supported_models.html" "<https://vllm.readthedocs.io/en/latest/models/supported_models.html"
"#supported-models>`_" "#supported-models>`_"
msgstr "" msgstr ""
"你可以在 " "你可以在 `这里 "
"[这里](https://vllm.readthedocs.io/en/latest/models/supported_models.html" "<https://vllm.readthedocs.io/en/latest/models/supported_models.html"
"#supported-models) 查看 vLLM 支持的模型。" "#supported-models>`_ 查看 vLLM 支持的模型。"
#: ../../getting_started/install/deploy.rst:397 #: ../../getting_started/install/deploy.rst:403
#: f7ae366723e9494d8177eeb963ba0ed9 #: bc8057ee75e14737bf8fca3ceb555dac
msgid "3.Prepare sql example(Optional)" msgid "3.Prepare sql example(Optional)"
msgstr "3.准备 sql example(可选)" msgstr "3.准备 sql example(可选)"
#: ../../getting_started/install/deploy.rst:398 #: ../../getting_started/install/deploy.rst:404
#: d302aac8ddb346598fc9d73e0f6c2cbc #: 9b0b9112237c4b3aaa1dd5d704ea32e6
msgid "**(Optional) load examples into SQLite**" 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 #: ../../getting_started/install/deploy.rst:411
#: ae2a315e40854f27a074f2c0f2506014 #: 0815e13b96264ffcba1526c82ba2e7c8
msgid "On windows platform:" msgid "On windows platform:"
msgstr "" msgstr "在 Windows 平台："
#: ../../getting_started/install/deploy.rst:412 #: ../../getting_started/install/deploy.rst:418
#: 36b4b7a813844af3a4ec8062b39059a3 #: 577a4167ecac4fa88586961f225f0487
msgid "4.Run db-gpt server" msgid "4.Run db-gpt server"
msgstr "4.运行db-gpt server" msgstr "4.运行db-gpt server"
#: ../../getting_started/install/deploy.rst:418 #: ../../getting_started/install/deploy.rst:424
#: e56f15e563484027b7efb2147c9b71a7 #: a9f96b064b674f80824257b4b0a18e2a
msgid "**Open http://localhost:5000 with your browser to see the product.**" msgid "**Open http://localhost:5000 with your browser to see the product.**"
msgstr "打开浏览器访问http://localhost:5000" 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." #~ " LLM model."
#~ msgstr "" #~ msgstr ""
#~ msgid "百川"
#~ msgstr ""
#~ msgid "百川 硬件要求"
#~ msgstr ""

172
docs/locales/zh_CN/LC_MESSAGES/index.po
View File

@ -8,7 +8,7 @@ msgid ""
msgstr "" msgstr ""
"Project-Id-Version: DB-GPT 0.3.0\n" "Project-Id-Version: DB-GPT 0.3.0\n"
"Report-Msgid-Bugs-To: \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" "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n" "Language: zh_CN\n"
@ -19,31 +19,27 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n" "Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\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" msgid "Getting Started"
msgstr "开始" msgstr "开始"
#: ../../index.rst:60 ../../index.rst:81 0f2fc16a44b043019556f5f3e0d0e2c0 #: ../../index.rst:60 ../../index.rst:81 1a4e8a5dc7754967a0af9fb3d2e53017
msgid "Modules" msgid "Modules"
msgstr "模块" msgstr "模块"
#: ../../index.rst:95 ../../index.rst:111 2624521b920a4b3b9eac3fec76635ab8 #: ../../index.rst:96 ../../index.rst:99 c815772ae8514f0c9b26911b0dd73f54
msgid "Use Cases"
msgstr "示例"
#: ../../index.rst:125 ../../index.rst:128 accec2bb9c5149f184a87e03955d6b22
msgid "Reference" msgid "Reference"
msgstr "参考" msgstr "参考"
#: ../../index.rst:138 ../../index.rst:144 26278dabd4944d1a9f14330e83935162 #: ../../index.rst:109 ../../index.rst:115 dabe4c3409df489f84e4ec588f2b34a5
msgid "Resources" msgid "Resources"
msgstr "资源" msgstr "资源"
#: ../../index.rst:7 9277d505dda74ae0862cd09d05cf5e63 #: ../../index.rst:7 7626b01b253546ac83ca0cf130dfa091
msgid "Welcome to DB-GPT!" msgid "Welcome to DB-GPT!"
msgstr "欢迎来到DB-GPT中文文档" msgstr "欢迎来到DB-GPT中文文档"
#: ../../index.rst:8 9fa76a01965746978a00ac411fca13a8 #: ../../index.rst:8 6037e5e0d7f7428ba92315a91ccfd53f
msgid "" msgid ""
"As large models are released and iterated upon, they are becoming " "As large models are released and iterated upon, they are becoming "
"increasingly intelligent. However, in the process of using large models, " "increasingly intelligent. However, in the process of using large models, "
@ -61,7 +57,7 @@ msgstr ""
"，我们启动了DB-" "，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。" "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 "" msgid ""
"**DB-GPT** is an experimental open-source project that uses localized GPT" "**DB-GPT** is an experimental open-source project that uses localized GPT"
" large models to interact with your data and environment. With this " " 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%" "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。" " 安全。"
#: ../../index.rst:12 7032e17191394f7090141927644fb512 #: ../../index.rst:12 9cfb7515430d49af8a1ca47f60264a58
msgid "**Features**" msgid "**Features**"
msgstr "特性" msgstr "特性"
#: ../../index.rst:13 5a7a8e5eace34d5f9a4f779bf5122928 #: ../../index.rst:13 2a1f84e455c84d9ca66c65f92e5b0d78
msgid "" msgid ""
"Currently, we have released multiple key features, which are listed below" "Currently, we have released multiple key features, which are listed below"
" to demonstrate our current capabilities:" " 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。" 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" msgid "SQL language capabilities - SQL generation - SQL diagnosis"
msgstr "SQL语言能力 - SQL生成 - SQL诊断" msgstr "SQL语言能力 - SQL生成 - SQL诊断"
#: ../../index.rst:19 556eaf756fec431ca5c453208292ab4f #: ../../index.rst:19 edfeef5284e7426a9e551e782bc5702c
msgid "" msgid ""
"Private domain Q&A and data processing - Database knowledge Q&A - Data " "Private domain Q&A and data processing - Database knowledge Q&A - Data "
"processing" "processing"
msgstr "私有领域问答与数据处理 - 数据库知识问答 - 数据处理" 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 "" msgid ""
"Plugins - Support custom plugin execution tasks and natively support the " "Plugins - Support custom plugin execution tasks and natively support the "
"Auto-GPT plugin, such as:" "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" 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 "" msgid ""
"Unified vector storage/indexing of knowledge base - Support for " "Unified vector storage/indexing of knowledge base - Support for "
"unstructured data such as PDF, Markdown, CSV, and WebURL" "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" 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 #, fuzzy
msgid "" msgid ""
"Multi LLMs Support - Supports multiple large language models, currently " "Multi LLMs Support - Supports multiple large language models, currently "
@ -111,63 +107,63 @@ msgid ""
"codet5p" "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)" 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 "" msgid ""
"How to get started using DB-GPT to interact with your data and " "How to get started using DB-GPT to interact with your data and "
"environment." "environment."
msgstr "开始使用DB-GPT与您的数据环境进行交互。" 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 #, fuzzy
msgid "`Quickstart Guide <./getting_started/getting_started.html>`_" msgid "`Quickstart Guide <./getting_started/getting_started.html>`_"
msgstr "`使用指南 <./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" msgid "Concepts and terminology"
msgstr "相关概念" msgstr "相关概念"
#: ../../index.rst:40 887cc43a3a134aba96eb7ca11e5ca86f #: ../../index.rst:40 ded4d9f80066498e90ba6214520013f7
#, fuzzy #, fuzzy
msgid "`Concepts and Terminology <./getting_started/concepts.html>`_" msgid "`Concepts and Terminology <./getting_started/concepts.html>`_"
msgstr "`相关概念 <./getting_started/concepts.html>`_" msgstr "`相关概念 <./getting_started/concepts.html>`_"
#: ../../index.rst:42 133e25c7dce046b1ab262489ecb60b4a #: ../../index.rst:42 cd662e53621e474d901146813c750044
msgid "Coming soon..." msgid "Coming soon..."
msgstr "" msgstr ""
#: ../../index.rst:44 a9e0812d32714a6f81ed75aa70f0c20e #: ../../index.rst:44 15edba57f1de44af8aff76735a2593de
msgid "`Tutorials <.getting_started/tutorials.html>`_" msgid "`Tutorials <.getting_started/tutorials.html>`_"
msgstr "`教程 <.getting_started/tutorials.html>`_" msgstr "`教程 <.getting_started/tutorials.html>`_"
#: ../../index.rst:62 4fccfd3082174f58926a9811f39e4d96 #: ../../index.rst:62 779454b29d8e4e6eb21497025922d1b8
msgid "" msgid ""
"These modules are the core abstractions with which we can interact with " "These modules are the core abstractions with which we can interact with "
"data and environment smoothly." "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。" 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 "" msgid ""
"It's very important for DB-GPT, DB-GPT also provide standard, extendable " "It's very important for DB-GPT, DB-GPT also provide standard, extendable "
"interfaces." "interfaces."
msgstr "DB-GPT还提供了标准的、可扩展的接口。" 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 "" msgid ""
"The docs for each module contain quickstart examples, how to guides, " "The docs for each module contain quickstart examples, how to guides, "
"reference docs, and conceptual 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。" 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" msgid "The modules are as follows"
msgstr "组成模块如下：" msgstr "组成模块如下："
#: ../../index.rst:69 442683a5f154429da87f452e49bcbb5c #: ../../index.rst:69 4a19083cadd04b8e8b649a622e0ceccd
msgid "" msgid ""
"`LLMs <./modules/llms.html>`_: Supported multi models management and " "`LLMs <./modules/llms.html>`_: Supported multi models management and "
"integrations." "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。 " 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 "" msgid ""
"`Prompts <./modules/prompts.html>`_: Prompt management, optimization, and" "`Prompts <./modules/prompts.html>`_: Prompt management, optimization, and"
" serialization for multi database." " 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 " "`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" "，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." 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。" 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 #, fuzzy
msgid "" msgid ""
"`Knowledge <./modules/knowledge.html>`_: Knowledge management, embedding," "`Knowledge <./modules/knowledge.html>`_: Knowledge management, embedding,"
" and search." " and search."
msgstr "`知识库能力： <./modules/knowledge.html>`_: 支持私域知识库问答能力, " 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 "" msgid ""
"`Connections <./modules/connections.html>`_: Supported multi databases " "`Connections <./modules/connections.html>`_: Supported multi databases "
"connection. management connections and interact with this." "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 " 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 #, fuzzy
msgid "`Vector <./modules/vector.html>`_: Supported multi vector database." 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。 " 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 #: ../../index.rst:97 9aceee0dbe1e4f7da499ac6aab23aea2
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
msgid "" msgid ""
"Full documentation on all methods, classes, installation methods, and " "Full documentation on all methods, classes, installation methods, and "
"integration setups for DB-GPT." "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。" 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 "" msgid ""
"Additional resources we think may be useful as you develop your " "Additional resources we think may be useful as you develop your "
"application!" "application!"
msgstr "“我们认为在您开发应用程序时可能有用的其他资源!”" 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 "" msgid ""
"`Discord <https://discord.gg/eZHE94MN>`_: if your have some problem or " "`Discord <https://discord.gg/eZHE94MN>`_: if your have some problem or "
"ideas, you can talk from discord." "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" #~ 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" #~ 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。"

1
pilot/model/cluster/worker/manager.py
View File

@ -1021,6 +1021,7 @@ def run_worker_manager(
system_app, system_app,
os.path.join(LOGDIR, worker_params.tracer_file), os.path.join(LOGDIR, worker_params.tracer_file),
root_operation_name="DB-GPT-WorkerManager-Entry", root_operation_name="DB-GPT-WorkerManager-Entry",
tracer_storage_cls=worker_params.tracer_storage_cls,
) )
_start_local_worker(worker_manager, worker_params) _start_local_worker(worker_manager, worker_params)

18
pilot/model/parameter.py
View File

@ -88,6 +88,12 @@ class ModelControllerParameters(BaseParameters):
"help": "The filename to store tracer span records", "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 @dataclass
@ -138,6 +144,12 @@ class ModelAPIServerParameters(BaseParameters):
"help": "The filename to store tracer span records", "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 @dataclass
@ -226,6 +238,12 @@ class ModelWorkerParameters(BaseModelParameters):
"help": "The filename to store tracer span records", "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 @dataclass

5
pilot/model/proxy/llms/tongyi.py
View File

@ -36,7 +36,10 @@ def tongyi_generate_stream(
if message.role == ModelMessageRoleType.HUMAN: if message.role == ModelMessageRoleType.HUMAN:
history.append({"role": "user", "content": message.content}) history.append({"role": "user", "content": message.content})
for message in messages: 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}) history.append({"role": "user", "content": message.content})
# elif message.role == ModelMessageRoleType.HUMAN: # elif message.role == ModelMessageRoleType.HUMAN:
# history.append({"role": "user", "content": message.content}) # history.append({"role": "user", "content": message.content})

6
pilot/server/base.py
View File

@ -147,6 +147,12 @@ class WebWerverParameters(BaseParameters):
"help": "The filename to store tracer span records", "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( disable_alembic_upgrade: Optional[bool] = field(
default=False, default=False,
metadata={ metadata={

6
pilot/server/dbgpt_server.py
View File

@ -195,7 +195,11 @@ def run_uvicorn(param: WebWerverParameters):
def run_webserver(param: WebWerverParameters = None): def run_webserver(param: WebWerverParameters = None):
if not param: if not param:
param = _get_webserver_params() 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( with root_tracer.start_span(
"run_webserver", "run_webserver",

7
pilot/utils/tracer/__init__.py
View File

@ -7,7 +7,11 @@ from pilot.utils.tracer.base import (
SpanStorageType, SpanStorageType,
TracerContext, 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 ( from pilot.utils.tracer.tracer_impl import (
root_tracer, root_tracer,
trace, trace,
@ -26,6 +30,7 @@ __all__ = [
"TracerContext", "TracerContext",
"MemorySpanStorage", "MemorySpanStorage",
"FileSpanStorage", "FileSpanStorage",
"SpanStorageContainer",
"root_tracer", "root_tracer",
"trace", "trace",
"initialize_tracer", "initialize_tracer",

7
pilot/utils/tracer/base.py
View File

@ -1,6 +1,6 @@
from __future__ import annotations from __future__ import annotations
from typing import Dict, Callable, Optional from typing import Dict, Callable, Optional, List
from dataclasses import dataclass from dataclasses import dataclass
from abc import ABC, abstractmethod from abc import ABC, abstractmethod
from enum import Enum from enum import Enum
@ -121,6 +121,11 @@ class SpanStorage(BaseComponent, ABC):
def append_span(self, span: Span): def append_span(self, span: Span):
"""Store the given span. This needs to be implemented by subclasses.""" """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): class Tracer(BaseComponent, ABC):
"""Abstract base class for tracing operations. """Abstract base class for tracing operations.

117
pilot/utils/tracer/span_storage.py
View File

@ -5,11 +5,12 @@ import datetime
import threading import threading
import queue import queue
import logging import logging
from typing import Optional, List
from concurrent.futures import Executor, ThreadPoolExecutor
from pilot.component import SystemApp from pilot.component import SystemApp
from pilot.utils.tracer.base import Span, SpanStorage from pilot.utils.tracer.base import Span, SpanStorage
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@ -24,8 +25,81 @@ class MemorySpanStorage(SpanStorage):
self.spans.append(span) 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): class FileSpanStorage(SpanStorage):
def __init__(self, filename: str, batch_size=10, flush_interval=10): def __init__(self, filename: str):
super().__init__() super().__init__()
self.filename = filename self.filename = filename
# Split filename into prefix and suffix # Split filename into prefix and suffix
@ -36,29 +110,18 @@ class FileSpanStorage(SpanStorage):
datetime.datetime.now().date() datetime.datetime.now().date()
) # Store the current date for checking date changes ) # Store the current date for checking date changes
self.queue = queue.Queue() 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): if not os.path.exists(filename):
# New file if not exist # New file if not exist
os.makedirs(os.path.dirname(filename), exist_ok=True) os.makedirs(os.path.dirname(filename), exist_ok=True)
with open(filename, "a"): with open(filename, "a"):
pass pass
self.flush_thread = threading.Thread(target=self._flush_to_file, daemon=True)
self.flush_thread.start()
def append_span(self, span: Span): def append_span(self, span: Span):
span_data = span.to_dict() self._write_to_file([span])
logger.debug(f"append span: {span_data}")
self.queue.put(span_data)
if self.queue.qsize() >= self.batch_size: def append_span_batch(self, spans: List[Span]):
try: self._write_to_file(spans)
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 _get_dated_filename(self, date: datetime.date) -> str: def _get_dated_filename(self, date: datetime.date) -> str:
"""Return the filename based on a specific date.""" """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)) os.rename(self.filename, self._get_dated_filename(self.last_date))
self.last_date = current_date self.last_date = current_date
def _write_to_file(self): def _write_to_file(self, spans: List[Span]):
self._roll_over_if_needed() 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: with open(self.filename, "a") as file:
for span_data in spans_to_write: for span in spans:
span_data = span.to_dict()
try: try:
file.write(json.dumps(span_data, ensure_ascii=False) + "\n") file.write(json.dumps(span_data, ensure_ascii=False) + "\n")
except Exception as e: except Exception as e:
logger.warning( logger.warning(
f"Write span to file failed: {str(e)}, span_data: {span_data}" 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()

95
pilot/utils/tracer/tests/test_span_storage.py
View File

@ -7,44 +7,53 @@ import time
from unittest.mock import patch from unittest.mock import patch
from datetime import datetime, timedelta 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 @pytest.fixture
def storage(request): def storage(request):
if not request or not hasattr(request, "param"): if not request or not hasattr(request, "param"):
batch_size = 10
flush_interval = 10
file_does_not_exist = False file_does_not_exist = False
else: 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) file_does_not_exist = request.param.get("file_does_not_exist", False)
if file_does_not_exist: if file_does_not_exist:
with tempfile.TemporaryDirectory() as tmp_dir: with tempfile.TemporaryDirectory() as tmp_dir:
filename = os.path.join(tmp_dir, "non_existent_file.jsonl") filename = os.path.join(tmp_dir, "non_existent_file.jsonl")
storage_instance = FileSpanStorage( storage_instance = FileSpanStorage(filename)
filename, batch_size=batch_size, flush_interval=flush_interval
)
yield storage_instance yield storage_instance
else: else:
with tempfile.NamedTemporaryFile(delete=True) as tmp_file: with tempfile.NamedTemporaryFile(delete=True) as tmp_file:
filename = tmp_file.name filename = tmp_file.name
storage_instance = FileSpanStorage( storage_instance = FileSpanStorage(filename)
filename, batch_size=batch_size, flush_interval=flush_interval
)
yield storage_instance 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): def read_spans_from_file(filename):
with open(filename, "r") as f: with open(filename, "r") as f:
return [json.loads(line) for line in f.readlines()] 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): def test_write_span(storage: SpanStorage):
span = Span("1", "a", SpanType.BASE, "b", "op1") span = Span("1", "a", SpanType.BASE, "b", "op1")
storage.append_span(span) storage.append_span(span)
@ -55,9 +64,6 @@ def test_write_span(storage: SpanStorage):
assert spans_in_file[0]["trace_id"] == "1" 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): def test_incremental_write(storage: SpanStorage):
span1 = Span("1", "a", SpanType.BASE, "b", "op1") span1 = Span("1", "a", SpanType.BASE, "b", "op1")
span2 = Span("2", "c", SpanType.BASE, "d", "op2") span2 = Span("2", "c", SpanType.BASE, "d", "op2")
@ -70,9 +76,6 @@ def test_incremental_write(storage: SpanStorage):
assert len(spans_in_file) == 2 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): def test_sync_and_async_append(storage: SpanStorage):
span = Span("1", "a", SpanType.BASE, "b", "op1") 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 assert len(spans_in_file) == 2
@pytest.mark.asyncio @pytest.mark.parametrize("storage", [{"file_does_not_exist": True}], indirect=True)
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
)
def test_non_existent_file(storage: SpanStorage): def test_non_existent_file(storage: SpanStorage):
span = Span("1", "a", SpanType.BASE, "b", "op1") span = Span("1", "a", SpanType.BASE, "b", "op1")
span2 = Span("2", "c", SpanType.BASE, "d", "op2") span2 = Span("2", "c", SpanType.BASE, "d", "op2")
@ -116,7 +99,7 @@ def test_non_existent_file(storage: SpanStorage):
time.sleep(0.1) time.sleep(0.1)
spans_in_file = read_spans_from_file(storage.filename) 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) storage.append_span(span2)
time.sleep(0.1) time.sleep(0.1)
@ -126,9 +109,7 @@ def test_non_existent_file(storage: SpanStorage):
assert spans_in_file[1]["trace_id"] == "2" assert spans_in_file[1]["trace_id"] == "2"
@pytest.mark.parametrize( @pytest.mark.parametrize("storage", [{"file_does_not_exist": True}], indirect=True)
"storage", [{"batch_size": 1, "file_does_not_exist": True}], indirect=True
)
def test_log_rollover(storage: SpanStorage): def test_log_rollover(storage: SpanStorage):
# mock start date # mock start date
mock_start_date = datetime(2023, 10, 18, 23, 59) 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) spans_in_dated_file = read_spans_from_file(dated_filename)
assert len(spans_in_dated_file) == 1 assert len(spans_in_dated_file) == 1
assert spans_in_dated_file[0]["trace_id"] == "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

17
pilot/utils/tracer/tracer_impl.py
View File

@ -3,6 +3,7 @@ from contextvars import ContextVar
from functools import wraps from functools import wraps
import asyncio import asyncio
import inspect import inspect
import logging
from pilot.component import SystemApp, ComponentType from pilot.component import SystemApp, ComponentType
@ -15,6 +16,9 @@ from pilot.utils.tracer.base import (
TracerContext, TracerContext,
) )
from pilot.utils.tracer.span_storage import MemorySpanStorage 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): class DefaultTracer(Tracer):
@ -197,10 +201,11 @@ def initialize_tracer(
system_app: SystemApp, system_app: SystemApp,
tracer_filename: str, tracer_filename: str,
root_operation_name: str = "DB-GPT-Web-Entry", root_operation_name: str = "DB-GPT-Web-Entry",
tracer_storage_cls: str = None,
): ):
if not system_app: if not system_app:
return return
from pilot.utils.tracer.span_storage import FileSpanStorage from pilot.utils.tracer.span_storage import FileSpanStorage, SpanStorageContainer
trace_context_var = ContextVar( trace_context_var = ContextVar(
"trace_context", "trace_context",
@ -208,7 +213,15 @@ def initialize_tracer(
) )
tracer = DefaultTracer(system_app) 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) system_app.register_instance(tracer)
root_tracer.initialize(system_app, trace_context_var) root_tracer.initialize(system_app, trace_context_var)
if system_app.app: if system_app.app: