github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-04 01:50:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs:v0.3.1 docs

Browse Source 
1.fmt
2.docs
This commit is contained in:
aries_ckt 2023-07-13 19:23:03 +08:00
parent 4e33e6ec2e
commit b5f3e079db
19 changed files with 374 additions and 179 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
docs/locales/zh_CN/LC_MESSAGES/getting_started/getting_started.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: 2023-07-05 17:51+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -19,29 +19,29 @@ 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/getting_started.md:1 2e1519d628044c07b384e8bbe441863a #: ../../getting_started/getting_started.md:1 0b2e795438a3413c875fd80191e85bad
msgid "Quickstart Guide" msgid "Quickstart Guide"
msgstr "使用指南" msgstr "使用指南"
#: ../../getting_started/getting_started.md:3 00e8dc6e242d4f3b8b2fbc5e06f1f14e #: ../../getting_started/getting_started.md:3 7b84c9776f8a4f9fb55afc640f37f45c
msgid "" msgid ""
"This tutorial gives you a quick walkthrough about use DB-GPT with you " "This tutorial gives you a quick walkthrough about use DB-GPT with you "
"environment and data." "environment and data."
msgstr "本教程为您提供了关于如何使用DB-GPT的使用指南。" msgstr "本教程为您提供了关于如何使用DB-GPT的使用指南。"
#: ../../getting_started/getting_started.md:5 4b4473a5fbd64cef996d82fa36abe136 #: ../../getting_started/getting_started.md:5 1b2880e1ef674bfdbf39ac9f330aeec9
msgid "Installation" msgid "Installation"
msgstr "安装" msgstr "安装"
#: ../../getting_started/getting_started.md:7 5ab3187dd2134afe958d83a431c98f43 #: ../../getting_started/getting_started.md:7 d0a8c6654bfe4bbdb0eb40ceb2ea3388
msgid "To get started, install DB-GPT with the following steps." msgid "To get started, install DB-GPT with the following steps."
msgstr "请按照以下步骤安装DB-GPT" msgstr "请按照以下步骤安装DB-GPT"
#: ../../getting_started/getting_started.md:9 7286e3a0da00450c9a6e9f29dbd27130 #: ../../getting_started/getting_started.md:9 0a4e0b06c7fe49a9b2ca56ba2eb7b8ba
msgid "1. Hardware Requirements" msgid "1. Hardware Requirements"
msgstr "1. 硬件要求" msgstr "1. 硬件要求"
#: ../../getting_started/getting_started.md:10 3f3d279ca8a54c8c8ed16af3e0ffb281 #: ../../getting_started/getting_started.md:10 2b42f6546ef141f696943ba2120584e5
msgid "" msgid ""
"As our project has the ability to achieve ChatGPT performance of over " "As our project has the ability to achieve ChatGPT performance of over "
"85%, there are certain hardware requirements. However, overall, the " "85%, there are certain hardware requirements. However, overall, the "
@ -49,62 +49,62 @@ msgid ""
"specific hardware requirements for deployment are as follows:" "specific hardware requirements for deployment are as follows:"
msgstr "由于我们的项目有能力达到85%以上的ChatGPT性能，所以对硬件有一定的要求。但总体来说，我们在消费级的显卡上即可完成项目的部署使用，具体部署的硬件说明如下:" msgstr "由于我们的项目有能力达到85%以上的ChatGPT性能，所以对硬件有一定的要求。但总体来说，我们在消费级的显卡上即可完成项目的部署使用，具体部署的硬件说明如下:"
#: ../../getting_started/getting_started.md 6e1e882511254687bd46fe45447794d1 #: ../../getting_started/getting_started.md 4df0c44eff8741f39ca0fdeff222f90c
msgid "GPU" msgid "GPU"
msgstr "GPU" msgstr "GPU"
#: ../../getting_started/getting_started.md f0ee9919e1254bcdbe6e489a5fbf450f #: ../../getting_started/getting_started.md b740a2991ce546cca43a426b760e9901
msgid "VRAM Size" msgid "VRAM Size"
msgstr "显存大小" msgstr "显存大小"
#: ../../getting_started/getting_started.md eed88601ef0b49b58d95b89928a3810e #: ../../getting_started/getting_started.md 222b91ff82f14d12acaac5aa238758c8
msgid "Performance" msgid "Performance"
msgstr "显存大小" msgstr "显存大小"
#: ../../getting_started/getting_started.md 4f717383ef2d4e2da9ee2d1c148aa6c5 #: ../../getting_started/getting_started.md c2d2ae6a4c964c4f90a9009160754782
msgid "RTX 4090" msgid "RTX 4090"
msgstr "RTX 4090" msgstr "RTX 4090"
#: ../../getting_started/getting_started.md d2d9bd1b57694404b39cdef49fd5b570 #: ../../getting_started/getting_started.md 529220ec6a294e449dc460ba2e8829a1
#: d7d914b8d5e34ac192b94d48f0ee1781 #: 5e0c5900842e4d66b2064b13cc31a3ad
msgid "24 GB" msgid "24 GB"
msgstr "24 GB" msgstr "24 GB"
#: ../../getting_started/getting_started.md cb86730ab05e4172941c3e771384c4ba #: ../../getting_started/getting_started.md 84d29eef342f4d6282295c0e32487548
msgid "Smooth conversation inference" msgid "Smooth conversation inference"
msgstr "可以流畅的进行对话推理，无卡顿" msgstr "可以流畅的进行对话推理，无卡顿"
#: ../../getting_started/getting_started.md 3e32d5c38bf6499cbfedb80944549114 #: ../../getting_started/getting_started.md 5a10effe322e4afb8315415c04dc05a4
msgid "RTX 3090" msgid "RTX 3090"
msgstr "RTX 3090" msgstr "RTX 3090"
#: ../../getting_started/getting_started.md 1d3caa2a06844997ad55d20863559e9f #: ../../getting_started/getting_started.md 8924059525ab43329a8bb6659e034d5e
msgid "Smooth conversation inference, better than V100" msgid "Smooth conversation inference, better than V100"
msgstr "可以流畅进行对话推理，有卡顿感，但好于V100" msgstr "可以流畅进行对话推理，有卡顿感，但好于V100"
#: ../../getting_started/getting_started.md b80ec359bd004d5f801ec09ca3b2d0ff #: ../../getting_started/getting_started.md 10f5bc076f524127a956d7a23f3666ba
msgid "V100" msgid "V100"
msgstr "V100" msgstr "V100"
#: ../../getting_started/getting_started.md aed55a6b8c8d49d9b9c02bfd5c10b062 #: ../../getting_started/getting_started.md 7d664e81984847c7accd08db93fad404
msgid "16 GB" msgid "16 GB"
msgstr "16 GB" msgstr "16 GB"
#: ../../getting_started/getting_started.md dcd6daab75fe4bf8b8dd19ea785f0bd6 #: ../../getting_started/getting_started.md 86765bc9ab01409fb7f5edf04f9b32a5
msgid "Conversation inference possible, noticeable stutter" msgid "Conversation inference possible, noticeable stutter"
msgstr "可以进行对话推理，有明显卡顿" msgstr "可以进行对话推理，有明显卡顿"
#: ../../getting_started/getting_started.md:18 e39a4b763ed74cea88d54d163ea72ce0 #: ../../getting_started/getting_started.md:18 a0ac5591c0ac4ac6a385e562353daf22
msgid "2. Install" msgid "2. Install"
msgstr "2. 安装" msgstr "2. 安装"
#: ../../getting_started/getting_started.md:20 9beba274b78a46c6aafb30173372b334 #: ../../getting_started/getting_started.md:20 a64a9a5945074ece872509f8cb425da9
msgid "" msgid ""
"This project relies on a local MySQL database service, which you need to " "This project relies on a local MySQL database service, which you need to "
"install locally. We recommend using Docker for installation." "install locally. We recommend using Docker for installation."
msgstr "本项目依赖一个本地的 MySQL 数据库服务，你需要本地安装，推荐直接使用 Docker 安装。" msgstr "本项目依赖一个本地的 MySQL 数据库服务，你需要本地安装，推荐直接使用 Docker 安装。"
#: ../../getting_started/getting_started.md:25 3bce689bb49043eca5b9aa3c5525eaac #: ../../getting_started/getting_started.md:25 11e799a372ab4d0f8269cd7be98bebc6
msgid "" msgid ""
"We use [Chroma embedding database](https://github.com/chroma-core/chroma)" "We use [Chroma embedding database](https://github.com/chroma-core/chroma)"
" as the default for our vector database, so there is no need for special " " as the default for our vector database, so there is no need for special "
@ -117,11 +117,11 @@ msgstr ""
"向量数据库我们默认使用的是Chroma内存数据库，所以无需特殊安装，如果有需要连接其他的同学，可以按照我们的教程进行安装配置。整个DB-" "向量数据库我们默认使用的是Chroma内存数据库，所以无需特殊安装，如果有需要连接其他的同学，可以按照我们的教程进行安装配置。整个DB-"
"GPT的安装过程，我们使用的是miniconda3的虚拟环境。创建虚拟环境，并安装python依赖包" "GPT的安装过程，我们使用的是miniconda3的虚拟环境。创建虚拟环境，并安装python依赖包"
#: ../../getting_started/getting_started.md:34 61ad49740d0b49afa254cb2d10a0d2ae #: ../../getting_started/getting_started.md:34 dcab69c83d4c48b9bb19c4336ee74a66
msgid "Before use DB-GPT Knowledge Management" msgid "Before use DB-GPT Knowledge Management"
msgstr "使用知识库管理功能之前" msgstr "使用知识库管理功能之前"
#: ../../getting_started/getting_started.md:40 656041e456f248a0a472be06357d7f89 #: ../../getting_started/getting_started.md:40 735aeb6ae8aa4344b7ff679548279acc
msgid "" msgid ""
"Once the environment is installed, we have to create a new folder " "Once the environment is installed, we have to create a new folder "
"\"models\" in the DB-GPT project, and then we can put all the models " "\"models\" in the DB-GPT project, and then we can put all the models "
@ -130,29 +130,33 @@ msgstr ""
"环境安装完成后，我们必须在DB-" "环境安装完成后，我们必须在DB-"
"GPT项目中创建一个新文件夹\"models\"，然后我们可以把从huggingface下载的所有模型放到这个目录下。" "GPT项目中创建一个新文件夹\"models\"，然后我们可以把从huggingface下载的所有模型放到这个目录下。"
#: ../../getting_started/getting_started.md:42 4dfb7d63fdf544f2bf9dd8663efa8d31 #: ../../getting_started/getting_started.md:43 7cbefe131b24488b9be39b3e8ed4f563
#, fuzzy #, fuzzy
msgid "Notice make sure you have install git-lfs" msgid "Notice make sure you have install git-lfs"
msgstr "确保你已经安装了git-lfs" msgstr "确保你已经安装了git-lfs"
#: ../../getting_started/getting_started.md:50 a52c137b8ef54b7ead41a2d8ff81d457 #: ../../getting_started/getting_started.md:53 54ec90ebb969475988451cd66e6ff412
msgid "" msgid ""
"The model files are large and will take a long time to download. During " "The model files are large and will take a long time to download. During "
"the download, let's configure the .env file, which needs to be copied and" "the download, let's configure the .env file, which needs to be copied and"
" created from the .env.template" " created from the .env.template"
msgstr "模型文件很大，需要很长时间才能下载。在下载过程中，让我们配置.env文件，它需要从。env.template中复制和创建。" msgstr "模型文件很大，需要很长时间才能下载。在下载过程中，让我们配置.env文件，它需要从。env.template中复制和创建。"
#: ../../getting_started/getting_started.md:56 db87d872a47047dc8cd1de390d068ed4 #: ../../getting_started/getting_started.md:56 9bdadbee88af4683a4eb7b4f221fb4b8
msgid "cp .env.template .env"
msgstr "cp .env.template .env"
#: ../../getting_started/getting_started.md:59 6357c4a0154b4f08a079419ac408442d
msgid "" msgid ""
"You can configure basic parameters in the .env file, for example setting " "You can configure basic parameters in the .env file, for example setting "
"LLM_MODEL to the model to be used" "LLM_MODEL to the model to be used"
msgstr "您可以在.env文件中配置基本参数，例如将LLM_MODEL设置为要使用的模型。" msgstr "您可以在.env文件中配置基本参数，例如将LLM_MODEL设置为要使用的模型。"
#: ../../getting_started/getting_started.md:58 c8865a327b4b44daa55813479c743e3c #: ../../getting_started/getting_started.md:61 2f349f3ed3184b849ade2a15d5bf0c6c
msgid "3. Run" msgid "3. Run"
msgstr "3. 运行" msgstr "3. 运行"
#: ../../getting_started/getting_started.md:59 e81dabe730134753a4daa05a7bdd44af #: ../../getting_started/getting_started.md:62 fe408e4405bd48288e2e746386615925
msgid "" msgid ""
"You can refer to this document to obtain the Vicuna weights: " "You can refer to this document to obtain the Vicuna weights: "
"[Vicuna](https://github.com/lm-sys/FastChat/blob/main/README.md#model-" "[Vicuna](https://github.com/lm-sys/FastChat/blob/main/README.md#model-"
@ -161,7 +165,7 @@ msgstr ""
"关于基础模型, 可以根据[Vicuna](https://github.com/lm-" "关于基础模型, 可以根据[Vicuna](https://github.com/lm-"
"sys/FastChat/blob/main/README.md#model-weights) 合成教程进行合成。" "sys/FastChat/blob/main/README.md#model-weights) 合成教程进行合成。"
#: ../../getting_started/getting_started.md:61 714cbc9485ea47d0a06aa1a31b9af3e3 #: ../../getting_started/getting_started.md:64 c0acfe28007f459ca21174f968763fa3
msgid "" msgid ""
"If you have difficulty with this step, you can also directly use the " "If you have difficulty with this step, you can also directly use the "
"model from [this link](https://huggingface.co/Tribbiani/vicuna-7b) as a " "model from [this link](https://huggingface.co/Tribbiani/vicuna-7b) as a "
@ -170,11 +174,11 @@ msgstr ""
"如果此步有困难的同学，也可以直接使用[此链接](https://huggingface.co/Tribbiani/vicuna-" "如果此步有困难的同学，也可以直接使用[此链接](https://huggingface.co/Tribbiani/vicuna-"
"7b)上的模型进行替代。" "7b)上的模型进行替代。"
#: ../../getting_started/getting_started.md:63 2b8f6985fe1a414e95d334d3ee9d0878 #: ../../getting_started/getting_started.md:66 cc0f4c4e43f24b679f857a8d937528ee
msgid "prepare server sql script" msgid "prepare server sql script"
msgstr "准备db-gpt server sql脚本" msgstr "准备db-gpt server sql脚本"
#: ../../getting_started/getting_started.md:69 7cb9beb0e15a46759dbcb4606dcb6867 #: ../../getting_started/getting_started.md:72 386948064fe646f2b9f51a262dd64bf2
msgid "" msgid ""
"set .env configuration set your vector store type, " "set .env configuration set your vector store type, "
"eg:VECTOR_STORE_TYPE=Chroma, now we support Chroma and Milvus(version > " "eg:VECTOR_STORE_TYPE=Chroma, now we support Chroma and Milvus(version > "
@ -183,17 +187,17 @@ msgstr ""
"在.env文件设置向量数据库环境变量，eg:VECTOR_STORE_TYPE=Chroma, 目前我们支持了 Chroma and " "在.env文件设置向量数据库环境变量，eg:VECTOR_STORE_TYPE=Chroma, 目前我们支持了 Chroma and "
"Milvus(version >2.1) " "Milvus(version >2.1) "
#: ../../getting_started/getting_started.md:72 cdb7ef30e8c9441293e8b3fd95d621ed #: ../../getting_started/getting_started.md:75 e6f6b06459944f2d8509703af365c664
#, fuzzy #, fuzzy
msgid "Run db-gpt server" msgid "Run db-gpt server"
msgstr "运行模型服务" msgstr "运行模型服务"
#: ../../getting_started/getting_started.md:77 e7bb3001d46b458aa0c522c4a7a8d45b #: ../../getting_started/getting_started.md:80 489b595dc08a459ca2fd83b1389d3bbd
#, fuzzy #, fuzzy
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"
#: ../../getting_started/getting_started.md:79 68c55e3ecfc642f2869a9917ec65904c #: ../../getting_started/getting_started.md:82 699afb01c9f243ab837cdc73252f624c
msgid "" msgid ""
"If you want to access an external LLM service, you need to 1.set the " "If you want to access an external LLM service, you need to 1.set the "
"variables LLM_MODEL=YOUR_MODEL_NAME " "variables LLM_MODEL=YOUR_MODEL_NAME "
@ -201,11 +205,11 @@ msgid ""
"file. 2.execute dbgpt_server.py in light mode" "file. 2.execute dbgpt_server.py in light mode"
msgstr "如果你想访问外部的大模型服务，1.需要在.env文件设置模型名和外部模型服务地址。2.使用light模式启动服务" msgstr "如果你想访问外部的大模型服务，1.需要在.env文件设置模型名和外部模型服务地址。2.使用light模式启动服务"
#: ../../getting_started/getting_started.md:86 474aea4023bb44dd970773b110bbf0ee #: ../../getting_started/getting_started.md:89 7df7f3870e1140d3a17dc322a46d6476
msgid "" msgid ""
"If you want to learn about dbgpt-webui, read https://github.com/csunny" "If you want to learn about dbgpt-webui, read https://github.com/csunny"
"/DB-GPT/tree/new-page-framework/datacenter" "/DB-GPT/tree/new-page-framework/datacenter"
msgstr "如果你想了解DB-GPT前端服务，访问https://github.com/csunny" msgstr ""
"/DB-GPT/tree/new-page-framework/datacenter" "如果你想了解DB-GPT前端服务，访问https://github.com/csunny/DB-GPT/tree/new-page-"
"framework/datacenter"

85
docs/locales/zh_CN/LC_MESSAGES/getting_started/installation.po Normal file
View File

@ -0,0 +1,85 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.0\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-07-13 15:39+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/installation.md:1 bc5bfc8ebfc847c5a22f2346357cf747
msgid "Installation"
msgstr "安装dbgpt包指南"
#: ../../getting_started/installation.md:2 1aaef0db5ee9426aa337021d782666af
msgid ""
"DB-GPT provides a third-party Python API package that you can integrate "
"into your own code."
msgstr "DB-GPT提供了python第三方包，你可以在你的代码中引入"
#: ../../getting_started/installation.md:4 de542f259e20441991a0e5a7d52769b8
msgid "Installation from Pip"
msgstr "使用pip安装"
#: ../../getting_started/installation.md:6 3357f019aa8249b292162de92757eec4
msgid "You can simply pip install:"
msgstr "你可以使用pip install"
#: ../../getting_started/installation.md:12 9c610d593608452f9d7d8d7e462251e3
msgid "Notice:make sure python>=3.10"
msgstr "注意:确保你的python版本>=3.10"
#: ../../getting_started/installation.md:15 b2ed238c29bb40cba990068e8d7ceae7
msgid "Environment Setup"
msgstr "环境设置"
#: ../../getting_started/installation.md:17 4804ad4d8edf44f49b1d35b271635fad
msgid "By default, if you use the EmbeddingEngine api"
msgstr "如果你想使用EmbeddingEngine api"
#: ../../getting_started/installation.md:19 2205f69ec60d4f73bb3a93a583928455
msgid "you will prepare embedding models from huggingface"
msgstr "你需要从huggingface下载embedding models"
#: ../../getting_started/installation.md:22 693c18a83f034dcc8c263674418bcde2
msgid "Notice make sure you have install git-lfs"
msgstr "确保你已经安装了git-lfs"
#: ../../getting_started/installation.md:30 dd8d0880b55e4c48bfc414f8cbdda268
msgid "version:"
msgstr "版本:"
#: ../../getting_started/installation.md:31 731e634b96164efbbc1ce9fa88361b12
msgid "db-gpt0.3.0"
msgstr "db-gpt0.3.0"
#: ../../getting_started/installation.md:32 38fb635be4554d94b527c6762253d46d
msgid ""
"[embedding_engine api](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge.html)"
msgstr "[embedding_engine api](https://db-gpt.readthedocs.io/en/latest/modules/knowledge.html)"
#: ../../getting_started/installation.md:33 a60b0ffe21a74ebca05529dc1dd1ba99
msgid ""
"[multi source embedding](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge/pdf/pdf_embedding.html)"
msgstr "[multi source embedding](https://db-gpt.readthedocs.io/en/latest/modules/knowledge/pdf/pdf_embedding.html)"
#: ../../getting_started/installation.md:34 3c752c9305414719bc3f561cf18a75af
msgid ""
"[vector connector](https://db-"
"gpt.readthedocs.io/en/latest/modules/vector.html)"
msgstr "[vector connector](https://db-gpt.readthedocs.io/en/latest/modules/vector.html)"

40
docs/locales/zh_CN/LC_MESSAGES/getting_started/tutorials.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: 2023-06-30 17:16+0800\n" "POT-Creation-Date: 2023-07-12 16:23+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"
@ -19,25 +19,25 @@ 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/tutorials.md:1 e494f27e68fd40efa2864a532087cfef #: ../../getting_started/tutorials.md:1 cb100b89a2a747cd90759e415c737070
msgid "Tutorials" msgid "Tutorials"
msgstr "教程" msgstr "教程"
#: ../../getting_started/tutorials.md:4 8eecfbf3240b44fcb425034600316cea #: ../../getting_started/tutorials.md:4 dbc2a2346b384cc3930086f97181b14b
msgid "This is a collection of DB-GPT tutorials on Medium." msgid "This is a collection of DB-GPT tutorials on Medium."
msgstr "这是知乎上DB-GPT教程的集合。．" msgstr "这是知乎上DB-GPT教程的集合。．"
#: ../../getting_started/tutorials.md:6 a40601867a3d4ce886a197f2f337ec0f #: ../../getting_started/tutorials.md:6 67e5b6dbac654d428e6a8be9d1ec6473
msgid "" msgid ""
"DB-GPT is divided into several functions, including chat with knowledge " "DB-GPT is divided into several functions, including chat with knowledge "
"base, execute SQL, chat with database, and execute plugins." "base, execute SQL, chat with database, and execute plugins."
msgstr "DB-GPT包含以下功能，和知识库聊天，执行SQL，和数据库聊天以及执行插件。" msgstr "DB-GPT包含以下功能，和知识库聊天，执行SQL，和数据库聊天以及执行插件。"
#: ../../getting_started/tutorials.md:8 493e6f56a75d45ef8bb15d3049a24994 #: ../../getting_started/tutorials.md:8 744aaec68aa3413c9b17b09714476d32
msgid "Introduction" msgid "Introduction"
msgstr "介绍" msgstr "介绍"
#: ../../getting_started/tutorials.md:9 4526a793cdb94b8f99f41c48cd5ee453 #: ../../getting_started/tutorials.md:9 305bcf5e847a4322a2834b84fa3c694a
#, fuzzy #, fuzzy
msgid "[What is DB-GPT](https://www.youtube.com/watch?v=QszhVJerc0I)" msgid "[What is DB-GPT](https://www.youtube.com/watch?v=QszhVJerc0I)"
msgstr "" msgstr ""
@ -45,12 +45,12 @@ msgstr ""
"GPT](https://www.bilibili.com/video/BV1SM4y1a7Nj/?buvid=551b023900b290f9497610b2155a2668&is_story_h5=false&mid=%2BVyE%2Fwau5woPcUKieCWS0A%3D%3D&p=1&plat_id=116&share_from=ugc&share_medium=iphone&share_plat=ios&share_session_id=5D08B533-82A4-4D40-9615-7826065B4574&share_source=GENERIC&share_tag=s_i&timestamp=1686307943&unique_k=bhO3lgQ&up_id=31375446)" "GPT](https://www.bilibili.com/video/BV1SM4y1a7Nj/?buvid=551b023900b290f9497610b2155a2668&is_story_h5=false&mid=%2BVyE%2Fwau5woPcUKieCWS0A%3D%3D&p=1&plat_id=116&share_from=ugc&share_medium=iphone&share_plat=ios&share_session_id=5D08B533-82A4-4D40-9615-7826065B4574&share_source=GENERIC&share_tag=s_i&timestamp=1686307943&unique_k=bhO3lgQ&up_id=31375446)"
" by csunny (https://github.com/csunny/DB-GPT)" " by csunny (https://github.com/csunny/DB-GPT)"
#: ../../getting_started/tutorials.md:11 95313384e5da4f5db96ac990596b2e73 #: ../../getting_started/tutorials.md:11 22fdc6937b2248ae8f5a7ef385aa55d9
#, fuzzy #, fuzzy
msgid "Knowledge" msgid "Knowledge"
msgstr "知识库" msgstr "知识库"
#: ../../getting_started/tutorials.md:13 e7a141f4df8d4974b0797dd7723c4658 #: ../../getting_started/tutorials.md:13 9bbf0f5aece64389b93b16235abda58e
#, fuzzy #, fuzzy
msgid "" msgid ""
"[How to Create your own knowledge repository](https://db-" "[How to Create your own knowledge repository](https://db-"
@ -59,55 +59,55 @@ msgstr ""
"[怎么创建自己的知识库](https://db-" "[怎么创建自己的知识库](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge.html)" "gpt.readthedocs.io/en/latest/modules/knowledge.html)"
#: ../../getting_started/tutorials.md:15 f7db5b05a2db44e6a98b7d0df0a6f4ee #: ../../getting_started/tutorials.md:15 ae201d75a3aa485e99b258103245db1c
#, fuzzy #, fuzzy
msgid "![Add new Knowledge demonstration](../../assets/new_knownledge.gif)" msgid "![Add new Knowledge demonstration](../../assets/new_knownledge.gif)"
msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)" msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)"
#: ../../getting_started/tutorials.md:15 1a1647a7ca23423294823529301dd75f #: ../../getting_started/tutorials.md:15 e7bfb3396f7b42f1a1be9f29df1773a2
#, fuzzy #, fuzzy
msgid "Add new Knowledge demonstration" msgid "Add new Knowledge demonstration"
msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)" msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)"
#: ../../getting_started/tutorials.md:17 de26224a814e4c6798d3a342b0f0fe3a #: ../../getting_started/tutorials.md:17 d37acc0486ec40309e7e944bb0458b0a
msgid "SQL Generation" msgid "SQL Generation"
msgstr "SQL生成" msgstr "SQL生成"
#: ../../getting_started/tutorials.md:18 f8fe82c554424239beb522f94d285c52 #: ../../getting_started/tutorials.md:18 86a328c9e15f46679a2611f7162f9fbe
#, fuzzy #, fuzzy
msgid "![sql generation demonstration](../../assets/demo_en.gif)" msgid "![sql generation demonstration](../../assets/demo_en.gif)"
msgstr "[sql生成演示](../../assets/demo_en.gif)" msgstr "[sql生成演示](../../assets/demo_en.gif)"
#: ../../getting_started/tutorials.md:18 41e932b692074fccb8059cadb0ed320e #: ../../getting_started/tutorials.md:18 03bc8d7320be44f0879a553a324ec26f
#, fuzzy #, fuzzy
msgid "sql generation demonstration" msgid "sql generation demonstration"
msgstr "[sql生成演示](../../assets/demo_en.gif)" msgstr "[sql生成演示](../../assets/demo_en.gif)"
#: ../../getting_started/tutorials.md:20 78bda916272f4cf99e9b26b4d9ba09ab #: ../../getting_started/tutorials.md:20 5f3b241f24634c09880d5de014f64f1b
msgid "SQL Execute" msgid "SQL Execute"
msgstr "SQL执行" msgstr "SQL执行"
#: ../../getting_started/tutorials.md:21 53cc83de34784c3c8d4d8204eacccbe9 #: ../../getting_started/tutorials.md:21 13a16debf2624f44bfb2e0453c11572d
#, fuzzy #, fuzzy
msgid "![sql execute demonstration](../../assets/auto_sql_en.gif)" msgid "![sql execute demonstration](../../assets/auto_sql_en.gif)"
msgstr "[sql execute 演示](../../assets/auto_sql_en.gif)" msgstr "[sql execute 演示](../../assets/auto_sql_en.gif)"
#: ../../getting_started/tutorials.md:21 535c06f487ed4d15a6cdd17a0154d798 #: ../../getting_started/tutorials.md:21 2d9673cfd48b49a5b1942fdc9de292bf
#, fuzzy #, fuzzy
msgid "sql execute demonstration" msgid "sql execute demonstration"
msgstr "SQL执行演示" msgstr "SQL执行演示"
#: ../../getting_started/tutorials.md:23 0482e6155dc44843adc3a3aa77528f03 #: ../../getting_started/tutorials.md:23 8cc0c647ad804969b470b133708de37f
#, fuzzy #, fuzzy
msgid "Plugins" msgid "Plugins"
msgstr "DB插件" msgstr "DB插件"
#: ../../getting_started/tutorials.md:24 632617dd88fe4688b789fbb941686c0f #: ../../getting_started/tutorials.md:24 cad5cc0cb94b42a1a6619bbd2a8b9f4c
#, fuzzy #, fuzzy
msgid "![db plugins demonstration](../../assets/chart_db_city_users.png)" msgid "![db plugins demonstration](../../assets/dashboard.png)"
msgstr "[db plugins 演示](../../assets/dbgpt_bytebase_plugin.gif)" msgstr "[db plugins 演示](../../assets/dbgpt_bytebase_plugin.gif)"
#: ../../getting_started/tutorials.md:24 020ff499469145f0a34ac468fff91948 #: ../../getting_started/tutorials.md:24 adeee7ea37b743c9b251976124520725
msgid "db plugins demonstration" msgid "db plugins demonstration"
msgstr "DB插件演示" msgstr "DB插件演示"

105
docs/locales/zh_CN/LC_MESSAGES/modules/knowledge.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: 2023-07-12 11:57+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -19,12 +19,12 @@ 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"
#: ../../modules/knowledge.rst:2 ../../modules/knowledge.rst:98 #: ../../modules/knowledge.rst:2 ../../modules/knowledge.rst:136
#: ca36c0ca545c4d70b51fe811a3e7caca #: 3cc8fa6e9fbd4d889603d99424e9529a
msgid "Knowledge" msgid "Knowledge"
msgstr "知识" msgstr "知识"
#: ../../modules/knowledge.rst:4 37818bc0ace74e008a52dbd838898c87 #: ../../modules/knowledge.rst:4 0465a393d9d541958c39c1d07c885d1f
#, fuzzy #, fuzzy
msgid "" msgid ""
"As the knowledge base is currently the most significant user demand " "As the knowledge base is currently the most significant user demand "
@ -36,47 +36,66 @@ msgstr ""
"由于知识库是当前用户需求最显著的场景，我们原生支持知识库的构建和处理。同时，我们还在本项目中提供了多种知识库管理策略，如:pdf,md , " "由于知识库是当前用户需求最显著的场景，我们原生支持知识库的构建和处理。同时，我们还在本项目中提供了多种知识库管理策略，如:pdf,md , "
"txt, word, ppt" "txt, word, ppt"
#: ../../modules/knowledge.rst:6 ../../modules/knowledge.rst:13 #: ../../modules/knowledge.rst:6 e670cbe14d8e4da88ba935e4120c31e0
#: c92bd129bf5043fd9d6224d245cc9a55
#, fuzzy
msgid "" msgid ""
"We currently support many document formats: raw text, txt, pdf, md, html," "We currently support many document formats: raw text, txt, pdf, md, html,"
" doc, ppt, and url." " doc, ppt, and url. In the future, we will continue to support more types"
msgstr "当前支持txt, pdf, md, html, doc, ppt, url文档格式" " of knowledge, including audio, video, various databases, and big data "
"sources. Of course, we look forward to your active participation in "
"contributing code."
msgstr ""
#: ../../modules/knowledge.rst:9 eec1169fea7a4a669433c347a4d929a2 #: ../../modules/knowledge.rst:9 e0bf601a1a0c458297306db6ff79f931
msgid "**Create your own knowledge repository**" msgid "**Create your own knowledge repository**"
msgstr "创建你自己的知识库" msgstr "创建你自己的知识库"
#: ../../modules/knowledge.rst:11 20565959da0842aa9f5bb3fe8fb37e10 #: ../../modules/knowledge.rst:11 bb26708135d44615be3c1824668010f6
msgid "1.prepare" msgid "1.prepare"
msgstr "准备" msgstr "准备"
#: ../../modules/knowledge.rst:15 515555d13e7548deb596d80ea1514bb2 #: ../../modules/knowledge.rst:13 c150a0378f3e4625908fa0d8a25860e9
#, fuzzy
msgid ""
"We currently support many document formats: TEXT(raw text), "
"DOCUMENT(.txt, .pdf, .md, .doc, .ppt, .html), and URL."
msgstr "当前支持txt, pdf, md, html, doc, ppt, url文档格式"
#: ../../modules/knowledge.rst:15 7f9f02a93d5d4325b3d2d976f4bb28a0
msgid "before execution:" msgid "before execution:"
msgstr "开始前" msgstr "开始前"
#: ../../modules/knowledge.rst:21 3333f92965ee41ea9cfa542de6c1e976 #: ../../modules/knowledge.rst:24 59699a8385e04982a992cf0d71f6dcd5
#, fuzzy
msgid "" msgid ""
"2.prepare embedding model, you can download from https://huggingface.co/." "2.prepare embedding model, you can download from https://huggingface.co/."
" Notice you have installed git-lfs. eg: git clone " " Notice you have installed git-lfs."
"https://huggingface.co/THUDM/chatglm2-6b" msgstr ""
msgstr "提前准备Embedding Model, 你可以在https://huggingface.co/进行下载，注意：你需要先安装git-lfs.eg: git clone " "提前准备Embedding Model, 你可以在https://huggingface.co/进行下载，注意：你需要先安装git-lfs.eg:"
"https://huggingface.co/THUDM/chatglm2-6b" " git clone https://huggingface.co/THUDM/chatglm2-6b"
#: ../../modules/knowledge.rst:29 7abcbe007d594f4aaa43ddef88ef4d89 #: ../../modules/knowledge.rst:27 2be1a17d0b54476b9dea080d244fd747
msgid ""
"eg: git clone https://huggingface.co/sentence-transformers/all-"
"MiniLM-L6-v2"
msgstr "eg: git clone https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2"
#: ../../modules/knowledge.rst:33 d328f6e243624c9488ebd27c9324621b
msgid "" msgid ""
"3.prepare vector_store instance and vector store config, now we support " "3.prepare vector_store instance and vector store config, now we support "
"Chroma, Milvus and Weaviate." "Chroma, Milvus and Weaviate."
msgstr "提前准备向量数据库环境，目前支持Chroma, Milvus and Weaviate向量数据库" msgstr "提前准备向量数据库环境，目前支持Chroma, Milvus and Weaviate向量数据库"
#: ../../modules/knowledge.rst:50 058fa57484a64756ab2650b46f4b33bf #: ../../modules/knowledge.rst:63 44f97154eff647d399fd30b6f9e3b867
msgid "" msgid ""
"3.init Url Type EmbeddingEngine api and embedding your document into " "3.init Url Type EmbeddingEngine api and embedding your document into "
"vector store in your code." "vector store in your code."
msgstr "初始化 Url类型 EmbeddingEngine api， 将url文档embedding向量化到向量数据库 " msgstr "初始化 Url类型 EmbeddingEngine api， 将url文档embedding向量化到向量数据库 "
#: ../../modules/knowledge.rst:62 5f255b96abd346479ab3c371393e47dc #: ../../modules/knowledge.rst:75 e2581b414f0148bca88253c7af9cd591
msgid "If you want to add your source_reader or text_splitter, do this:"
msgstr "如果你想手动添加你自定义的source_reader和text_splitter, 请参考:"
#: ../../modules/knowledge.rst:95 74c110414f924bbfa3d512e45ba2f30f
#, fuzzy #, fuzzy
msgid "" msgid ""
"4.init Document Type EmbeddingEngine api and embedding your document into" "4.init Document Type EmbeddingEngine api and embedding your document into"
@ -86,17 +105,17 @@ msgstr ""
"初始化 文档型类型 EmbeddingEngine api， 将文档embedding向量化到向量数据库(文档可以是.txt, .pdf, " "初始化 文档型类型 EmbeddingEngine api， 将文档embedding向量化到向量数据库(文档可以是.txt, .pdf, "
".md, .html, .doc, .ppt)" ".md, .html, .doc, .ppt)"
#: ../../modules/knowledge.rst:75 d8c85ba7714749269714b03857738f70 #: ../../modules/knowledge.rst:108 0afd40098d5f4dfd9e44fe1d8004da25
msgid "" msgid ""
"5.init TEXT Type EmbeddingEngine api and embedding your document into " "5.init TEXT Type EmbeddingEngine api and embedding your document into "
"vector store in your code." "vector store in your code."
msgstr "初始化TEXT类型 EmbeddingEngine api， 将文档embedding向量化到向量数据库" msgstr "初始化TEXT类型 EmbeddingEngine api， 将文档embedding向量化到向量数据库"
#: ../../modules/knowledge.rst:87 c59e4650d57e44ae8d967768dddf908a #: ../../modules/knowledge.rst:120 a66961bf3efd41fa8ea938129446f5a5
msgid "4.similar search based on your knowledge base. ::" msgid "4.similar search based on your knowledge base. ::"
msgstr "在知识库进行相似性搜索" msgstr "在知识库进行相似性搜索"
#: ../../modules/knowledge.rst:93 f500fcdc791c4286b411819ae9ab3dc6 #: ../../modules/knowledge.rst:126 b7066f408378450db26770f83fbd2716
msgid "" msgid ""
"Note that the default vector model used is text2vec-large-chinese (which " "Note that the default vector model used is text2vec-large-chinese (which "
"is a large model, so if your personal computer configuration is not " "is a large model, so if your personal computer configuration is not "
@ -106,12 +125,48 @@ msgstr ""
"注意，这里默认向量模型是text2vec-large-chinese(模型比较大，如果个人电脑配置不够建议采用text2vec-base-" "注意，这里默认向量模型是text2vec-large-chinese(模型比较大，如果个人电脑配置不够建议采用text2vec-base-"
"chinese),因此确保需要将模型download下来放到models目录中。" "chinese),因此确保需要将模型download下来放到models目录中。"
#: ../../modules/knowledge.rst:95 62a5e10a19844ba9955113f5c78cb460 #: ../../modules/knowledge.rst:128 58481d55cab74936b6e84b24c39b1674
#, fuzzy
msgid "" msgid ""
"`pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf " "`pdf_embedding <./knowledge/pdf/pdf_embedding.html>`_: supported pdf "
"embedding." "embedding."
msgstr "pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf embedding." msgstr "pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf embedding."
#: ../../modules/knowledge.rst:129 fbb013c4f1bc46af910c91292f6690cf
#, fuzzy
msgid ""
"`markdown_embedding <./knowledge/markdown/markdown_embedding.html>`_: "
"supported markdown embedding."
msgstr "pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf embedding."
#: ../../modules/knowledge.rst:130 59d45732f4914d16b4e01aee0992edf7
#, fuzzy
msgid ""
"`word_embedding <./knowledge/word/word_embedding.html>`_: supported word "
"embedding."
msgstr "pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf embedding."
#: ../../modules/knowledge.rst:131 df0e6f311861423e885b38e020a7c0f0
#, fuzzy
msgid ""
"`url_embedding <./knowledge/url/url_embedding.html>`_: supported url "
"embedding."
msgstr "pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf embedding."
#: ../../modules/knowledge.rst:132 7c550c1f5bc34fe9986731fb465e12cd
#, fuzzy
msgid ""
"`ppt_embedding <./knowledge/ppt/ppt_embedding.html>`_: supported ppt "
"embedding."
msgstr "pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf embedding."
#: ../../modules/knowledge.rst:133 8648684cb191476faeeb548389f79050
#, fuzzy
msgid ""
"`string_embedding <./knowledge/string/string_embedding.html>`_: supported"
" raw text embedding."
msgstr "pdf_embedding <./knowledge/pdf_embedding.html>`_: supported pdf embedding."
#~ msgid "before execution: python -m spacy download zh_core_web_sm" #~ msgid "before execution: python -m spacy download zh_core_web_sm"
#~ msgstr "在执行之前请先执行python -m spacy download zh_core_web_sm" #~ msgstr "在执行之前请先执行python -m spacy download zh_core_web_sm"

19
docs/locales/zh_CN/LC_MESSAGES/modules/knowledge/markdown/markdown_embedding.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: 2023-06-14 14:51+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -20,12 +20,13 @@ msgstr ""
"Generated-By: Babel 2.12.1\n" "Generated-By: Babel 2.12.1\n"
#: ../../modules/knowledge/markdown/markdown_embedding.md:1 #: ../../modules/knowledge/markdown/markdown_embedding.md:1
#: b5fd3aea05a64590955b958b753bf22a #: 6d4eb4d8566b4dbaa301715148342aca
msgid "MarkdownEmbedding" #, fuzzy
msgid "Markdown"
msgstr "MarkdownEmbedding" msgstr "MarkdownEmbedding"
#: ../../modules/knowledge/markdown/markdown_embedding.md:3 #: ../../modules/knowledge/markdown/markdown_embedding.md:3
#: 0f98ce5b34d44c6f9c828e4b497984de #: 050625646fa14cb1822d0d430fdf06ec
msgid "" msgid ""
"markdown embedding can import md text into a vector knowledge base. The " "markdown embedding can import md text into a vector knowledge base. The "
"entire embedding process includes the read (loading data), data_process " "entire embedding process includes the read (loading data), data_process "
@ -36,20 +37,20 @@ msgstr ""
"数据预处理data_process()和数据进向量数据库index_to_store()" "数据预处理data_process()和数据进向量数据库index_to_store()"
#: ../../modules/knowledge/markdown/markdown_embedding.md:5 #: ../../modules/knowledge/markdown/markdown_embedding.md:5
#: 7f5ebfa8c7c146d7a340baca85634e16 #: af1313489c164e968def2f5f1716a522
msgid "inheriting the SourceEmbedding" msgid "inheriting the SourceEmbedding"
msgstr "继承SourceEmbedding" msgstr "继承SourceEmbedding"
#: ../../modules/knowledge/markdown/markdown_embedding.md:17 #: ../../modules/knowledge/markdown/markdown_embedding.md:18
#: 732e946bc9d149a5af802b239304b943 #: aebe894f955b44f3ac677ce50d47c846
#, fuzzy #, fuzzy
msgid "" msgid ""
"implement read() and data_process() read() method allows you to read data" "implement read() and data_process() read() method allows you to read data"
" and split data into chunk" " and split data into chunk"
msgstr "实现read方法可以加载数据" msgstr "实现read方法可以加载数据"
#: ../../modules/knowledge/markdown/markdown_embedding.md:33 #: ../../modules/knowledge/markdown/markdown_embedding.md:41
#: f7e53658aee7403688b333b24ff08ce2 #: d53a087726be4a0dbb8dadbeb772442b
msgid "data_process() method allows you to pre processing your ways" msgid "data_process() method allows you to pre processing your ways"
msgstr "实现data_process方法可以进行数据预处理" msgstr "实现data_process方法可以进行数据预处理"

21
docs/locales/zh_CN/LC_MESSAGES/modules/knowledge/pdf/pdf_embedding.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: 2023-06-14 14:51+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -20,12 +20,12 @@ msgstr ""
"Generated-By: Babel 2.12.1\n" "Generated-By: Babel 2.12.1\n"
#: ../../modules/knowledge/pdf/pdf_embedding.md:1 #: ../../modules/knowledge/pdf/pdf_embedding.md:1
#: fe600a1f3f9f492da81652ebd3d6d52d #: edf96281acc04612a3384b451dc71391
msgid "PDFEmbedding" msgid "PDF"
msgstr "" msgstr ""
#: ../../modules/knowledge/pdf/pdf_embedding.md:3 #: ../../modules/knowledge/pdf/pdf_embedding.md:3
#: a26a7d6ff041476b975bab5c0bf9f506 #: fdc7396cc2eb4186bb28ea8c491738bc
#, fuzzy #, fuzzy
msgid "" msgid ""
"pdfembedding can import PDF text into a vector knowledge base. The entire" "pdfembedding can import PDF text into a vector knowledge base. The entire"
@ -37,20 +37,23 @@ msgstr ""
"数据预处理data_process()和数据进向量数据库index_to_store()" "数据预处理data_process()和数据进向量数据库index_to_store()"
#: ../../modules/knowledge/pdf/pdf_embedding.md:5 #: ../../modules/knowledge/pdf/pdf_embedding.md:5
#: 1895f2a6272c43f0b328caba092102a9 #: d4950371bace43d8957bce9757d77b6e
msgid "inheriting the SourceEmbedding" msgid "inheriting the SourceEmbedding"
msgstr "继承SourceEmbedding" msgstr "继承SourceEmbedding"
#: ../../modules/knowledge/pdf/pdf_embedding.md:17 #: ../../modules/knowledge/pdf/pdf_embedding.md:18
#: 2a4a349398354f9cb3e8d9630a4b8696 #: 990c46bba6f3438da542417e4addb96f
#, fuzzy #, fuzzy
msgid "" msgid ""
"implement read() and data_process() read() method allows you to read data" "implement read() and data_process() read() method allows you to read data"
" and split data into chunk" " and split data into chunk"
msgstr "实现read方法可以加载数据" msgstr "实现read方法可以加载数据"
#: ../../modules/knowledge/pdf/pdf_embedding.md:34 #: ../../modules/knowledge/pdf/pdf_embedding.md:39
#: 9b5c6d3e9e96443a908a09a8a762ea7a #: 29cf5a37da2f4ad7ab66750970f62d3f
msgid "data_process() method allows you to pre processing your ways" msgid "data_process() method allows you to pre processing your ways"
msgstr "实现data_process方法可以进行数据预处理" msgstr "实现data_process方法可以进行数据预处理"
#~ msgid "PDFEmbedding"
#~ msgstr ""

21
docs/locales/zh_CN/LC_MESSAGES/modules/knowledge/ppt/ppt_embedding.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: 2023-06-14 14:51+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -20,12 +20,12 @@ msgstr ""
"Generated-By: Babel 2.12.1\n" "Generated-By: Babel 2.12.1\n"
#: ../../modules/knowledge/ppt/ppt_embedding.md:1 #: ../../modules/knowledge/ppt/ppt_embedding.md:1
#: 2cdb249b2b284064a0c9117d051e35d4 #: 86b98a120d0d4796a034c47a23ec8a03
msgid "PPTEmbedding" msgid "PPT"
msgstr "" msgstr ""
#: ../../modules/knowledge/ppt/ppt_embedding.md:3 #: ../../modules/knowledge/ppt/ppt_embedding.md:3
#: 71676e9b35434a849a206788da8f1394 #: af78e8c3a6c24bf79e03da41c6d13fba
msgid "" msgid ""
"ppt embedding can import ppt text into a vector knowledge base. The " "ppt embedding can import ppt text into a vector knowledge base. The "
"entire embedding process includes the read (loading data), data_process " "entire embedding process includes the read (loading data), data_process "
@ -36,20 +36,23 @@ msgstr ""
"数据预处理data_process()和数据进向量数据库index_to_store()" "数据预处理data_process()和数据进向量数据库index_to_store()"
#: ../../modules/knowledge/ppt/ppt_embedding.md:5 #: ../../modules/knowledge/ppt/ppt_embedding.md:5
#: 016aeae4786e4d5bad815670bd109481 #: 0ddb5ec40a4e4864b63e7f578c2f3c34
msgid "inheriting the SourceEmbedding" msgid "inheriting the SourceEmbedding"
msgstr "继承SourceEmbedding" msgstr "继承SourceEmbedding"
#: ../../modules/knowledge/ppt/ppt_embedding.md:17 #: ../../modules/knowledge/ppt/ppt_embedding.md:23
#: 2fb5b9dc912342df8c275cfd0e993fe0 #: b74741f4a1814fe19842985a3f960972
#, fuzzy #, fuzzy
msgid "" msgid ""
"implement read() and data_process() read() method allows you to read data" "implement read() and data_process() read() method allows you to read data"
" and split data into chunk" " and split data into chunk"
msgstr "实现read方法可以加载数据" msgstr "实现read方法可以加载数据"
#: ../../modules/knowledge/ppt/ppt_embedding.md:31 #: ../../modules/knowledge/ppt/ppt_embedding.md:44
#: 9a00f72c7ec84bde9971579c720d2628 #: bc1e705c60cd4dde921150cb814ac8ae
msgid "data_process() method allows you to pre processing your ways" msgid "data_process() method allows you to pre processing your ways"
msgstr "实现data_process方法可以进行数据预处理" msgstr "实现data_process方法可以进行数据预处理"
#~ msgid "PPTEmbedding"
#~ msgstr ""

21
docs/locales/zh_CN/LC_MESSAGES/modules/knowledge/url/url_embedding.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: 2023-06-14 14:51+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -20,12 +20,12 @@ msgstr ""
"Generated-By: Babel 2.12.1\n" "Generated-By: Babel 2.12.1\n"
#: ../../modules/knowledge/url/url_embedding.md:1 #: ../../modules/knowledge/url/url_embedding.md:1
#: e6d335e613ec4c3a80b89de67ba93098 #: c1db535b997f4a90a75806f389200a4e
msgid "URL Embedding" msgid "URL"
msgstr "" msgstr ""
#: ../../modules/knowledge/url/url_embedding.md:3 #: ../../modules/knowledge/url/url_embedding.md:3
#: 25e7643335264bdaaa9386ded243d51d #: a4e3929be4964c35b7d169eaae8f29fe
msgid "" msgid ""
"url embedding can import PDF text into a vector knowledge base. The " "url embedding can import PDF text into a vector knowledge base. The "
"entire embedding process includes the read (loading data), data_process " "entire embedding process includes the read (loading data), data_process "
@ -36,20 +36,23 @@ msgstr ""
"数据预处理data_process()和数据进向量数据库index_to_store()" "数据预处理data_process()和数据进向量数据库index_to_store()"
#: ../../modules/knowledge/url/url_embedding.md:5 #: ../../modules/knowledge/url/url_embedding.md:5
#: 4b8ca6d93ed0412ab1e640bd42b400ac #: 0c0be35a31e84e76a60e9e4ffb61a414
msgid "inheriting the SourceEmbedding" msgid "inheriting the SourceEmbedding"
msgstr "继承SourceEmbedding" msgstr "继承SourceEmbedding"
#: ../../modules/knowledge/url/url_embedding.md:17 #: ../../modules/knowledge/url/url_embedding.md:23
#: 5d69d27adc70406db97c398a339f6453 #: f9916af3adee4da2988e5ed1912f2bdd
#, fuzzy #, fuzzy
msgid "" msgid ""
"implement read() and data_process() read() method allows you to read data" "implement read() and data_process() read() method allows you to read data"
" and split data into chunk" " and split data into chunk"
msgstr "实现read方法可以加载数据" msgstr "实现read方法可以加载数据"
#: ../../modules/knowledge/url/url_embedding.md:34 #: ../../modules/knowledge/url/url_embedding.md:44
#: 7d055e181d9b4d47965ab249b18bd704 #: 56c0720ae3d840069daad2ba7edc8122
msgid "data_process() method allows you to pre processing your ways" msgid "data_process() method allows you to pre processing your ways"
msgstr "实现data_process方法可以进行数据预处理" msgstr "实现data_process方法可以进行数据预处理"
#~ msgid "URL Embedding"
#~ msgstr ""

21
docs/locales/zh_CN/LC_MESSAGES/modules/knowledge/word/word_embedding.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: 2023-06-14 14:51+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -20,12 +20,12 @@ msgstr ""
"Generated-By: Babel 2.12.1\n" "Generated-By: Babel 2.12.1\n"
#: ../../modules/knowledge/word/word_embedding.md:1 #: ../../modules/knowledge/word/word_embedding.md:1
#: 1b3272def692480bb101060a33d076c6 #: fa236aa8d2e5471d8436e0ec60f906e8
msgid "WordEmbedding" msgid "Word"
msgstr "" msgstr ""
#: ../../modules/knowledge/word/word_embedding.md:3 #: ../../modules/knowledge/word/word_embedding.md:3
#: a7ea0e94e5c74dab9aa7fb80ed42ed39 #: 02d0c183f7f646a7b74e22d0166c8718
msgid "" msgid ""
"word embedding can import word doc/docx text into a vector knowledge " "word embedding can import word doc/docx text into a vector knowledge "
"base. The entire embedding process includes the read (loading data), " "base. The entire embedding process includes the read (loading data), "
@ -36,20 +36,23 @@ msgstr ""
"数据预处理data_process()和数据进向量数据库index_to_store()" "数据预处理data_process()和数据进向量数据库index_to_store()"
#: ../../modules/knowledge/word/word_embedding.md:5 #: ../../modules/knowledge/word/word_embedding.md:5
#: 12ba9527ef0745538dffb6b1dcf96933 #: ffa094cb7739457d88666c5b624bf078
msgid "inheriting the SourceEmbedding" msgid "inheriting the SourceEmbedding"
msgstr "继承SourceEmbedding" msgstr "继承SourceEmbedding"
#: ../../modules/knowledge/word/word_embedding.md:17 #: ../../modules/knowledge/word/word_embedding.md:18
#: a4e5e7553f4a43b0b79ba0de83268ef0 #: 146f03d86fd147b7847b7b907d52b408
#, fuzzy #, fuzzy
msgid "" msgid ""
"implement read() and data_process() read() method allows you to read data" "implement read() and data_process() read() method allows you to read data"
" and split data into chunk" " and split data into chunk"
msgstr "实现read方法可以加载数据" msgstr "实现read方法可以加载数据"
#: ../../modules/knowledge/word/word_embedding.md:29 #: ../../modules/knowledge/word/word_embedding.md:39
#: 188a434dee7543f89cf5f1584f29ca62 #: b29a213855af4446a64aadc5a3b76739
msgid "data_process() method allows you to pre processing your ways" msgid "data_process() method allows you to pre processing your ways"
msgstr "实现data_process方法可以进行数据预处理" msgstr "实现data_process方法可以进行数据预处理"
#~ msgid "WordEmbedding"
#~ msgstr ""

69
docs/locales/zh_CN/LC_MESSAGES/use_cases/knownledge_based_qa.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: 2023-06-13 11:38+0800\n" "POT-Creation-Date: 2023-07-13 15:39+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"
@ -19,40 +19,43 @@ 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"
#: ../../use_cases/knownledge_based_qa.md:1 ddfe412b92e14324bdc11ffe58114e5f #~ msgid "Knownledge based qa"
msgid "Knownledge based qa" #~ msgstr "知识问答"
msgstr "知识问答"
#: ../../use_cases/knownledge_based_qa.md:3 48635316cc704a779089ff7b5cb9a836 #~ msgid ""
msgid "" #~ "Chat with your own knowledge is a"
"Chat with your own knowledge is a very interesting thing. In the usage " #~ " very interesting thing. In the usage"
"scenarios of this chapter, we will introduce how to build your own " #~ " scenarios of this chapter, we will"
"knowledge base through the knowledge base API. Firstly, building a " #~ " introduce how to build your own "
"knowledge store can currently be initialized by executing \"python " #~ "knowledge base through the knowledge "
"tool/knowledge_init.py\" to initialize the content of your own knowledge " #~ "base API. Firstly, building a knowledge"
"base, which was introduced in the previous knowledge base module. Of " #~ " store can currently be initialized "
"course, you can also call our provided knowledge embedding API to store " #~ "by executing \"python tool/knowledge_init.py\" "
"knowledge." #~ "to initialize the content of your "
msgstr "" #~ "own knowledge base, which was introduced"
"用自己的知识聊天是一件很有趣的事情。在本章的使用场景中，我们将介绍如何通过知识库API构建自己的知识库。首先，构建知识存储目前可以通过执行“python" #~ " in the previous knowledge base "
" " #~ "module. Of course, you can also "
"tool/knowledge_init.py”来初始化您自己的知识库的内容，这在前面的知识库模块中已经介绍过了。当然，你也可以调用我们提供的知识嵌入API来存储知识。" #~ "call our provided knowledge embedding "
#~ "API to store knowledge."
#~ msgstr ""
#~ "用自己的知识聊天是一件很有趣的事情。在本章的使用场景中，我们将介绍如何通过知识库API构建自己的知识库。首先，构建知识存储目前可以通过执行“python"
#~ " "
#~ "tool/knowledge_init.py”来初始化您自己的知识库的内容，这在前面的知识库模块中已经介绍过了。当然，你也可以调用我们提供的知识嵌入API来存储知识。"
#: ../../use_cases/knownledge_based_qa.md:6 0a5c68429c9343cf8b88f4f1dddb18eb #~ msgid ""
#, fuzzy #~ "We currently support many document "
msgid "" #~ "formats: txt, pdf, md, html, doc, "
"We currently support many document formats: txt, pdf, md, html, doc, ppt," #~ "ppt, and url."
" and url." #~ msgstr "“我们目前支持四种文件格式: txt, pdf, url, 和md。"
msgstr "“我们目前支持四种文件格式: txt, pdf, url, 和md。"
#: ../../use_cases/knownledge_based_qa.md:20 83f3544c06954e5cbc0cc7788f699eb1 #~ msgid ""
msgid "" #~ "Now we currently support vector "
"Now we currently support vector databases: Chroma (default) and Milvus. " #~ "databases: Chroma (default) and Milvus. "
"You can switch between them by modifying the \"VECTOR_STORE_TYPE\" field " #~ "You can switch between them by "
"in the .env file." #~ "modifying the \"VECTOR_STORE_TYPE\" field in"
msgstr "“我们目前支持向量数据库:Chroma(默认)和Milvus。你可以通过修改.env文件中的“VECTOR_STORE_TYPE”参数在它们之间切换。" #~ " the .env file."
#~ msgstr "“我们目前支持向量数据库:Chroma(默认)和Milvus。你可以通过修改.env文件中的“VECTOR_STORE_TYPE”参数在它们之间切换。"
#: ../../use_cases/knownledge_based_qa.md:31 ac12f26b81384fc4bf44ccce1c0d86b4 #~ msgid "Below is an example of using the knowledge base API to query knowledge:"
msgid "Below is an example of using the knowledge base API to query knowledge:" #~ msgstr "下面是一个使用知识库API进行查询的例子:"
msgstr "下面是一个使用知识库API进行查询的例子:"

17
pilot/common/sql_database.py
View File

@ -344,7 +344,14 @@ class Database:
return [ return [
d[0] d[0]
for d in results for d in results
if d[0] not in ["information_schema", "performance_schema", "sys", "mysql", "knowledge_management"] if d[0]
not in [
"information_schema",
"performance_schema",
"sys",
"mysql",
"knowledge_management",
]
] ]
def convert_sql_write_to_select(self, write_sql): def convert_sql_write_to_select(self, write_sql):
@ -421,7 +428,13 @@ class Database:
session = self._db_sessions() session = self._db_sessions()
cursor = session.execute(text(f"SHOW CREATE TABLE {table_name}")) cursor = session.execute(text(f"SHOW CREATE TABLE {table_name}"))
ans = cursor.fetchall() ans = cursor.fetchall()
return ans[0][1] res = ans[0][1]
res = re.sub(r"\s*ENGINE\s*=\s*InnoDB\s*", " ", res, flags=re.IGNORECASE)
res = re.sub(
r"\s*DEFAULT\s*CHARSET\s*=\s*\w+\s*", " ", res, flags=re.IGNORECASE
)
res = re.sub(r"\s*COLLATE\s*=\s*\w+\s*", " ", res, flags=re.IGNORECASE)
return res
def get_fields(self, table_name): def get_fields(self, table_name):
"""Get column fields about specified table.""" """Get column fields about specified table."""

10
pilot/embedding_engine/csv_embedding.py
View File

@ -2,7 +2,11 @@ from typing import Dict, List, Optional
from langchain.document_loaders import CSVLoader from langchain.document_loaders import CSVLoader
from langchain.schema import Document from langchain.schema import Document
from langchain.text_splitter import TextSplitter, SpacyTextSplitter, RecursiveCharacterTextSplitter from langchain.text_splitter import (
TextSplitter,
SpacyTextSplitter,
RecursiveCharacterTextSplitter,
)
from pilot.embedding_engine import SourceEmbedding, register from pilot.embedding_engine import SourceEmbedding, register
@ -18,7 +22,9 @@ class CSVEmbedding(SourceEmbedding):
text_splitter: Optional[TextSplitter] = None, text_splitter: Optional[TextSplitter] = None,
): ):
"""Initialize with csv path.""" """Initialize with csv path."""
super().__init__(file_path, vector_store_config, source_reader=None, text_splitter=None) super().__init__(
file_path, vector_store_config, source_reader=None, text_splitter=None
)
self.file_path = file_path self.file_path = file_path
self.vector_store_config = vector_store_config self.vector_store_config = vector_store_config
self.source_reader = source_reader or None self.source_reader = source_reader or None

4
pilot/embedding_engine/markdown_embedding.py
View File

@ -28,7 +28,9 @@ class MarkdownEmbedding(SourceEmbedding):
text_splitter: Optional[TextSplitter] = None, text_splitter: Optional[TextSplitter] = None,
): ):
"""Initialize raw text word path.""" """Initialize raw text word path."""
super().__init__(file_path, vector_store_config, source_reader=None, text_splitter=None) super().__init__(
file_path, vector_store_config, source_reader=None, text_splitter=None
)
self.file_path = file_path self.file_path = file_path
self.vector_store_config = vector_store_config self.vector_store_config = vector_store_config
self.source_reader = source_reader or None self.source_reader = source_reader or None

4
pilot/embedding_engine/pdf_embedding.py
View File

@ -24,7 +24,9 @@ class PDFEmbedding(SourceEmbedding):
text_splitter: Optional[TextSplitter] = None, text_splitter: Optional[TextSplitter] = None,
): ):
"""Initialize pdf word path.""" """Initialize pdf word path."""
super().__init__(file_path, vector_store_config, source_reader=None, text_splitter=None) super().__init__(
file_path, vector_store_config, source_reader=None, text_splitter=None
)
self.file_path = file_path self.file_path = file_path
self.vector_store_config = vector_store_config self.vector_store_config = vector_store_config
self.source_reader = source_reader or None self.source_reader = source_reader or None

4
pilot/embedding_engine/ppt_embedding.py
View File

@ -24,7 +24,9 @@ class PPTEmbedding(SourceEmbedding):
text_splitter: Optional[TextSplitter] = None, text_splitter: Optional[TextSplitter] = None,
): ):
"""Initialize ppt word path.""" """Initialize ppt word path."""
super().__init__(file_path, vector_store_config, source_reader=None, text_splitter=None) super().__init__(
file_path, vector_store_config, source_reader=None, text_splitter=None
)
self.file_path = file_path self.file_path = file_path
self.vector_store_config = vector_store_config self.vector_store_config = vector_store_config
self.source_reader = source_reader or None self.source_reader = source_reader or None

18
pilot/embedding_engine/string_embedding.py
View File

@ -1,7 +1,11 @@
from typing import List, Optional from typing import List, Optional
from langchain.schema import Document from langchain.schema import Document
from langchain.text_splitter import TextSplitter, SpacyTextSplitter, RecursiveCharacterTextSplitter from langchain.text_splitter import (
TextSplitter,
SpacyTextSplitter,
RecursiveCharacterTextSplitter,
)
from pilot.embedding_engine import SourceEmbedding, register from pilot.embedding_engine import SourceEmbedding, register
@ -17,7 +21,12 @@ class StringEmbedding(SourceEmbedding):
text_splitter: Optional[TextSplitter] = None, text_splitter: Optional[TextSplitter] = None,
): ):
"""Initialize raw text word path.""" """Initialize raw text word path."""
super().__init__(file_path=file_path, vector_store_config=vector_store_config, source_reader=None, text_splitter=None) super().__init__(
file_path=file_path,
vector_store_config=vector_store_config,
source_reader=None,
text_splitter=None,
)
self.file_path = file_path self.file_path = file_path
self.vector_store_config = vector_store_config self.vector_store_config = vector_store_config
self.source_reader = source_reader or None self.source_reader = source_reader or None
@ -32,16 +41,15 @@ class StringEmbedding(SourceEmbedding):
try: try:
self.text_splitter = SpacyTextSplitter( self.text_splitter = SpacyTextSplitter(
pipeline="zh_core_web_sm", pipeline="zh_core_web_sm",
chunk_size=100, chunk_size=500,
chunk_overlap=100, chunk_overlap=100,
) )
except Exception: except Exception:
self.text_splitter = RecursiveCharacterTextSplitter( self.text_splitter = RecursiveCharacterTextSplitter(
chunk_size=100, chunk_overlap=50 chunk_size=100, chunk_overlap=50
) )
return self.text_splitter.split_documents(docs) return self.text_splitter.split_documents(docs)
return docs
@register @register
def data_process(self, documents: List[Document]): def data_process(self, documents: List[Document]):

5
pilot/embedding_engine/url_embedding.py
View File

@ -23,13 +23,14 @@ class URLEmbedding(SourceEmbedding):
text_splitter: Optional[TextSplitter] = None, text_splitter: Optional[TextSplitter] = None,
): ):
"""Initialize url word path.""" """Initialize url word path."""
super().__init__(file_path, vector_store_config, source_reader=None, text_splitter=None) super().__init__(
file_path, vector_store_config, source_reader=None, text_splitter=None
)
self.file_path = file_path self.file_path = file_path
self.vector_store_config = vector_store_config self.vector_store_config = vector_store_config
self.source_reader = source_reader or None self.source_reader = source_reader or None
self.text_splitter = text_splitter or None self.text_splitter = text_splitter or None
@register @register
def read(self): def read(self):
"""Load from url path.""" """Load from url path."""

4
pilot/embedding_engine/word_embedding.py
View File

@ -24,7 +24,9 @@ class WordEmbedding(SourceEmbedding):
text_splitter: Optional[TextSplitter] = None, text_splitter: Optional[TextSplitter] = None,
): ):
"""Initialize with word path.""" """Initialize with word path."""
super().__init__(file_path, vector_store_config, source_reader=None, text_splitter=None) super().__init__(
file_path, vector_store_config, source_reader=None, text_splitter=None
)
self.file_path = file_path self.file_path = file_path
self.vector_store_config = vector_store_config self.vector_store_config = vector_store_config
self.source_reader = source_reader or None self.source_reader = source_reader or None

1
pilot/summary/db_summary_client.py
View File

@ -77,7 +77,6 @@ class DBSummaryClient:
def get_db_summary(self, dbname, query, topk): def get_db_summary(self, dbname, query, topk):
vector_store_config = { vector_store_config = {
"vector_store_name": dbname + "_profile", "vector_store_name": dbname + "_profile",
"chroma_persist_path": KNOWLEDGE_UPLOAD_ROOT_PATH,
"vector_store_type": CFG.VECTOR_STORE_TYPE, "vector_store_type": CFG.VECTOR_STORE_TYPE,
"chroma_persist_path": KNOWLEDGE_UPLOAD_ROOT_PATH, "chroma_persist_path": KNOWLEDGE_UPLOAD_ROOT_PATH,
} }