feat: Command-line tool with knowledge repository initialization

This commit is contained in:
FangYin Cheng
2023-09-01 18:21:22 +08:00
parent d42afb50a7
commit e5bbd0bd86
9 changed files with 153 additions and 257 deletions

View File

@@ -8,7 +8,7 @@ msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 0.3.0\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-07-31 17:04+0800\n"
"POT-Creation-Date: 2023-09-01 18:16+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@@ -19,11 +19,11 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../modules/knownledge.md:1 b18cf12f806941f3b9d1c13b52d0dfe5
#: ../../modules/knownledge.md:1 ba585bf3ba464c32a156d308f39e65dc
msgid "Knownledge"
msgstr "知识"
#: ../../modules/knownledge.md:3 3fe78b30d3994e4484df41a677614eb2
#: ../../modules/knownledge.md:3 bc5d67c51b004ff8b2d1bbca17fd4aa7
msgid ""
"As the knowledge base is currently the most significant user demand "
"scenario, we natively support the construction and processing of "
@@ -31,15 +31,15 @@ msgid ""
"base management strategies in this project, such as:"
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:"
#: ../../modules/knownledge.md:4 17b2485a12744b5587655201be50e023
#: ../../modules/knownledge.md:4 519f2686500340d191ad5a91eabc7676
msgid "Default built-in knowledge base"
msgstr "默认内置知识库"
#: ../../modules/knownledge.md:5 e137d9916a0a4a0681dbfed5d5a5065f
#: ../../modules/knownledge.md:5 93a25018fc144dfe98fcea0755f2ea94
msgid "Custom addition of knowledge bases"
msgstr "自定义新增知识库"
#: ../../modules/knownledge.md:6 0bca133996d4435b84245f2b53f43d72
#: ../../modules/knownledge.md:6 37359e14b2464b2c9fc4e5621755bb0d
msgid ""
"Various usage scenarios such as constructing knowledge bases through "
"plugin capabilities and web crawling. Users only need to organize the "
@@ -47,51 +47,52 @@ msgid ""
"the knowledge base required for the large model."
msgstr "各种使用场景,例如通过插件功能和爬虫构建知识库。用户只需要组织知识文档,并且他们可以使用我们现有的功能来构建大型模型所需的知识库。"
#: ../../modules/knownledge.md:9 7355eed198514efc8e3bc178039b0251
#: ../../modules/knownledge.md:9 656fcb11886546df9e058227d94481b3
msgid "Create your own knowledge repository"
msgstr "创建你自己的知识库"
#: ../../modules/knownledge.md:11 96e0276a5d3047fea5410e9b33c33308
#: ../../modules/knownledge.md:11 37fc3ae2cfe044f8ac61de484bf0653d
msgid ""
"1.Place personal knowledge files or folders in the pilot/datasets "
"directory."
msgstr "1.将个人知识文件或文件夹放在pilot/datasets目录中。"
#: ../../modules/knownledge.md:13 8762c0a463094c19924cdd4b7b1b1ede
#: ../../modules/knownledge.md:13 a675d90485834690bfca68b41a10c085
msgid ""
"We currently support many document formats: txt, pdf, md, html, doc, ppt,"
" and url."
msgstr "当前支持txt, pdf, md, doc, ppt, html文档格式"
#: ../../modules/knownledge.md:15 752a5e7c623a49439ecf1ce8e6ccca7d
#: ../../modules/knownledge.md:15 f2c25b0536ff4b3191e13f3020e883a6
msgid "before execution:"
msgstr "在执行之前"
#: ../../modules/knownledge.md:22 fbef967557a94b938f8e47497bb43c20
#: ../../modules/knownledge.md:22 65427906c8b54cd699a07ed482251c83
msgid ""
"2.Update your .env, set your vector store type, VECTOR_STORE_TYPE=Chroma "
"(now only support Chroma and Milvus, if you set Milvus, please set "
"MILVUS_URL and MILVUS_PORT)"
msgstr "2.更新你的.env设置你的向量存储类型VECTOR_STORE_TYPE=Chroma(现在只支持Chroma和Milvus如果你设置了Milvus请设置MILVUS_URL和MILVUS_PORT)"
#: ../../modules/knownledge.md:25 f1745e2f17864711a636ecbdd6cb9833
msgid "2.Run the knowledge repository script in the tools directory."
msgstr "2.在tools目录执行知识入库脚本"
#: ../../modules/knownledge.md:25 287ae6ee51cc4b668d99e48b81147d3f
#, fuzzy
msgid "2.Run the knowledge repository initialization command"
msgstr "2.执行知识入库命令"
#: ../../modules/knownledge.md:34 5ae832d038b245a29a9e089f9e169cb0
#: ../../modules/knownledge.md:31 1fe0ac58d8354c7fba782901cb0673d8
msgid ""
"Optionally, you can run `python tools/knowledge_init.py -h` command to "
"see more usage."
msgstr ""
"Optionally, you can run `dbgpt knowledge load --help` command to see more"
" usage."
msgstr "另外,你可以运行 `dbgpt knowledge load --help` 命令来查看更多的用法"
#: ../../modules/knownledge.md:36 4aab02276dfd41819dbd218ecc608326
#: ../../modules/knownledge.md:33 e1607e330195470f9087bd4ffbc6d45d
msgid ""
"3.Add the knowledge repository in the interface by entering the name of "
"your knowledge repository (if not specified, enter \"default\") so you "
"can use it for Q&A based on your knowledge base."
msgstr "如果选择新增知识库,在界面上新增知识库输入你的知识库名"
#: ../../modules/knownledge.md:38 f990c8495c994aa1beb040ede6b2329a
#: ../../modules/knownledge.md:35 0614e35ccfba42ea9e63881cb481815e
msgid ""
"Note that the default vector model used is text2vec-large-chinese (which "
"is a large model, so if your personal computer configuration is not "
@@ -101,3 +102,9 @@ 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-"
"chinese),因此确保需要将模型download下来放到models目录中。"
#~ msgid ""
#~ "Optionally, you can run `python "
#~ "tools/knowledge_init.py -h` command to see "
#~ "more usage."
#~ msgstr ""

View File

@@ -22,16 +22,13 @@ python -m spacy download zh_core_web_sm
2.Update your .env, set your vector store type, VECTOR_STORE_TYPE=Chroma
(now only support Chroma and Milvus, if you set Milvus, please set MILVUS_URL and MILVUS_PORT)
2.Run the knowledge repository script in the tools directory.
```
python tools/knowledge_init.py
--vector_name : your vector store name default_value:default
2.Run the knowledge repository initialization command
```bash
dbgpt knowledge load
```
Optionally, you can run `python tools/knowledge_init.py -h` command to see more usage.
Optionally, you can run `dbgpt knowledge load --help` command to see more usage.
3.Add the knowledge repository in the interface by entering the name of your knowledge repository (if not specified, enter "default") so you can use it for Q&A based on your knowledge base.