github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-03 01:12:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

update:readme knowledge part

Browse Source
This commit is contained in:
aries-ckt 2023-05-25 22:16:18 +08:00
parent b42e8e4549
commit d735240ec6
2 changed files with 18 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
README.zh.md
View File

@ -190,18 +190,28 @@ $ python webserver.py
### 打造属于你的知识库： ### 打造属于你的知识库：
1、将个人知识文件或者文件夹放入pilot/datasets目录中 1.将个人知识文件或者文件夹放入pilot/datasets目录中
2、在tools目录执行知识入库脚本 2.在.env文件指定你的向量数据库类型,VECTOR_STORE_TYPE(默认Chroma),目前支持Chroma,Milvus(需要设置MILVUS_URL和MILVUS_PORT)
3.在tools目录执行知识入库脚本（）
如果是选择默认知识库，不需要指定 --vector_name, 默认default
``` ```
python tools/knowledge_init.py python tools/knowledge_init.py
--vector_name : your vector store name default_value:default ```
--append: append mode, True:append, False: not append default_value:False
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,
``` ```
3、在界面上新增知识库输入你的知识库名（如果没指定输入default）,就可以根据你的知识库进行问答 python tools/knowledge_init.py --vector_name = yourname
--vector_name: vector_name default_value:default
```
就可以根据你的知识库进行问答
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。 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。

3
docs/modules/knownledge.md
View File

@ -10,6 +10,9 @@ As the knowledge base is currently the most significant user demand scenario, we
1.Place personal knowledge files or folders in the pilot/datasets directory. 1.Place personal knowledge files or folders in the pilot/datasets directory.
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. 2.Run the knowledge repository script in the tools directory.
``` ```