github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-03 17:39:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix:milvus readme

Browse Source
This commit is contained in:
aries-ckt 2023-05-26 15:09:47 +08:00
parent e9b14cb974
commit 061646fc8e
3 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -194,7 +194,9 @@ To use multiple models, modify the LLM_MODEL parameter in the .env configuration
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.Run the knowledge repository script in the tools directory. 2.set .env configuration set your vector store type, eg:VECTOR_STORE_TYPE=Chroma, now we support Chroma and Milvus(version > 2.1)
3.Run the knowledge repository script in the tools directory.
```bash ```bash
& python tools/knowledge_init.py & python tools/knowledge_init.py
@ -204,7 +206,7 @@ To use multiple models, modify the LLM_MODEL parameter in the .env configuration
``` ```
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. 4.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.
Note that the default vector model used is text2vec-large-chinese (which is a large model, so if your personal computer configuration is not enough, it is recommended to use text2vec-base-chinese). Therefore, ensure that you download the model and place it in the models directory. Note that the default vector model used is text2vec-large-chinese (which is a large model, so if your personal computer configuration is not enough, it is recommended to use text2vec-base-chinese). Therefore, ensure that you download the model and place it in the models directory.

2
README.zh.md
View File

@ -194,6 +194,8 @@ $ python webserver.py
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) 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)
注意Milvus版本需要>2.1
3.在tools目录执行知识入库脚本（） 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 如果是选择默认知识库，不需要指定 --vector_name, 默认default

2
requirements.txt
View File

@ -46,7 +46,7 @@ wandb
llama-index==0.5.27 llama-index==0.5.27
pymysql pymysql
unstructured==0.6.3 unstructured==0.6.3
grpcio==1.54.2 grpcio==1.47.5
auto-gpt-plugin-template auto-gpt-plugin-template
pymdown-extensions pymdown-extensions