We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Windows
=3.11
latest release
Installation From Source
Docker Installation
Docker Compose Installation
Cluster Installation
AutoDL Image
Other
7754HX 笔记本版本cpu 4070 笔记本版本
deepseek+glm-4-0520+bge_embedding
VECTOR_STORE_TYPE=Chroma 后,window 不读取配置文件中的 MILVIS、TuGrah配置。当前版本似乎将VECTOR_STORE_TYPE和Graph定义成唯一组件,但在实际应用中会依赖同一个目的下的不同组件。 配置文件如下,已经完成了隐私控制:
`VECTOR_STORE_TYPE=Chroma GRAPH_STORE_TYPE=TuGraph
#CHROMA_PERSIST_PATH=/root/DB-GPT/pilot/data
#VECTOR_STORE_TYPE=Milvus MILVUS_URL=10.108.. MILVUS_PORT=19530 MILVUS_USERNAME=wintelia MILVUS_PASSWORD=wintelia2024 MILVUS_SECURE=False
#VECTOR_STORE_TYPE=Weaviate #WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
## ElasticSearch vector db config
#VECTOR_STORE_TYPE=ElasticSearch ElasticSearch_URL=10.108.. ElasticSearch_PORT=9200 ElasticSearch_USERNAME EicSearchlast_PASSWORD
TUGRAPH_HOST=10.108.4.1 TUGRAPH_PORT=33314 TUGRAPH_USERNAME=admin TUGRAPH_PASSWORD=73@TuGraph TUGRAPH_VERTEX_TYPE=entity TUGRAPH_EDGE_TYPE=relation TUGRAPH_EDGE_NAME_KEY=label
## #** WebServer Language Support **# ##
#LANGUAGE=en LANGUAGE=zh`
dbgpt.storage.vector_store.milvus_store中 class MilvusStore 在被上层调用了采用了默认的 MilvusVectorConfig 配置(当VECTOR_STORE_TYPE 被指向非Milvus时)。这导致配置文件在期望使用多个 VECTOR_STORE 时出现错误。
在该版本中,同样的情况出现在Graphrag上,由于对.env配置文件读取的异常,同时采用同类型多个服务组件变得困难。
期望官方调整.env的读取方式,对于proxy_llm 以列表方式读取,运行在online的llm下初始化时运行多个模型,载入多个不同组件的Vector_store和graph作为备选。
我正在将Graphrag作为服务整合进入dbgpt,但由于配置读取上设计思路的复杂化导致直接嵌入几乎不可取。
windows 11 下配置 ### TuGraph config #VECTOR_STORE_TYPE=ElasticSearch ### Weaviate vector db config 和#VECTOR_STORE_TYPE=Milvus 即可复现
No response
The text was updated successfully, but these errors were encountered:
一个临时的解决方案能够让配置生效: 修改dbgpt.storage.vector_store.milvus_store.MilvusStore 中(大约在164行)所有关于milvus的配置判断,先判断os.getenv下的配置信息,再从 milvus_vector_config = vector_store_config.to_dict() 中读取。
在测试中,大多数情况下milvus组件的配置都默认指向了localhost,这是不对的。
Sorry, something went wrong.
@shaoqing404, sorry about that, we will update milvus url config localhost
localhost
This issue has been marked as stale, because it has been over 30 days without any activity.
stale
This issue bas been closed, because it has been marked as stale and there has been no activity for over 7 days.
No branches or pull requests
Search before asking
Operating system information
Windows
Python version information
DB-GPT version
latest release
Related scenes
Installation Information
Installation From Source
Docker Installation
Docker Compose Installation
Cluster Installation
AutoDL Image
Other
Device information
7754HX 笔记本版本cpu
4070 笔记本版本
Models information
deepseek+glm-4-0520+bge_embedding
What happened
VECTOR_STORE_TYPE=Chroma 后,window 不读取配置文件中的 MILVIS、TuGrah配置。当前版本似乎将VECTOR_STORE_TYPE和Graph定义成唯一组件,但在实际应用中会依赖同一个目的下的不同组件。
配置文件如下,已经完成了隐私控制:
`VECTOR_STORE_TYPE=Chroma
GRAPH_STORE_TYPE=TuGraph
Chroma vector db config
#CHROMA_PERSIST_PATH=/root/DB-GPT/pilot/data
Milvus vector db config
#VECTOR_STORE_TYPE=Milvus
MILVUS_URL=10.108..
MILVUS_PORT=19530
MILVUS_USERNAME=wintelia
MILVUS_PASSWORD=wintelia2024
MILVUS_SECURE=False
Weaviate vector db config
#VECTOR_STORE_TYPE=Weaviate
#WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
#VECTOR_STORE_TYPE=ElasticSearch
ElasticSearch_URL=10.108..
ElasticSearch_PORT=9200
ElasticSearch_USERNAME
EicSearchlast_PASSWORD
TuGraph config
TUGRAPH_HOST=10.108.4.1
TUGRAPH_PORT=33314
TUGRAPH_USERNAME=admin
TUGRAPH_PASSWORD=73@TuGraph
TUGRAPH_VERTEX_TYPE=entity
TUGRAPH_EDGE_TYPE=relation
TUGRAPH_EDGE_NAME_KEY=label
##
#** WebServer Language Support **#
##
en, zh, fr, ja, ko, ru
#LANGUAGE=en
LANGUAGE=zh`
What you expected to happen
dbgpt.storage.vector_store.milvus_store中 class MilvusStore 在被上层调用了采用了默认的 MilvusVectorConfig 配置(当VECTOR_STORE_TYPE 被指向非Milvus时)。这导致配置文件在期望使用多个 VECTOR_STORE 时出现错误。
在该版本中,同样的情况出现在Graphrag上,由于对.env配置文件读取的异常,同时采用同类型多个服务组件变得困难。
期望官方调整.env的读取方式,对于proxy_llm 以列表方式读取,运行在online的llm下初始化时运行多个模型,载入多个不同组件的Vector_store和graph作为备选。
我正在将Graphrag作为服务整合进入dbgpt,但由于配置读取上设计思路的复杂化导致直接嵌入几乎不可取。
How to reproduce
windows 11 下配置 ### TuGraph config #VECTOR_STORE_TYPE=ElasticSearch ### Weaviate vector db config 和#VECTOR_STORE_TYPE=Milvus 即可复现
Additional context
No response
Are you willing to submit PR?
The text was updated successfully, but these errors were encountered: