[Question]: Does ragflow support cluster deployment? Does it support shared knowledge bases after clustering? The main purpose of clustering is to address the resource limitations of a single server.

[myplxdm]

Self Checks

• [ ] I have searched for existing issues search for existing issues, including closed ones.
• [ ] I confirm that I am using English to submit this report (Language Policy).
• [ ] Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
• [ ] Please do not modify this template :) and fill in all the required fields.

Describe your problem

Does ragflow support cluster deployment? Does it support shared knowledge bases after clustering? The main purpose of clustering is to address the resource limitations of a single server.

[dosubot[bot]]

RAGFlow does support distributed computing, which is a key aspect of cluster deployment. This is evidenced by the use of RedisDistributedLock for distributed locking, allowing for resource sharing and coordination across different nodes in a distributed system ^[1]. Additionally, the documentation mentions load balancing techniques for cluster deployment, suggesting the use of nginx as an upstream load balancer with multiple instances of ragflow_server.py ^[2].

Regarding shared knowledge bases, the open-source version of RAGFlow allows team members to access and share knowledge bases ^[3]. However, there is no specific mention of limitations or considerations when using shared knowledge bases in a clustered environment.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[KevinHuSh]

Cluster deployment is supported. Multiple RAGFlow server nodes with one MySQL DB can full fill KB sharing.