eosphoros-ai / DB-GPT

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents
http://docs.dbgpt.cn
MIT License
13.87k stars 1.87k forks source link

[Feature]:请问text2sql任务,表数量,规模过大,不能一次性输出大模型上下文的话,应该怎么办,框架有支持嘛 #492

Closed steph730 closed 12 months ago

steph730 commented 1 year ago

Is your feature request related to a problem? Please describe. A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Describe the solution you'd like A clear and concise description of what you want to happen.

Describe alternatives you've considered A clear and concise description of any alternative solutions or features you've considered.

Additional context Add any other context or screenshots about the feature request here.

xs818818 commented 1 year ago

同问,我也遇到这个问题

steph730 commented 1 year ago

同问,我也遇到这个问题

有什么解决办法嘛,这个不支持的话用不到实际生产项目中啊

Xavier-123 commented 1 year ago

同问,我也遇到这个问题

有什么解决办法嘛,这个不支持的话用不到实际生产项目中啊

.env里面的KNOWLEDGE_SEARCH_TOP_SIZE参数可以限制吧

csunny commented 12 months ago

@steph730 最新的版本有通过表summary做召回。 #885 不过在实际生产环境使用中, 面对数十万的表,精确度是一个很复杂的问题,后续我们也会针对性做更多的优化, 可以持续关注我们项目的迭代。