You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@kyuubi.apache.org by zhigang wang <ia...@gmail.com> on 2026/03/31 06:33:24 UTC
[DISCUSS] KPIP: Data Agent Engine — AI-Powered Autonomous Data Analysis
Hi Kyuubi community,
I'd like to propose a new engine type: Data Agent Engine, which enables
users to perform data analysis through natural language.
What it does: Users connect via JDBC/REST, ask questions in plain language,
and an AI agent (ReAct loop) autonomously explores schemas, generates SQL,
executes queries, verifies results, and self-corrects — without user
intervention.
Key architecture decision: The agent's SQL tool uses Kyuubi's JDBC driver
to connect back to Kyuubi Server, following the same pattern as the
existing JDBC Engine. This ensures all queries go through the Server
gateway, preserving AuthZ (Ranger), audit logging, multi-tenancy, and
resource isolation.
Client → Kyuubi Server → Data Agent Engine
│ (sql_query tool)
JDBC Driver (user creds)
│
Kyuubi Server → Spark/Trino/Hive
Implementation: Java + LangChain4j on the JVM, consistent with all
existing Kyuubi engines.
Full proposal: https://github.com/apache/kyuubi/discussions/7373
Looking forward to your feedback!
Best,
Zhigang
Re: [DISCUSS] KPIP: Data Agent Engine — AI-Powered Autonomous Data Analysis
Posted by Cheng Pan <pa...@gmail.com>.
+1, looking forward your PRs.
Thanks,
Cheng Pan
> On Apr 2, 2026, at 19:26, zhigang wang <ia...@gmail.com> wrote:
>
> Thanks for the +1! I've started prototyping and will open an umbrella
> issue + PRs soon. Looking forward to feedback from the community.
>
> Kent Yao <ya...@apache.org> 于2026年3月31日周二 18:58写道：
>
>> +1
>>
>> zhigang wang <ia...@gmail.com> 于2026年3月31日周二 14:33写道：
>>
>>> Hi Kyuubi community,
>>>
>>> I'd like to propose a new engine type: Data Agent Engine, which enables
>>> users to perform data analysis through natural language.
>>>
>>> What it does: Users connect via JDBC/REST, ask questions in plain
>> language,
>>> and an AI agent (ReAct loop) autonomously explores schemas, generates
>> SQL,
>>> executes queries, verifies results, and self-corrects — without user
>>> intervention.
>>>
>>> Key architecture decision: The agent's SQL tool uses Kyuubi's JDBC driver
>>> to connect back to Kyuubi Server, following the same pattern as the
>>> existing JDBC Engine. This ensures all queries go through the Server
>>> gateway, preserving AuthZ (Ranger), audit logging, multi-tenancy, and
>>> resource isolation.
>>>
>>> Client → Kyuubi Server → Data Agent Engine
>>> │ (sql_query tool)
>>> JDBC Driver (user creds)
>>> │
>>> Kyuubi Server → Spark/Trino/Hive
>>>
>>> Implementation: Java + LangChain4j on the JVM, consistent with all
>>> existing Kyuubi engines.
>>>
>>> Full proposal: https://github.com/apache/kyuubi/discussions/7373
>>>
>>> Looking forward to your feedback!
>>>
>>> Best,
>>> Zhigang
>>>
>>
Re: [DISCUSS] KPIP: Data Agent Engine — AI-Powered Autonomous Data Analysis
Posted by zhigang wang <ia...@gmail.com>.
Thanks for the +1! I've started prototyping and will open an umbrella
issue + PRs soon. Looking forward to feedback from the community.
Kent Yao <ya...@apache.org> 于2026年3月31日周二 18:58写道：
> +1
>
> zhigang wang <ia...@gmail.com> 于2026年3月31日周二 14:33写道：
>
> > Hi Kyuubi community,
> >
> > I'd like to propose a new engine type: Data Agent Engine, which enables
> > users to perform data analysis through natural language.
> >
> > What it does: Users connect via JDBC/REST, ask questions in plain
> language,
> > and an AI agent (ReAct loop) autonomously explores schemas, generates
> SQL,
> > executes queries, verifies results, and self-corrects — without user
> > intervention.
> >
> > Key architecture decision: The agent's SQL tool uses Kyuubi's JDBC driver
> > to connect back to Kyuubi Server, following the same pattern as the
> > existing JDBC Engine. This ensures all queries go through the Server
> > gateway, preserving AuthZ (Ranger), audit logging, multi-tenancy, and
> > resource isolation.
> >
> > Client → Kyuubi Server → Data Agent Engine
> > │ (sql_query tool)
> > JDBC Driver (user creds)
> > │
> > Kyuubi Server → Spark/Trino/Hive
> >
> > Implementation: Java + LangChain4j on the JVM, consistent with all
> > existing Kyuubi engines.
> >
> > Full proposal: https://github.com/apache/kyuubi/discussions/7373
> >
> > Looking forward to your feedback!
> >
> > Best,
> > Zhigang
> >
>
Re: [DISCUSS] KPIP: Data Agent Engine — AI-Powered Autonomous Data Analysis
Posted by Kent Yao <ya...@apache.org>.
+1
zhigang wang <ia...@gmail.com> 于2026年3月31日周二 14:33写道：
> Hi Kyuubi community,
>
> I'd like to propose a new engine type: Data Agent Engine, which enables
> users to perform data analysis through natural language.
>
> What it does: Users connect via JDBC/REST, ask questions in plain language,
> and an AI agent (ReAct loop) autonomously explores schemas, generates SQL,
> executes queries, verifies results, and self-corrects — without user
> intervention.
>
> Key architecture decision: The agent's SQL tool uses Kyuubi's JDBC driver
> to connect back to Kyuubi Server, following the same pattern as the
> existing JDBC Engine. This ensures all queries go through the Server
> gateway, preserving AuthZ (Ranger), audit logging, multi-tenancy, and
> resource isolation.
>
> Client → Kyuubi Server → Data Agent Engine
> │ (sql_query tool)
> JDBC Driver (user creds)
> │
> Kyuubi Server → Spark/Trino/Hive
>
> Implementation: Java + LangChain4j on the JVM, consistent with all
> existing Kyuubi engines.
>
> Full proposal: https://github.com/apache/kyuubi/discussions/7373
>
> Looking forward to your feedback!
>
> Best,
> Zhigang
>