GitHub user vinothchandar edited a discussion: [DISCUSS] New Agentic lakehouse module & built-in AI agent gateway
(Also mirrored to dev ML) Hi all, I'd like to propose adding an optional, self-hostable AI serving layer to Hudi — making every Hudi table something you can talk to, and over time, something agents can help operate. Concretely: a set of Helm charts deploying Trino + a new agent gateway service that hosts an LLM agent loop with guarded read-only SQL tools over the lakehouse, exposes the same tools to external agents via MCP, and ships a small chat UI. Local inference (Ollama) is the out-of-box default; API providers and vLLM are values-file choices. Nothing about existing Hudi APIs, configs, or storage changes — it's all additive. Why in the project rather than as external glue: the tools can be engine-native (catalog introspection today; incremental queries and table services operations next), the stack stays fully open and self-hostable, and answer quality can build on Hudi-specific knowledge. - Umbrella feature issue with the breakdown: #19256 - Initial implementation (charts + gateway + local dev environment): #19265 Would love feedback on the direction, the proposed breakdown, and interest in contributing — especially from folks running Hudi with Trino, or with opinions on inference deployment and agent tooling. If the direction lands well here, we'll firm up designs on the individual sub-issues (and RFCs if engine/format surfaces are touched). The longer arc is: - Agents that assist with operating tables — tuning, inspection, maintenance — reducing ops and tuning complexity. - Context is as important to AI inference as the model itself. Hudi tables support for [unstructured data](https://github.com/apache/hudi/blob/master/rfc/rfc-100/rfc-100.md), [vector search index](https://github.com/apache/hudi/pull/19107) - can serve any data at inference time. - Emitting traces back to Hudi tables from agent-gateway can help eval, fine-tuning. - Traces also help the agent optimize the layout of tables, build indexes and such. GitHub link: https://github.com/apache/hudi/discussions/19264 ---- This is an automatically sent email for [email protected]. To unsubscribe, please send an email to: [email protected]
