vikramkoka opened a new pull request, #67660:
URL: https://github.com/apache/airflow/pull/67660
Demonstrates Dynamic Task Mapping, structured LLM output (Pydantic),
cost-controlled synthesis (UsageLimits), and HITL approval using LLMOperator
with live data from the Apache Confluence wiki and GitHub.
The DAG accepts an aip_numbers param (default: 76,99,103,105,108) to choose
which AIPs to investigate. For each AIP it fetches the spec via Confluence CQL
search and gathers PR/commit evidence from the GitHub Search API, then fans out
structured LLM analysis via DTM and synthesizes a cross-AIP progress report for
maintainer review.
<!-- SPDX-License-Identifier: Apache-2.0
https://www.apache.org/licenses/LICENSE-2.0 -->
---
##### Was generative AI tooling used to co-author this PR?
- [ x] Yes (please specify the tool below)
Generated-by: [Claude] following [the
guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#gen-ai-assisted-contributions)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
