vikramkoka opened a new pull request, #67671:
URL: https://github.com/apache/airflow/pull/67671
Two Dags demonstrating a multi-company financial research pipeline using
real SEC 10-K filings fetched live from the EDGAR public API:
- Indexing DAG (weekly): fetches 10-K filings by stock ticker, extracts
Risk Factors and MD&A sections, builds per-company vector indexes via
LlamaIndexEmbeddingOperator with DTM fan-out.
- Analysis DAG (on-demand): analyst submits tickers and a comparison
question via HITLEntryOperator, LLM decomposes into company-specific
sub-questions (N decided at runtime), retrieves from per-company indexes via
DTM, synthesizes a structured report (AnalysisReport Pydantic model with
UsageLimits), formats for human review, and gates on ApprovalOperator.
Features showcased: Dynamic Task Mapping, structured LLM output,
UsageLimits, HITL input and approval, and live external API integration.
Default tickers: AAPL, MSFT, UBER, LYFT, AMZN.
<!-- 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]
