vikramkoka opened a new pull request, #67618:
URL: https://github.com/apache/airflow/pull/67618
LangChain counterpart to `example_llamaindex_10k.py` — same DAG shape, same
sample data, same Pydantic models, different framework underneath. Demonstrates
that the framework choice is a swappable implementation detail while Airflow
provides orchestration, HITL, and observability.
Two DAGs:
- `example_langchain_10k_index` (weekly): builds per-company FAISS vector
indexes via Dynamic Task Mapping using LangChainHook +
RecursiveCharacterTextSplitter + FAISS.
- `example_langchain_10k_analysis` (manual trigger): HITL entry → @task.llm
sub-question decomposition with structured output → Dynamic Task Mapping
fan-out retrieval (one FAISS query per sub-question) → collect → LLMOperator
synthesis with UsageLimits and AnalysisReport schema → ApprovalOperator gate.
<!-- 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]
