inchang-ing opened a new pull request, #12488:
URL: https://github.com/apache/seatunnel/pull/12488
### Purpose of this pull request
This PR closes #9718. It adds a bilingual (English + Chinese) guide
introducing how to build RAG-ready data processing pipelines with SeaTunnel,
and registers it in the sidebar under **Introduction**.
The document covers:
- Why a data pipeline matters for RAG (parsing → chunking → enrichment →
embedding → vector store)
- The SeaTunnel building blocks with links to each plugin doc: LocalFile
document parsing (`markdown` / `pdf` + RAG metadata fields), JDBC / CDC
sources, TextChunk, Split, Metadata, LLM, Embedding transforms, Milvus and
Qdrant sinks
- Two end-to-end HOCON examples: a Markdown knowledge base loaded into
Milvus, and MySQL rows vectorized into Qdrant
- Strategies for keeping vectors fresh (full rebuild, upsert, CDC) including
the honest caveat that stale chunks are not auto-deleted
- Best practices (chunk sizing, embedding retries/batching, float32
precision, primary-key constraints, metadata filtering) and a short FAQ
All option names used in the examples were verified against the existing
connector and transform documentation in this repo. The en/zh pages are
content-aligned, and all relative links were checked to resolve to existing
files.
### Does this PR introduce _any_ user-facing change?
Yes — it adds two new documentation pages:
- `docs/en/introduction/rag-data-processing.md`
- `docs/zh/introduction/rag-data-processing.md`
registered in `docs/sidebars.js` under the Introduction category. There are
no code behavior changes.
### How was this patch tested?
Documentation-only change. Verified locally:
- All relative links in both documents resolve to existing files in the repo
- The en and zh pages have aligned section structure (8 sections each) and
balanced code fences
- HOCON examples follow the same formatting as existing examples in the
connector docs (e.g. the Milvus sink example)
- The new page id `introduction/rag-data-processing` is registered in
`docs/sidebars.js`
### Check list
* [ ] If any new Jar binary package adding in your PR, please add License
Notice according
[New License
Guide](https://github.com/apache/seatunnel/blob/dev/docs/en/developer/new-license.md)
* [x] If necessary, please update the documentation to describe the new
feature. https://github.com/apache/seatunnel/tree/dev/docs
* [ ] If necessary, please update `incompatible-changes.md` to describe the
incompatibility caused by this PR.
* [ ] If you are contributing the connector code, please check that the
following files are updated:
1. Update
[plugin-mapping.properties](https://github.com/apache/seatunnel/blob/dev/plugin-mapping.properties)
and add new connector information in it
2. Update the pom file of
[seatunnel-dist](https://github.com/apache/seatunnel/blob/dev/seatunnel-dist/pom.xml)
3. Add ci label in
[label-scope-conf](https://github.com/apache/seatunnel/blob/dev/.github/workflows/labeler/label-scope-conf.yml)
4. Add e2e testcase in
[seatunnel-e2e](https://github.com/apache/seatunnel/tree/dev/seatunnel-e2e/seatunnel-connector-v2-e2e/)
5. Update connector
[plugin_config](https://github.com/apache/seatunnel/blob/dev/config/plugin_config)
--
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]
