SEZ9 commented on issue #9718: URL: https://github.com/apache/seatunnel/issues/9718#issuecomment-5852030118
Could you clarify the intended scope and location of this document? For example: should it be a single end-to-end guide under docs/en/ (e.g. docs/en/concept/ or a new docs/en/rag/ section) covering unstructured source ingestion, text chunking/splitting, Embedding/LLM transforms, and vector-store sinks (Milvus, Qdrant, Pinecone, Elasticsearch, etc.), with a complete runnable job config example? Also, should it be added to the sidebars of both the English and Chinese docs? For contributors picking this up: please base the doc on features that already exist in the codebase (relevant transforms such as Embedding/LLM and the vector-database connectors), link to their existing connector/transform pages instead of duplicating parameter tables, and include a full example config that has been verified to run. Please comment here before starting so we can avoid duplicate work. It would help to list the concrete components that make up 'RAG Ready' in the issue body so the scope is unambiguous — e.g. which sources, transforms, and sinks are considered part of the pipeline, and which SeaTunnel version the doc should target. <!-- streview-comment:1343 --> -- 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]
