apache/seatunnel

[Feature] Connector prepare for RAG

Open

#9713 opened on Aug 18, 2025

View on GitHub
 (3 comments) (4 reactions) (0 assignees)Java (6,897 stars) (1,432 forks)batch import
featuregood first issuehelp wantedllm

Description

Search before asking

  • I had searched in the feature and found no similar feature requirement.

Description

As a multimodal data integration tool, we hope that SeaTunnel can support parsing complex file types, converting their contents into structured file streams, and ultimately writing them into a vector library through embedding. This issue tracks related tasks.

For chunking please refer Please refer https://docs.dify.ai/en/guides/knowledge-base/create-knowledge-and-upload-documents/chunking-and-cleaning-text and https://docs.llamaindex.ai/en/stable/examples/node_parsers/semantic_chunking/

Usage Scenario

No response

Related issues

No response

Are you willing to submit a PR?

  • Yes I am willing to submit a PR!

Code of Conduct

Contributor guide

Tech stack
java
Domain
dataai
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Knowledge of RAG pipelinesUnderstanding of text chunking techniquesFamiliarity with SeaTunnel connector APIBasic knowledge of vector databases
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20
Research direction
Investigate the chunking strategies referenced (Dify and LlamaIndex) to understand how to split documents into chunks. Evaluate existing SeaTunnel connectors for patterns on how to implement new connector types. Consider vector database options (e.g., Pinecone, Milvus) as targets for embedding storage. Review the SeaTunnel documentation and source code for connector development guidelines. Design a prototype connector that parses a simple file type, chunks the content, generates embeddings via an external API, and writes to a vector database.