6 Commits

Author SHA1 Message Date
jay77721
2a1a93ed3a refactor(extractor): unify 5-in-1 modular schema across dataset and pipeline, drop legacy field_name and custom prompt (#18432)
Refactor the Extractor component into a pure, unified **5-in-1 modular extraction engine** across both Dataset (`knowledgebase.parser_config`) and Pipeline (Canvas DSL).
2026-08-19 15:02:46 +08:00
jay77721
3e38b6cacb fix(ingestion): unify extractor prompt placeholder rendering and per-chunk substitution (#18355) 2026-08-17 15:19:47 +08:00
jay77721
e1b8366ecc refactor: remove resume (CV) workflow DSL template and Go handling code (#18177) 2026-08-13 10:47:37 +08:00
Jack
3c0f8fc192 Refactor: refactor dataflow_service.go and guard nats message re-delivery (#16826)
### Summary

1. refactor dataflow_service.go 
2. guard nats message re-delivery
3. support document parse cancelling & re-run
2026-07-13 11:08:04 +08:00
Jack
8ac80284c4 Feat: add embedding support (#16769)
### Summary

Feat: add embedding support
2026-07-09 16:24:39 +08:00
Zhichang Yu
014c3f634f Align Go ingestion boundaries with Python (#16647)
Moves doc_id blob resolution into Parser, tightens chunker/tokenizer to
Python output_format semantics, updates extractor list handling, and
fixes real-template integration tests.
2026-07-05 20:43:52 +08:00