6 Commits
Author SHA1 Message Date
Xinyu Mu 1635b16899 docs: add multilingual vocational task engine guide (#1749) 2026-10-01 21:01:09 +08:00
jackefnandwyuc 44e1ca0ca0 feat(rag): add document lexical retrieval foundation (#1078)
* feat(rag): add document lexical retrieval foundation

* fix(rag): align foundation contracts with review

* fix(rag): handle quoted br attributes

* perf(rag): stream grapheme chunk splitting

* fix(rag): preserve exact replacement scope

* perf(rag): avoid repeated grapheme segmentation

* refactor(rag): isolate grapheme chunking

* perf(rag): avoid runtime-dependent grapheme segmentation

* fix(rag): complete review contract corrections

* fix(rag): resolve follow-up correctness review

* fix(rag): address latest review corrections

---------

Co-authored-by: wyuc <wang-yc24@mails.tsinghua.edu.cn>
2026-08-17 12:16:31 +08:00
jackefn b4834f5c74 feat(document): add transform pipeline foundation (#920)
Add a provider-neutral document transform pipeline with execution history, normalization, conservative noise removal, cancellation, and failure policies.

Keep document structure and outline generation out of the canonical artifact until a concrete consumer and evaluation criteria exist.
2026-08-07 03:00:48 -04:00
jackefnandRowan_lxb baff0998bb Feat/document bundles milestone 3 (#844)
* feat(document): support document bundles

* fix(document): avoid server extractor imports in client bundle

* fix(pdf): default mineru backend to pipeline

* fix(document): address bundle review findings

* fix(document): harden extraction limits and storage errors

* fix(document): make analysis step format agnostic

---------

Co-authored-by: Rowan_lxb <Lxb_savior@163.com>
2026-07-13 23:01:40 +08:00
jackefnandYanpeng Wang 3b7a0ca0c0 feat(document): add multi-format course material upload (#741)
* feat(document): add multi-format course material upload

* fix(document): support office uploads with mineru cloud

* fix(document): handle mineru cloud office edge cases

* fix(document): align mineru cloud artifact metadata

---------

Co-authored-by: Yanpeng Wang <yanpg.wang@gmail.com>
2026-07-02 17:58:58 +08:00
jackefn a7cb5b5813 feat(document): add extractor provider foundation (#704) 2026-06-14 16:59:40 +08:00