Jack ae256bcf59 feat(chunker): add ManualChunker for manual-layout PDFs (#18272) ...

Add `ManualChunker`, the Go port of Python's `manual` doc-type chunk method (`rag/app/manual.py`). Like `GroupTitleChunker` it merges adjacent text records into heading-bounded groups, but it first re-sorts the records into physical reading order before grouping.

2026-08-14 16:55:08 +08:00

..

admin

fix(ingestion): remove broken built-in Resume pipeline (#18173)

2026-08-12 19:11:49 +08:00

agent

Port agentic search high/ultra research loop to Go (#18242)

2026-08-14 10:16:46 +08:00

binding

Port PR14140 and PR16881 to GO (#17102)

2026-07-21 17:46:23 +08:00

channels

fix: return error when chat-channel start has error (#18068)

2026-08-11 19:36:35 +08:00

cli

feat(cli): add sync logs listing commands for the user CLI (#18195)

2026-08-13 18:39:29 +08:00

common

feat: add UCloud agent sandbox provider (#18088)

2026-08-13 15:33:03 +08:00

component/messagefit

feat(component): add shared message-fit package (#18091)

2026-08-12 13:03:45 +08:00

dao

Add MySQL and PostgreSQL connectors to Go syncer (#18162)

2026-08-13 20:16:44 +08:00

deepdoc

fix(pdf/layout): recover title-bridged & gutter-less double columns (2D rescue + L3) (#18150)

2026-08-12 17:59:50 +08:00

engine

Go: add error logs when fail to init infinity (#18235)

2026-08-13 20:17:53 +08:00

entity

Go: refactor embed and rerank interface (#18240)

2026-08-13 22:14:23 +08:00

handler

feat(chunker): add ManualChunker for manual-layout PDFs (#18272)

2026-08-14 16:55:08 +08:00

harness

Go: fix context and warnings (#18097)

2026-08-11 16:18:49 +08:00

ingestion

feat(chunker): add ManualChunker for manual-layout PDFs (#18272)

2026-08-14 16:55:08 +08:00

mcp

Go: add context, part5 (#17392)

2026-07-27 10:20:16 +08:00

parser

fix(parser): support .msg parsing and make email attachments retrievable (#18198)

2026-08-14 10:38:38 +08:00

router

feat(cli): add sync logs listing commands for the user CLI (#18195)

2026-08-13 18:39:29 +08:00

server

feat[Go]: resuming transmission from the point of interruption during data source synchronisation (#18176)

2026-08-13 18:38:37 +08:00

service

feat(chunker): add ManualChunker for manual-layout PDFs (#18272)

2026-08-14 16:55:08 +08:00

storage

Go: fix context (#18118)

2026-08-11 19:19:29 +08:00

syncer

Add MySQL and PostgreSQL connectors to Go syncer (#18162)

2026-08-13 20:16:44 +08:00

tokenizer

fix(tokenizer): load cl100k BPE table from disk instead of failing silently offline (#17712)

2026-08-03 19:03:08 +08:00

utility

Go: fix context and warnings (#18097)

2026-08-11 16:18:49 +08:00

development.md

Go: fix heartbeat log (#17899)

2026-08-05 22:05:07 +08:00