惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

The GitHub Blog
The GitHub Blog
有赞技术团队
有赞技术团队
Apple Machine Learning Research
Apple Machine Learning Research
V
V2EX
Engineering at Meta
Engineering at Meta
美团技术团队
H
Hackread – Cybersecurity News, Data Breaches, AI and More
博客园 - 司徒正美
I
InfoQ
S
SegmentFault 最新的问题
博客园 - 叶小钗
N
Netflix TechBlog - Medium
Y
Y Combinator Blog
IT之家
IT之家
博客园 - Franky
大猫的无限游戏
大猫的无限游戏
人人都是产品经理
人人都是产品经理
T
The Blog of Author Tim Ferriss
月光博客
月光博客
The Cloudflare Blog
U
Unit 42
GbyAI
GbyAI
L
LangChain Blog
Microsoft Azure Blog
Microsoft Azure Blog

Release notes from OmniClip-RAG

Release Caelune / 凯露恩 v0.5.6 · EllisMorrow/Caelune Release v0.5.5 · EllisMorrow/Caelune Release v0.5.4 · EllisMorrow/Caelune Release v0.5.2 · EllisMorrow/Caelune Release v0.5.1 · EllisMorrow/Caelune Release v0.5.0 · EllisMorrow/Caelune Release v0.4.13 · EllisMorrow/OmniClip-RAG Release v0.4.13 · EllisMorrow/Caelune Release v0.4.12 · EllisMorrow/OmniClip-RAG Release v0.4.12 · EllisMorrow/Caelune Release v0.4.9 · EllisMorrow/Caelune Release v0.4.11 · EllisMorrow/OmniClip-RAG Release v0.4.11 · EllisMorrow/Caelune Release v0.4.10 · EllisMorrow/OmniClip-RAG Release v0.4.10 · EllisMorrow/Caelune Release v0.4.9 · EllisMorrow/OmniClip-RAG Release v0.4.8 · msjsc001/OmniClip-RAG Release v0.4.8 · EllisMorrow/OmniClip-RAG Release v0.4.8 · EllisMorrow/Caelune Release v0.4.7 · msjsc001/OmniClip-RAG Release v0.4.7 · EllisMorrow/OmniClip-RAG Release v0.4.7 · EllisMorrow/Caelune Release v0.4.6 · msjsc001/OmniClip-RAG Release v0.4.6 · EllisMorrow/OmniClip-RAG Release v0.4.6 · EllisMorrow/Caelune Release v0.4.5 · msjsc001/OmniClip-RAG Release v0.4.5 · EllisMorrow/Caelune Release v0.4.4 · msjsc001/OmniClip-RAG Release v0.4.4 · EllisMorrow/OmniClip-RAG Release v0.4.3 · msjsc001/OmniClip-RAG
Release v0.4.5 · EllisMorrow/OmniClip-RAG
EllisMorrow · 2026-03-25 · via Release notes from OmniClip-RAG

OmniClip RAG v0.4.5 Release Notes

Release Focus

v0.4.5 is the extension oversized-routing hardening release.

This version finishes a practical stability problem that real users hit during PDF / Tika builds: some extension files are valid large text carriers and should still enter the search index, while others are really structured noise explosions that should never be allowed to poison the index or pin a build at a fake-progress plateau.

The release turns that distinction into a stable contract.

Highlights

  • Oversized extension inputs are no longer handled with one blunt rule:
    • text-heavy carriers such as PDF / DOC / DOCX / EPUB / TXT / RTF / ODT / EML / MSG now regroup oversized parse output before indexing
    • structured/noisy carriers such as HTML / MHTML / XML / XLSX / PPTX / ZIP are skipped before they can drag builds into long vector-write stalls
  • Extension builds now leave a durable per-file issue report:
    • regrouped oversized text carriers
    • structured oversized skips
    • parse/runtime/I/O failures
  • Activity feedback is more honest without becoming noisy:
    • the desktop shell reports grouped summaries
    • the file-level reasons go into a dedicated issue log instead of flooding the activity area
  • The practical Tika at 92% stall class is narrowed significantly:
    • oversized structured pages now exit before write_vector
    • oversize text carriers are retained through regrouping instead of being silently thrown away

Release Assets

v0.4.5 ships the same three public release assets:

  • OmniClipRAG-v0.4.5-win64.zip
    • desktop GUI package
  • OmniClipRAG-MCP-v0.4.5-win64.zip
    • manual MCP package for direct stdio setup
  • omniclip-rag-mcp-win-x64-v0.4.5.mcpb
    • MCPB package for the official MCP Registry line

MCP / Registry Note

This release does not add new MCP tools or widen the MCP surface.

What changes is release alignment:

  • Registry metadata is refreshed to v0.4.5
  • the .mcpb asset is rebuilt from the same tagged source
  • the MCP ZIP, GUI ZIP, and Registry-facing metadata stay on the same release line

Notes

  • This release intentionally does not optimize or replace the underlying parsers.
  • It also does not redesign extension query semantics, resume semantics, or index-state contracts.
  • The goal is narrower and safer: keep valid large text carriers searchable, keep structured noise out of the indexes, and make the reasons auditable after every build.