mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-07-09 05:12:12 +02:00
fix jtd, remove temp files - final translation push
Signed-off-by: Alex Jenkins <kjenkins60@gatech.edu>
This commit is contained in:
parent
bfabe742d2
commit
62290d793c
543 changed files with 4399 additions and 1373 deletions
|
|
@ -1,5 +1,13 @@
|
|||
---
|
||||
layout: default
|
||||
title: "通用文档解码器"
|
||||
parent: "Chinese (Beta)"
|
||||
---
|
||||
|
||||
# 通用文档解码器
|
||||
|
||||
> **Beta Translation:** This document was translated via Machine Learning and as such may not be 100% accurate. All non-English languages are currently classified as Beta.
|
||||
|
||||
## 概述
|
||||
|
||||
一个由 `unstructured` 驱动的通用文档解码器,它支持通过单个服务处理各种常见的文档格式。该服务具有完整的溯源功能和库管理员集成,记录源位置作为知识图谱元数据,从而实现端到端的可追溯性。
|
||||
|
|
@ -286,4 +294,4 @@ Document → [通用解码器] → TextDocument → [分块器] → Chunk → ..
|
|||
- 某些格式可能导致文本提取效果不佳(扫描的 PDF 文件缺少 OCR,复杂的 XLSX 布局)。
|
||||
缓解措施:配置 `strategy` 参数,并且现有的 Mistral OCR 解码器仍然可用于高质量的 PDF OCR。
|
||||
- `unstructured` 版本更新可能会更改元素元数据。
|
||||
缓解措施:固定版本,并为每个格式测试提取质量。
|
||||
缓解措施:固定版本,并为每个格式测试提取质量。
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue