Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
MinerU
Commits
48a43370
Unverified
Commit
48a43370
authored
Jan 17, 2025
by
Xiaomeng Zhao
Committed by
GitHub
Jan 17, 2025
Browse files
Merge pull request #1571 from myhloli/dev
feat(llm_aided): add reasonability check and fine-tuning guidelines
parents
b894b780
d986e393
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
0 deletions
+5
-0
magic_pdf/post_proc/llm_aided.py
magic_pdf/post_proc/llm_aided.py
+5
-0
No files found.
magic_pdf/post_proc/llm_aided.py
View file @
48a43370
...
@@ -115,6 +115,11 @@ def llm_aided_title(pdf_info_dict, title_aided_config):
...
@@ -115,6 +115,11 @@ def llm_aided_title(pdf_info_dict, title_aided_config):
- 标题层级最多为4级,不要添加过多的层级
- 标题层级最多为4级,不要添加过多的层级
- 优化后的标题只保留代表该标题的层级的整数,不要保留其他信息
- 优化后的标题只保留代表该标题的层级的整数,不要保留其他信息
5. 合理性检查与微调:
- 在完成初步分级后,仔细检查分级结果的合理性
- 根据上下文关系和逻辑顺序,对不合理的分级进行微调
- 确保最终的分级结果符合文档的实际结构和逻辑
IMPORTANT:
IMPORTANT:
请直接返回优化过的由标题层级组成的json,格式如下:
请直接返回优化过的由标题层级组成的json,格式如下:
{{"0":1,"1":2,"2":2,"3":3}}
{{"0":1,"1":2,"2":2,"3":3}}
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment