Skip to content

fix(llm_aided): update prompt #1753

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
myhloli merged 2 commits into from
Feb 24, 2025
+6 −2
Merged

fix(llm_aided): update prompt #1753

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
90a27ec
fix(magic_pdf): correct negative indexing for `end_page_id`
myhloli Feb 24, 2025
9e332f0
fix(llm_aided): update prompt
myhloli Feb 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion magic_pdf/model/doc_analyze_by_custom_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,7 +145,11 @@ def doc_analyze(
table_enable=None,
) -> InferenceResult:

end_page_id = end_page_id if end_page_id is not None else len(dataset) - 1
end_page_id = (
end_page_id
if end_page_id is not None and end_page_id >= 0
else len(dataset) - 1
)

model_manager = ModelSingleton()
custom_model = model_manager.get_model(
Expand Down
2 changes: 1 addition & 1 deletion magic_pdf/post_proc/llm_aided.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,7 @@ def llm_aided_title(pdf_info_dict, title_aided_config):
- 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
- 字典中包含OCR错误识别的标题，你可以通过将其层级标记为 0 来排除它们
- 字典中可能包含被误当成标题的正文，你可以通过将其层级标记为 0 来排除它们

IMPORTANT:
请直接返回优化过的由标题层级组成的字典，格式为{{标题id:标题层级}}，如下：
Expand Down