apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-24 23:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix model

Browse source
This commit is contained in:
Ray 2025-08-28 13:07:15 +08:00
parent 6d1b505541
commit 4b4ae4d51d
5 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -123,7 +123,7 @@ python3 run_pageindex.py --pdf_path /path/to/your/document.pdf
You can customize the processing with additional optional arguments:
```
--model OpenAI model to use (default: gpt-4.1)
--model OpenAI model to use (default: gpt-4o-2024-11-20)
--toc-check-pages Pages to check for table of contents (default: 20)
--max-pages-per-node Max pages per node (default: 10)
--max-tokens-per-node Max tokens per node (default: 20000)

2
pageindex/config.yaml
View file

@ -1,4 +1,4 @@
model: "gpt-4.1"
model: "gpt-4o-2024-11-20"
toc_check_page_num: 20
max_page_num_each_node: 10
max_token_num_each_node: 20000

4
pageindex/page_index.py
View file

@ -496,7 +496,7 @@ def remove_first_physical_index_section(text):
return text
### add verify completeness
def generate_toc_continue(toc_content, part, model="gpt-4.1"):
def generate_toc_continue(toc_content, part, model="gpt-4o-2024-11-20"):
print('start generate_toc_continue')
prompt = """
You are an expert in extracting hierarchical tree structure.
@ -729,7 +729,7 @@ def check_toc(page_list, opt=None):
################### fix incorrect toc #########################################################
def single_toc_item_index_fixer(section_title, content, model="gpt-4.1"):
def single_toc_item_index_fixer(section_title, content, model="gpt-4o-2024-11-20"):
tob_extractor_prompt = """
You are given a section title and several pages of a document, your job is to find the physical index of the start page of the section in the partial document.

2
pageindex/utils.py
View file

@ -410,7 +410,7 @@ def add_preface_if_needed(data):
def get_page_tokens(pdf_path, model="gpt-4.1", pdf_parser="PyPDF2"):
def get_page_tokens(pdf_path, model="gpt-4o-2024-11-20", pdf_parser="PyPDF2"):
enc = tiktoken.encoding_for_model(model)
if pdf_parser == "PyPDF2":
pdf_reader = PyPDF2.PdfReader(pdf_path)

2
run_pageindex.py
View file

@ -10,7 +10,7 @@ if __name__ == "__main__":
parser.add_argument('--pdf_path', type=str, help='Path to the PDF file')
parser.add_argument('--md_path', type=str, help='Path to the Markdown file')
parser.add_argument('--model', type=str, default='gpt-4.1', help='Model to use')
parser.add_argument('--model', type=str, default='gpt-4o-2024-11-20', help='Model to use')
parser.add_argument('--toc-check-pages', type=int, default=20,
help='Number of pages to check for table of contents (PDF only)')