CC/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

improve long text breakdown perfomance

Browse Source
This commit is contained in:
binary-husky
2023-12-19 19:30:44 +08:00
parent 6e9936531d
commit a0bfa7ba1c
13 changed files with 186 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
crazy_functions/批量总结PDF文档.py
View File

@@ -20,14 +20,9 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
TOKEN_LIMIT_PER_FRAGMENT = 2500
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
from request_llms.bridge_all import model_info
enc = model_info["gpt-3.5-turbo"]['tokenizer']
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]