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

Merge Latest Frontier (#1991)

Browse Source 
* logging sys to loguru: stage 1 complete

* import loguru: stage 2

* logging -> loguru: stage 3

* support o1-preview and o1-mini

* logging -> loguru stage 4

* update social helper

* logging -> loguru: final stage

* fix: console output

* update translation matrix

* fix: loguru argument error with proxy enabled (#1977)

* relax llama index version

* remove comment

* Added some modules to support openrouter (#1975)

* Added some modules for supporting openrouter model

Added some modules for supporting openrouter model

* Update config.py

* Update .gitignore

* Update bridge_openrouter.py

* Not changed actually

* Refactor logging in bridge_openrouter.py

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>

* remove logging extra

---------

Co-authored-by: Steven Moder <java20131114@gmail.com>
Co-authored-by: Ren Lifei <2602264455@qq.com>
This commit is contained in:
binary-husky
2024-10-05 17:09:18 +08:00
committed by GitHub
parent 597c320808
commit a01ca93362
91 changed files with 2558 additions and 742 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
crazy_functions/批量总结PDF文档.py
View File

@@ -1,16 +1,18 @@
from loguru import logger
from toolbox import update_ui, promote_file_to_downloadzone, gen_time_str
from toolbox import CatchException, report_exception
from toolbox import write_history_to_file, promote_file_to_downloadzone
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
from .crazy_utils import read_and_clean_pdf_text
from .crazy_utils import input_clipping
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
from crazy_functions.crazy_utils import read_and_clean_pdf_text
from crazy_functions.crazy_utils import input_clipping
def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
file_write_buffer = []
for file_name in file_manifest:
print('begin analysis on:', file_name)
logger.info('begin analysis on:', file_name)
############################## <第 0 步，切割PDF> ##################################
# 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
# 的长度必须小于 2500 个 Token
@@ -38,7 +40,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
last_iteration_result = paper_meta # 初始值是摘要
MAX_WORD_TOTAL = 4096 * 0.7
n_fragment = len(paper_fragments)
if n_fragment >= 20: print('文章极长，不能达到预期效果')
if n_fragment >= 20: logger.warning('文章极长，不能达到预期效果')
for i in range(n_fragment):
NUM_OF_WORD = MAX_WORD_TOTAL // n_fragment
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i]}"