From 3271b93341df7dab3d059d406437152293ec73a3 Mon Sep 17 00:00:00 2001 From: HuangHai <10402852@qq.com> Date: Thu, 10 Jul 2025 13:08:00 +0800 Subject: [PATCH] 'commit' --- dsLightRag/ShiTi/T2_ImageToMd.py | 2 +- dsLightRag/ShiTi/T3_DocxToMd.py | 6 +----- dsLightRag/Util/LightRagUtil.py | 8 +++++++- .../__pycache__/LightRagUtil.cpython-310.pyc | Bin 5489 -> 5302 bytes .../《动能定理》巩固练习_origin.pdf | Bin 326324 -> 326324 bytes 5 files changed, 9 insertions(+), 7 deletions(-) diff --git a/dsLightRag/ShiTi/T2_ImageToMd.py b/dsLightRag/ShiTi/T2_ImageToMd.py index afe6389a..2066762a 100644 --- a/dsLightRag/ShiTi/T2_ImageToMd.py +++ b/dsLightRag/ShiTi/T2_ImageToMd.py @@ -29,5 +29,5 @@ completion = client.chat.completions.create( ocr_text = completion.choices[0].message.content # 二、调用格式化函数处理内容 -format_exam_content(client=client, raw_text=ocr_text, output_path="../output/数学OCR整理后的结果.md") +format_exam_content(raw_text=ocr_text, output_path="../output/数学OCR整理后的结果.md") print("保存成功!") diff --git a/dsLightRag/ShiTi/T3_DocxToMd.py b/dsLightRag/ShiTi/T3_DocxToMd.py index cebddd88..8813d8b7 100644 --- a/dsLightRag/ShiTi/T3_DocxToMd.py +++ b/dsLightRag/ShiTi/T3_DocxToMd.py @@ -90,11 +90,7 @@ async def main(): f.write(content) # 新增:使用大模型整理内容 - format_exam_content( - client=llm_model_func(), - raw_text=content, - output_path=os.path.join(output_dir, "物理Docx整理后的结果.md") - ) + format_exam_content(raw_text=content, output_path=os.path.join(output_dir, "物理Docx整理后的结果.md")) logger.info(f"内容整理完成,保存至: {os.path.join(output_dir, '物理Docx整理后的结果.md')}") diff --git a/dsLightRag/Util/LightRagUtil.py b/dsLightRag/Util/LightRagUtil.py index 4771ae88..5a6de628 100644 --- a/dsLightRag/Util/LightRagUtil.py +++ b/dsLightRag/Util/LightRagUtil.py @@ -8,6 +8,8 @@ from lightrag import LightRAG from lightrag.kg.shared_storage import initialize_pipeline_status from lightrag.llm.openai import openai_complete_if_cache, openai_embed from lightrag.utils import EmbeddingFunc, logger, set_verbose_debug +from openai import OpenAI + from Config.Config import * @@ -181,7 +183,11 @@ def create_vision_model_func(llm_model_func): return vision_model_func -def format_exam_content(client, raw_text, output_path): +def format_exam_content(raw_text, output_path): + client = OpenAI( + api_key=LLM_API_KEY, + base_url=LLM_BASE_URL, + ) """ 将OCR识别的原始试卷内容格式化为标准试题格式 diff --git a/dsLightRag/Util/__pycache__/LightRagUtil.cpython-310.pyc b/dsLightRag/Util/__pycache__/LightRagUtil.cpython-310.pyc index e69b59416966344f374b072349f033d88545123e..5ee61c5fb1ae8ef2af684a38007c6f8334da0c9b 100644 GIT binary patch delta 1766 zcmZWp-ESL35WijDo!4JyJ5J&xOL7haH1B_5FY3wYpxg2ep?ec*vtBvNM1p&!93|7LFIH?y;| zyYttvAIwr%D&-aU-8vsG-?>woAiv*v&ffH^jVe*N!n5AMC51DdyQws4JkJXt2Xlmv z^P)Y}ro6mbMZ2pR>kb60qSImhAn8>V25}6@eS$%HR4yMn^EwV+blF*rY1AM%D`*#}+`juf0f2nblt*hMdw*ZyrS^14uM4T(gC#Cxt$_ znMN<~e7HdrTS3cCFjSMfA}OJQSu|Izc)9-xsWg|;Tq3{F6;RdkNKDNf@@jWOEK{r=C~kT&_+Qq?22$B&EkT z?)r)REq7>O9%C#3m`qUA=VdW}Ov9N(zMda97g5Uy%lY3*Zs5kQ<+&f&O)$6RR{kKd zV*wVO?G*%+}HHElDSyB+2g!W92olMHtc`YC*JQ zQV5T}2cO~!!utqM$4%HN&+?bJHFZl~D^86!fMOD%Kg~>i2ISAhv7wK^65-3E1cy%a ze}panF5V{v`Acb%tVm+KaM(kCAHdYaf!eoT|(y8%KJtzdI zEh@h(k8FMnYOKU0rkvcS8#JeIx{>K+ddjN`NZQGC)Q-k8T;&?qzo0zZ%b;{9XTVo` zYDed}QKggZunjHF^$2zxUc8<8)Y#B_`d9g$c9#(43UnqF#)lc~QS-{A61}lT$hbma zEWjTp&C)FFqhBD%>)zSwuY|N^y>?*Qfp5_P0K#R|Lj(elkTtO%4MZG5Q4l#aJ-Sj2 zwY6-;4e8a6)Li7NAvCE(TN7?NDL@~zNc_3RjG-Ke%h;ahQR zb9mH244j0tcVDDhpVYM1E&o5-j}R$30I+jewyCNXScOqa7-fWR>)Qsa&>}hTP@LQV zo=InC&3$4LGcb1g!|}9bI0Ab^q6J-l^+rO2Rgtzle2$3}gQqtW!*iYG7+%@&ZtQwd z{|;xto;JFMjyty8v@ng*S!_ej@xBl>WX)ixOcaas5+$nVMsbo2xFv*jBYpnDLS75O zM!+j1Fm0#>yxH9qVW*%wbv=6uPbhjGfGLc?phehng$$A+mLbD*dQyEzX?}aeU^!N0 JWmYO4`4?--qw@d& delta 2003 zcmZWqYitx%6rMXfJ3HMM`)DbBNufSih#15`cvxsFMX(PjRq3b<)4kK}lzlXJW+{+u zic(t=Ue+tb2dRZWYA}?91P}@S_b>jMe5)hNYp;W z#XAzjQQFK@zunce6LelfZ2lD)CJ|mKwpNCLVg&)j;}If}FcFW-k6G-xEgm35<@Y=- z6>6xhbEnqcv|nrP>E5x=6oe^3A5?nq-`URr4p(`WI?Ytp#wDJ~M4(^^Bn^ z8U0A}QQNRozQ?;N5JyTq!U}%E+Y@d8RrRHFsg%Kh@`v|z(!lHF4J5?7ud+Q_9B!50L_UW zHZ3!kU34lw=YNF{*CHb!mP(~93@Hwd@{gC)jZA>i!n|ZL{6uPC2SH7G0OlVbD0p9R zORQr6lni?co&wn@fD{IV0Wu&`k$R{^y%$9)7d$9aBK4gShoyov;Gs&DFdz+hhrPC3 z5V1?qz!}fE@UUDMk*9nG?vnHqP; z$H4pW@|PuhaSng|2+nlwlbQ3^HWw{8b24ojS$lJR=b({o+T~uoJah8qgDcbS)yeyJ zPc5*RKBU>k5#;?ZjF}7LGZ%kcpyu-SVBRjajm`D5cey)$8yNS0zA<~VaoW8*Iu{Ep zJ^RZS?l+T9Ls`hd{p>6xSxTUkUUAU%ROB8Z@A56NmFwSwyd-;hau6K}#gUTzy6y1E*efIZks;+ES;srXOxsBK9Jy2jN14yk2`oy2;o)@r$y{bI zZP;+^oM>N;Wpvv%C^WyU4dru4-}84WULtA65j`_cyCociWAy^eCk2&=B8o&26(T;C zABUBQ7$p8Dk|**=@~|9G5@JV3qK>TwRSnPe(6z<3nqt^L9d9a=5flQi7%YQ?BBUHX_+*b-ezpQ&D46EdFySK@}EX#hE66&IX2Nh6cu_ bhDMf_hAzhDKw#!#YGP-Du3~!2FBSs;VE!AS