镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-07 15:06:48 +00:00
比较提交
2 次代码提交
frontier_2
...
frontier_1
| 作者 | SHA1 | 提交日期 | |
|---|---|---|---|
|
19a24523e5 | ||
|
|
76685040af |
51
.github/workflows/build-with-latex-arm.yml
vendored
51
.github/workflows/build-with-latex-arm.yml
vendored
@@ -1,51 +0,0 @@
|
||||
# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
|
||||
name: build-with-latex-arm
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- "master"
|
||||
|
||||
env:
|
||||
REGISTRY: ghcr.io
|
||||
IMAGE_NAME: ${{ github.repository }}_with_latex_arm
|
||||
|
||||
jobs:
|
||||
build-and-push-image:
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
|
||||
steps:
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v3
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Log in to the Container registry
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Extract metadata (tags, labels) for Docker
|
||||
id: meta
|
||||
uses: docker/metadata-action@v4
|
||||
with:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
|
||||
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
push: true
|
||||
platforms: linux/arm64
|
||||
file: docs/GithubAction+NoLocal+Latex
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
@@ -697,6 +697,15 @@ def _merge_pdfs_ng(pdf1_path, pdf2_path, output_path):
|
||||
),
|
||||
0,
|
||||
)
|
||||
if "/Annots" in page1:
|
||||
page1_annot_id = [annot.idnum for annot in page1["/Annots"]]
|
||||
else:
|
||||
page1_annot_id = []
|
||||
|
||||
if "/Annots" in page2:
|
||||
page2_annot_id = [annot.idnum for annot in page2["/Annots"]]
|
||||
else:
|
||||
page2_annot_id = []
|
||||
if "/Annots" in new_page:
|
||||
annotations = new_page["/Annots"]
|
||||
for i, annot in enumerate(annotations):
|
||||
@@ -711,8 +720,7 @@ def _merge_pdfs_ng(pdf1_path, pdf2_path, output_path):
|
||||
if "/S" in action and action["/S"] == "/GoTo":
|
||||
# 内部链接：跳转到文档中的某个页面
|
||||
dest = action.get("/D") # 目标页或目标位置
|
||||
# if dest and annot.idnum in page2_annot_id:
|
||||
if dest in pdf2_reader.named_destinations:
|
||||
if dest and annot.idnum in page2_annot_id:
|
||||
# 获取原始文件中跳转信息，包括跳转页面
|
||||
destination = pdf2_reader.named_destinations[
|
||||
dest
|
||||
@@ -724,39 +732,24 @@ def _merge_pdfs_ng(pdf1_path, pdf2_path, output_path):
|
||||
)
|
||||
# 更新跳转信息，跳转到对应的页面和，指定坐标 (100, 150)，缩放比例为 100%
|
||||
# “/D”:[10,'/XYZ',100,100,0]
|
||||
if destination.dest_array[1] == "/XYZ":
|
||||
annot_obj["/A"].update(
|
||||
{
|
||||
NameObject("/D"): ArrayObject(
|
||||
[
|
||||
NumberObject(page_number),
|
||||
destination.dest_array[1],
|
||||
FloatObject(
|
||||
destination.dest_array[
|
||||
2
|
||||
]
|
||||
+ int(
|
||||
page1.mediaBox.getWidth()
|
||||
)
|
||||
),
|
||||
destination.dest_array[3],
|
||||
destination.dest_array[4],
|
||||
]
|
||||
) # 确保键和值是 PdfObject
|
||||
}
|
||||
)
|
||||
else:
|
||||
annot_obj["/A"].update(
|
||||
{
|
||||
NameObject("/D"): ArrayObject(
|
||||
[
|
||||
NumberObject(page_number),
|
||||
destination.dest_array[1],
|
||||
]
|
||||
) # 确保键和值是 PdfObject
|
||||
}
|
||||
)
|
||||
|
||||
annot_obj["/A"].update(
|
||||
{
|
||||
NameObject("/D"): ArrayObject(
|
||||
[
|
||||
NumberObject(page_number),
|
||||
destination.dest_array[1],
|
||||
FloatObject(
|
||||
destination.dest_array[2]
|
||||
+ int(
|
||||
page1.mediaBox.getWidth()
|
||||
)
|
||||
),
|
||||
destination.dest_array[3],
|
||||
destination.dest_array[4],
|
||||
]
|
||||
) # 确保键和值是 PdfObject
|
||||
}
|
||||
)
|
||||
rect = annot_obj.get("/Rect")
|
||||
# 更新点击坐标
|
||||
rect = ArrayObject(
|
||||
@@ -780,9 +773,7 @@ def _merge_pdfs_ng(pdf1_path, pdf2_path, output_path):
|
||||
): rect # 确保键和值是 PdfObject
|
||||
}
|
||||
)
|
||||
# if dest and annot.idnum in page1_annot_id:
|
||||
if dest in pdf1_reader.named_destinations:
|
||||
|
||||
if dest and annot.idnum in page1_annot_id:
|
||||
# 获取原始文件中跳转信息，包括跳转页面
|
||||
destination = pdf1_reader.named_destinations[
|
||||
dest
|
||||
@@ -794,36 +785,21 @@ def _merge_pdfs_ng(pdf1_path, pdf2_path, output_path):
|
||||
)
|
||||
# 更新跳转信息，跳转到对应的页面和，指定坐标 (100, 150)，缩放比例为 100%
|
||||
# “/D”:[10,'/XYZ',100,100,0]
|
||||
if destination.dest_array[1] == "/XYZ":
|
||||
annot_obj["/A"].update(
|
||||
{
|
||||
NameObject("/D"): ArrayObject(
|
||||
[
|
||||
NumberObject(page_number),
|
||||
destination.dest_array[1],
|
||||
FloatObject(
|
||||
destination.dest_array[
|
||||
2
|
||||
]
|
||||
),
|
||||
destination.dest_array[3],
|
||||
destination.dest_array[4],
|
||||
]
|
||||
) # 确保键和值是 PdfObject
|
||||
}
|
||||
)
|
||||
else:
|
||||
annot_obj["/A"].update(
|
||||
{
|
||||
NameObject("/D"): ArrayObject(
|
||||
[
|
||||
NumberObject(page_number),
|
||||
destination.dest_array[1],
|
||||
]
|
||||
) # 确保键和值是 PdfObject
|
||||
}
|
||||
)
|
||||
|
||||
annot_obj["/A"].update(
|
||||
{
|
||||
NameObject("/D"): ArrayObject(
|
||||
[
|
||||
NumberObject(page_number),
|
||||
destination.dest_array[1],
|
||||
FloatObject(
|
||||
destination.dest_array[2]
|
||||
),
|
||||
destination.dest_array[3],
|
||||
destination.dest_array[4],
|
||||
]
|
||||
) # 确保键和值是 PdfObject
|
||||
}
|
||||
)
|
||||
rect = annot_obj.get("/Rect")
|
||||
rect = ArrayObject(
|
||||
[
|
||||
@@ -844,12 +820,14 @@ def _merge_pdfs_ng(pdf1_path, pdf2_path, output_path):
|
||||
elif "/S" in action and action["/S"] == "/URI":
|
||||
# 外部链接：跳转到某个URI
|
||||
uri = action.get("/URI")
|
||||
|
||||
output_writer.addPage(new_page)
|
||||
# Save the merged PDF file
|
||||
with open(output_path, "wb") as output_file:
|
||||
output_writer.write(output_file)
|
||||
|
||||
|
||||
|
||||
def _merge_pdfs_legacy(pdf1_path, pdf2_path, output_path):
|
||||
import PyPDF2 # PyPDF2这个库有严重的内存泄露问题，把它放到子进程中运行，从而方便内存的释放
|
||||
|
||||
|
||||
@@ -3,19 +3,33 @@
|
||||
# - 2 构建 docker build -t gpt-academic-nolocal-latex -f docs/GithubAction+NoLocal+Latex .
|
||||
# - 3 运行 docker run -v /home/fuqingxu/arxiv_cache:/root/arxiv_cache --rm -it --net=host gpt-academic-nolocal-latex
|
||||
|
||||
FROM menghuan1918/ubuntu_uv_ctex:latest
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
SHELL ["/bin/bash", "-c"]
|
||||
FROM fuqingxu/python311_texlive_ctex:latest
|
||||
ENV PATH "$PATH:/usr/local/texlive/2022/bin/x86_64-linux"
|
||||
ENV PATH "$PATH:/usr/local/texlive/2023/bin/x86_64-linux"
|
||||
ENV PATH "$PATH:/usr/local/texlive/2024/bin/x86_64-linux"
|
||||
ENV PATH "$PATH:/usr/local/texlive/2025/bin/x86_64-linux"
|
||||
ENV PATH "$PATH:/usr/local/texlive/2026/bin/x86_64-linux"
|
||||
|
||||
# 指定路径
|
||||
WORKDIR /gpt
|
||||
|
||||
RUN pip3 install openai numpy arxiv rich
|
||||
RUN pip3 install colorama Markdown pygments pymupdf
|
||||
RUN pip3 install python-docx pdfminer
|
||||
RUN pip3 install nougat-ocr
|
||||
|
||||
# 装载项目文件
|
||||
COPY . .
|
||||
RUN /root/.cargo/bin/uv venv --seed \
|
||||
&& source .venv/bin/activate \
|
||||
&& /root/.cargo/bin/uv pip install openai numpy arxiv rich colorama Markdown pygments pymupdf python-docx pdfminer \
|
||||
&& /root/.cargo/bin/uv pip install -r requirements.txt \
|
||||
&& /root/.cargo/bin/uv clean
|
||||
|
||||
|
||||
# 安装依赖
|
||||
RUN pip3 install -r requirements.txt
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 可选步骤，用于预热模块
|
||||
RUN .venv/bin/python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
# 启动
|
||||
CMD [".venv/bin/python3", "-u", "main.py"]
|
||||
CMD ["python3", "-u", "main.py"]
|
||||
|
||||
@@ -256,8 +256,6 @@ model_info = {
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
"openai_disable_system_prompt": True,
|
||||
"openai_disable_stream": True,
|
||||
},
|
||||
"o1-mini": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
@@ -266,8 +264,6 @@ model_info = {
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
"openai_disable_system_prompt": True,
|
||||
"openai_disable_stream": True,
|
||||
},
|
||||
|
||||
"gpt-4-turbo": {
|
||||
|
||||
在新工单中引用
屏蔽一个用户