Skip to content

GitLab

Unverified Commit 84f84d26 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1693 from shniubobo/feat/web_api 

Update web_api
parents e9203f91 d9406e5b
Hide whitespace changes
Inline Side-by-side
Showing with 398 additions and 240 deletions
projects/web_api/Dockerfile
View file @ 84f84d26
# Use the official Ubuntu base image FROM python:3.10-slim-bookworm AS base
FROM ubuntu:latest
# ENV http_proxy http://127.0.0.1:7890 WORKDIR /app
# ENV https_proxy http://127.0.0.1:7890
# Set environment variables to non-interactive to avoid prompts during installation ENV DEBIAN_FRONTEND=noninteractive \
ENV DEBIAN_FRONTEND=noninteractive LANG=C.UTF-8 \
ENV LANG C.UTF-8 PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
# ADD sources.list /etc/apt PIP_DISABLE_PIP_VERSION_CHECK=1 \
# RUN apt-get clean PIP_NO_CACHE_DIR=1
FROM base AS build
# Update the package list and install necessary packages # Update the package list and install necessary packages
RUN apt-get -q update \
&& apt-get -q install -y --no-install-recommends \
apt-utils \
bats \
build-essential
RUN apt-get update && apt-get install -y vim net-tools procps lsof curl wget iputils-ping telnet lrzsz git
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y \ apt-get install -y --no-install-recommends \
software-properties-common && \ build-essential && \
add-apt-repository ppa:deadsnakes/ppa && \ apt-get clean && \
apt-get update && \ rm -rf /var/lib/apt/lists/*
apt-get install -y \
python3.10 \
python3.10-venv \
python3.10-distutils \
python3-pip \
wget \
git \
libgl1 \
libglib2.0-0 \
&& rm -rf /var/lib/apt/lists/*
# RUN unset http_proxy && unset https_proxy
# Set Python 3.10 as the default python3
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
# Create a virtual environment for MinerU
RUN python3 -m venv /opt/mineru_venv
RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple
# Activate the virtual environment and install necessary Python packages
RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
pip install --upgrade pip && \
pip install magic-pdf[full] --extra-index-url https://myhloli.github.io/wheels/ --no-cache-dir"
# Build Python dependencies
COPY requirements.txt .
RUN python -m venv /app/venv && \
. /app/venv/bin/activate && \
pip install -r requirements.txt && \
pip uninstall -y paddlepaddle && \
pip install -i https://www.paddlepaddle.org.cn/packages/stable/cu118/ \
paddlepaddle-gpu==3.0.0rc1
RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \ # Download models
pip install fastapi uvicorn python-multipart --no-cache-dir" COPY download_models.py .
RUN . /app/venv/bin/activate && \
./download_models.py
RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
pip uninstall paddlepaddle -y"
RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \ FROM base AS prod
python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/ --no-cache-dir"
# Copy the configuration file template and set up the model directory # Copy Python dependencies and models from the build stage
COPY magic-pdf.template.json /root/magic-pdf.json COPY --from=build /app/venv /app/venv
ADD models /opt/models COPY --from=build /opt/models /opt/models
ADD .paddleocr /root/.paddleocr COPY --from=build /opt/layoutreader /opt/layoutreader
ADD app.py /root/app.py
WORKDIR /root # Update the package list and install necessary packages
RUN apt-get update && \
# Set the models directory in the configuration file (adjust the path as needed) apt-get install -y --no-install-recommends \
RUN sed -i 's|/tmp/models|/opt/models|g' /root/magic-pdf.json libgl1 \
libglib2.0-0 \
# Create the models directory libgomp1 && \
# RUN mkdir -p /opt/models apt-get clean && \
rm -rf /var/lib/apt/lists/*
# Set the entry point to activate the virtual environment and run the command line tool # Create volume for paddleocr models
# ENTRYPOINT ["/bin/bash", "-c", "source /opt/mineru_venv/bin/activate && exec \"$@\" && python3 app.py", "--"] RUN mkdir -p /root/.paddleocr
VOLUME [ "/root/.paddleocr" ]
# Copy the app and its configuration file
COPY entrypoint.sh /app/entrypoint.sh
COPY magic-pdf.json /root/magic-pdf.json
COPY app.py /app/app.py
# Expose the port that FastAPI will run on # Expose the port that FastAPI will run on
EXPOSE 8000 EXPOSE 8000
# Command to run FastAPI using Uvicorn, pointing to app.py and binding to 0.0.0.0:8000 # Command to run FastAPI using Uvicorn, pointing to app.py and binding to 0.0.0.0:8000
CMD ["/bin/bash", "-c", "source /opt/mineru_venv/bin/activate && uvicorn app:app --host 0.0.0.0 --port 8000"] ENTRYPOINT [ "/app/entrypoint.sh" ]
\ No newline at end of file CMD ["--host", "0.0.0.0", "--port", "8000"]
projects/web_api/README.md
View file @ 84f84d26
基于MinerU的PDF解析API # 基于MinerU的PDF解析API
- MinerU的GPU镜像构建 - MinerU的GPU镜像构建
- 基于FastAPI的PDF解析接口 - 基于FastAPI的PDF解析接口
支持一键启动，已经打包到镜像中，自带模型权重，支持GPU推理加速，GPU速度相比CPU每页解析要快几十倍不等 ## 构建方式
```
docker build -t mineru-api .
```
## 启动命令： 或者使用代理：
```
docker build --build-arg http_proxy=http://127.0.0.1:7890 --build-arg https_proxy=http://127.0.0.1:7890 -t mineru-api .
```
```docker run -itd --name=mineru_server --gpus=all -p 8888:8000 quincyqiang/mineru:0.1-models``` ## 启动命令
![](https://i-blog.csdnimg.cn/direct/bcff4f524ea5400db14421ba7cec4989.png) ```
docker run --rm -it --gpus=all -v ./paddleocr:/root/.paddleocr -p 8000:8000 mineru-api
```
具体截图请见博客：https://blog.csdn.net/yanqianglifei/article/details/141979684 初次调用 API 时会自动下载 paddleocr 的模型（约数十 MB），其余模型已包含在镜像中。
## 测试参数
## 启动日志： 访问地址：
![](https://i-blog.csdnimg.cn/direct/4eb5657567e4415eba912179dca5c8aa.png) ```
http://localhost:8000/docs
http://127.0.0.1:8000/docs
```
## 输入参数： ## 旧版镜像地址
访问地址： > 阿里云地址：docker pull registry.cn-beijing.aliyuncs.com/quincyqiang/mineru:0.1-models
>
> dockerhub地址：docker pull quincyqiang/mineru:0.1-models
http://localhost:8888/docs
http://127.0.01:8888/docs ## 旧版截图
![](https://i-blog.csdnimg.cn/direct/8b3a2bc5908042268e8cc69756e331a2.png) ### 启动命令
## 解析效果： ![](https://i-blog.csdnimg.cn/direct/bcff4f524ea5400db14421ba7cec4989.png)
![](https://i-blog.csdnimg.cn/direct/a54dcae834ae48d498fb595aca4212c3.png) 具体截图请见博客：https://blog.csdn.net/yanqianglifei/article/details/141979684
### 启动日志
![](https://i-blog.csdnimg.cn/direct/4eb5657567e4415eba912179dca5c8aa.png)
## 镜像地址： ### 测试参数
> 阿里云地址：docker pull registry.cn-beijing.aliyuncs.com/quincyqiang/mineru:0.1-models ![](https://i-blog.csdnimg.cn/direct/8b3a2bc5908042268e8cc69756e331a2.png)
> dockerhub地址：docker pull quincyqiang/mineru:0.1-models ### 解析效果
![](https://i-blog.csdnimg.cn/direct/a54dcae834ae48d498fb595aca4212c3.png)
projects/web_api/app.py
View file @ 84f84d26
import copy
import json import json
import os import os
from tempfile import NamedTemporaryFile from base64 import b64encode
from glob import glob
from io import StringIO
from typing import Tuple, Union
import uvicorn import uvicorn
from fastapi import FastAPI, File, UploadFile from fastapi import FastAPI, HTTPException, UploadFile
from fastapi.responses import JSONResponse from fastapi.responses import JSONResponse
from loguru import logger from loguru import logger
import magic_pdf.model as model_config import magic_pdf.model as model_config
from magic_pdf.config.enums import SupportedPdfParseMethod from magic_pdf.config.enums import SupportedPdfParseMethod
from magic_pdf.data.data_reader_writer import FileBasedDataWriter from magic_pdf.data.data_reader_writer import DataWriter, FileBasedDataWriter
from magic_pdf.data.data_reader_writer.s3 import S3DataReader, S3DataWriter
from magic_pdf.data.dataset import PymuDocDataset from magic_pdf.data.dataset import PymuDocDataset
from magic_pdf.libs.config_reader import get_bucket_name, get_s3_config
from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
from magic_pdf.operators.models import InferenceResult from magic_pdf.operators.models import InferenceResult
from magic_pdf.operators.pipes import PipeResult
model_config.__use_inside_model__ = True model_config.__use_inside_model__ = True
app = FastAPI() app = FastAPI()
def json_md_dump( class MemoryDataWriter(DataWriter):
model_json, def __init__(self):
middle_json, self.buffer = StringIO()
md_writer,
pdf_name, def write(self, path: str, data: bytes) -> None:
content_list, if isinstance(data, str):
md_content, self.buffer.write(data)
): else:
# Write model results to model.json self.buffer.write(data.decode("utf-8"))
orig_model_list = copy.deepcopy(model_json)
md_writer.write_string( def write_string(self, path: str, data: str) -> None:
f'{pdf_name}_model.json', self.buffer.write(data)
json.dumps(orig_model_list, ensure_ascii=False, indent=4),
) def get_value(self) -> str:
return self.buffer.getvalue()
# Write intermediate results to middle.json
md_writer.write_string( def close(self):
f'{pdf_name}_middle.json', self.buffer.close()
json.dumps(middle_json, ensure_ascii=False, indent=4),
)
def init_writers(
# Write text content results to content_list.json pdf_path: str = None,
md_writer.write_string( pdf_file: UploadFile = None,
f'{pdf_name}_content_list.json', output_path: str = None,
json.dumps(content_list, ensure_ascii=False, indent=4), output_image_path: str = None,
) ) -> Tuple[
Union[S3DataWriter, FileBasedDataWriter],
# Write results to .md file Union[S3DataWriter, FileBasedDataWriter],
md_writer.write_string( bytes,
f'{pdf_name}.md', ]:
md_content,
)
@app.post('/pdf_parse', tags=['projects'], summary='Parse PDF file')
async def pdf_parse_main(
pdf_file: UploadFile = File(...),
parse_method: str = 'auto',
model_json_path: str = None,
is_json_md_dump: bool = True,
output_dir: str = 'output',
):
"""Execute the process of converting PDF to JSON and MD, outputting MD and
JSON files to the specified directory.
:param pdf_file: The PDF file to be parsed
:param parse_method: Parsing method, can be auto, ocr, or txt. Default is auto. If results are not satisfactory, try ocr
:param model_json_path: Path to existing model data file. If empty, use built-in model. PDF and model_json must correspond
:param is_json_md_dump: Whether to write parsed data to .json and .md files. Default is True. Different stages of data will be written to different .json files (3 in total), md content will be saved to .md file # noqa E501
:param output_dir: Output directory for results. A folder named after the PDF file will be created to store all results
""" """
try: Initialize writers based on path type
# Create a temporary file to store the uploaded PDF
with NamedTemporaryFile(delete=False, suffix='.pdf') as temp_pdf:
temp_pdf.write(await pdf_file.read())
temp_pdf_path = temp_pdf.name
pdf_name = os.path.basename(pdf_file.filename).split('.')[0] Args:
pdf_path: PDF file path (local path or S3 path)
pdf_file: Uploaded PDF file object
output_path: Output directory path
output_image_path: Image output directory path
if output_dir: Returns:
output_path = os.path.join(output_dir, pdf_name) Tuple[writer, image_writer, pdf_bytes]: Returns initialized writer tuple and PDF
file content
"""
if pdf_path:
is_s3_path = pdf_path.startswith("s3://")
if is_s3_path:
bucket = get_bucket_name(pdf_path)
ak, sk, endpoint = get_s3_config(bucket)
writer = S3DataWriter(
output_path, bucket=bucket, ak=ak, sk=sk, endpoint_url=endpoint
)
image_writer = S3DataWriter(
output_image_path, bucket=bucket, ak=ak, sk=sk, endpoint_url=endpoint
)
# 临时创建reader读取文件内容
temp_reader = S3DataReader(
"", bucket=bucket, ak=ak, sk=sk, endpoint_url=endpoint
)
pdf_bytes = temp_reader.read(pdf_path)
else: else:
output_path = os.path.join(os.path.dirname(temp_pdf_path), pdf_name) writer = FileBasedDataWriter(output_path)
image_writer = FileBasedDataWriter(output_image_path)
os.makedirs(output_image_path, exist_ok=True)
with open(pdf_path, "rb") as f:
pdf_bytes = f.read()
else:
# 处理上传的文件
pdf_bytes = pdf_file.file.read()
writer = FileBasedDataWriter(output_path)
image_writer = FileBasedDataWriter(output_image_path)
os.makedirs(output_image_path, exist_ok=True)
output_image_path = os.path.join(output_path, 'images') return writer, image_writer, pdf_bytes
# Get parent path of images for relative path in .md and content_list.json
image_path_parent = os.path.basename(output_image_path)
pdf_bytes = open(temp_pdf_path, 'rb').read() # Read binary data of PDF file def process_pdf(
pdf_bytes: bytes,
parse_method: str,
image_writer: Union[S3DataWriter, FileBasedDataWriter],
) -> Tuple[InferenceResult, PipeResult]:
"""
Process PDF file content
Args:
pdf_bytes: Binary content of PDF file
parse_method: Parse method ('ocr', 'txt', 'auto')
image_writer: Image writer
if model_json_path: Returns:
# Read original JSON data of PDF file parsed by model, list type Tuple[InferenceResult, PipeResult]: Returns inference result and pipeline result
model_json = json.loads(open(model_json_path, 'r', encoding='utf-8').read()) """
ds = PymuDocDataset(pdf_bytes)
infer_result: InferenceResult = None
pipe_result: PipeResult = None
if parse_method == "ocr":
infer_result = ds.apply(doc_analyze, ocr=True)
pipe_result = infer_result.pipe_ocr_mode(image_writer)
elif parse_method == "txt":
infer_result = ds.apply(doc_analyze, ocr=False)
pipe_result = infer_result.pipe_txt_mode(image_writer)
else: # auto
if ds.classify() == SupportedPdfParseMethod.OCR:
infer_result = ds.apply(doc_analyze, ocr=True)
pipe_result = infer_result.pipe_ocr_mode(image_writer)
else: else:
model_json = [] infer_result = ds.apply(doc_analyze, ocr=False)
pipe_result = infer_result.pipe_txt_mode(image_writer)
# Execute parsing steps
image_writer, md_writer = FileBasedDataWriter( return infer_result, pipe_result
output_image_path
), FileBasedDataWriter(output_path)
def encode_image(image_path: str) -> str:
ds = PymuDocDataset(pdf_bytes) """Encode image using base64"""
# Choose parsing method with open(image_path, "rb") as f:
if parse_method == 'auto': return b64encode(f.read()).decode()
if ds.classify() == SupportedPdfParseMethod.OCR:
parse_method = 'ocr'
else: @app.post(
parse_method = 'txt' "/pdf_parse",
tags=["projects"],
if parse_method not in ['txt', 'ocr']: summary="Parse PDF files (supports local files and S3)",
logger.error('Unknown parse method, only auto, ocr, txt allowed') )
async def pdf_parse(
pdf_file: UploadFile = None,
pdf_path: str = None,
parse_method: str = "auto",
is_json_md_dump: bool = False,
output_dir: str = "output",
return_layout: bool = False,
return_info: bool = False,
return_content_list: bool = False,
return_images: bool = False,
):
"""
Execute the process of converting PDF to JSON and MD, outputting MD and JSON files
to the specified directory.
Args:
pdf_file: The PDF file to be parsed. Must not be specified together with
`pdf_path`
pdf_path: The path to the PDF file to be parsed. Must not be specified together
with `pdf_file`
parse_method: Parsing method, can be auto, ocr, or txt. Default is auto. If
results are not satisfactory, try ocr
is_json_md_dump: Whether to write parsed data to .json and .md files. Default
to False. Different stages of data will be written to different .json files
(3 in total), md content will be saved to .md file
output_dir: Output directory for results. A folder named after the PDF file
will be created to store all results
return_layout: Whether to return parsed PDF layout. Default to False
return_info: Whether to return parsed PDF info. Default to False
return_content_list: Whether to return parsed PDF content list. Default to False
"""
try:
if (pdf_file is None and pdf_path is None) or (
pdf_file is not None and pdf_path is not None
):
return JSONResponse( return JSONResponse(
content={'error': 'Invalid parse method'}, status_code=400 content={"error": "Must provide either pdf_file or pdf_path"},
status_code=400,
) )
if len(model_json) == 0: # Get PDF filename
if parse_method == 'ocr': pdf_name = os.path.basename(pdf_path if pdf_path else pdf_file.filename).split(
infer_result = ds.apply(doc_analyze, ocr=True) "."
else: )[0]
infer_result = ds.apply(doc_analyze, ocr=False) output_path = f"{output_dir}/{pdf_name}"
output_image_path = f"{output_path}/images"
else: # Initialize readers/writers and get PDF content
infer_result = InferenceResult(model_json, ds) writer, image_writer, pdf_bytes = init_writers(
pdf_path=pdf_path,
if len(model_json) == 0 and not model_config.__use_inside_model__: pdf_file=pdf_file,
logger.error('Need model list input') output_path=output_path,
return JSONResponse( output_image_path=output_image_path,
content={'error': 'Model list input required'}, status_code=400 )
)
if parse_method == 'ocr': # Process PDF
pipe_res = infer_result.pipe_ocr_mode(image_writer) infer_result, pipe_result = process_pdf(pdf_bytes, parse_method, image_writer)
else:
pipe_res = infer_result.pipe_txt_mode(image_writer) # Use MemoryDataWriter to get results
content_list_writer = MemoryDataWriter()
md_content_writer = MemoryDataWriter()
middle_json_writer = MemoryDataWriter()
# Use PipeResult's dump method to get data
pipe_result.dump_content_list(content_list_writer, "", "images")
pipe_result.dump_md(md_content_writer, "", "images")
pipe_result.dump_middle_json(middle_json_writer, "")
# Save results in text and md format # Get content
content_list = pipe_res.get_content_list(image_path_parent, drop_mode='none') content_list = json.loads(content_list_writer.get_value())
md_content = pipe_res.get_markdown(image_path_parent, drop_mode='none') md_content = md_content_writer.get_value()
middle_json = json.loads(middle_json_writer.get_value())
model_json = infer_result.get_infer_res()
# If results need to be saved
if is_json_md_dump: if is_json_md_dump:
json_md_dump(infer_result._infer_res, pipe_res._pipe_res, md_writer, pdf_name, content_list, md_content) writer.write_string(
data = { f"{pdf_name}_content_list.json", content_list_writer.get_value()
'layout': copy.deepcopy(infer_result._infer_res), )
'info': pipe_res._pipe_res, writer.write_string(f"{pdf_name}.md", md_content)
'content_list': content_list, writer.write_string(
'md_content': md_content, f"{pdf_name}_middle.json", middle_json_writer.get_value()
} )
writer.write_string(
f"{pdf_name}_model.json",
json.dumps(model_json, indent=4, ensure_ascii=False),
)
# Save visualization results
pipe_result.draw_layout(os.path.join(output_path, f"{pdf_name}_layout.pdf"))
pipe_result.draw_span(os.path.join(output_path, f"{pdf_name}_spans.pdf"))
pipe_result.draw_line_sort(
os.path.join(output_path, f"{pdf_name}_line_sort.pdf")
)
infer_result.draw_model(os.path.join(output_path, f"{pdf_name}_model.pdf"))
# Build return data
data = {}
if return_layout:
data["layout"] = model_json
if return_info:
data["info"] = middle_json
if return_content_list:
data["content_list"] = content_list
if return_images:
image_paths = glob(f"{output_image_path}/*.jpg")
data["images"] = {
os.path.basename(
image_path
): f"data:image/jpeg;base64,{encode_image(image_path)}"
for image_path in image_paths
}
data["md_content"] = md_content # md_content is always returned
# Clean up memory writers
content_list_writer.close()
md_content_writer.close()
middle_json_writer.close()
return JSONResponse(data, status_code=200) return JSONResponse(data, status_code=200)
except Exception as e: except Exception as e:
logger.exception(e) logger.exception(e)
return JSONResponse(content={'error': str(e)}, status_code=500) return JSONResponse(content={"error": str(e)}, status_code=500)
finally:
# Clean up the temporary file
if 'temp_pdf_path' in locals():
os.unlink(temp_pdf_path)
if __name__ == '__main__': if __name__ == "__main__":
uvicorn.run(app, host='0.0.0.0', port=8888) uvicorn.run(app, host="0.0.0.0", port=8888)
projects/web_api/download_models.py 0 → 100755
View file @ 84f84d26
#!/usr/bin/env python
from huggingface_hub import snapshot_download
if __name__ == "__main__":
mineru_patterns = [
"models/Layout/LayoutLMv3/*",
"models/Layout/YOLO/*",
"models/MFD/YOLO/*",
"models/MFR/unimernet_small_2501/*",
"models/TabRec/TableMaster/*",
"models/TabRec/StructEqTable/*",
]
model_dir = snapshot_download(
"opendatalab/PDF-Extract-Kit-1.0",
allow_patterns=mineru_patterns,
local_dir="/opt/",
)
layoutreader_pattern = [
"*.json",
"*.safetensors",
]
layoutreader_model_dir = snapshot_download(
"hantian/layoutreader",
allow_patterns=layoutreader_pattern,
local_dir="/opt/layoutreader/",
)
model_dir = model_dir + "/models"
print(f"model_dir is: {model_dir}")
print(f"layoutreader_model_dir is: {layoutreader_model_dir}")
projects/web_api/entrypoint.sh 0 → 100755
View file @ 84f84d26
#!/usr/bin/env bash
set -euo pipefail
. /app/venv/bin/activate
exec uvicorn app:app "$@"
projects/web_api/magic-pdf.json
View file @ 84f84d26
...@@ -4,10 +4,41 @@ ...@@ -4,10 +4,41 @@
"bucket-name-2":["ak", "sk", "endpoint"] "bucket-name-2":["ak", "sk", "endpoint"]
}, },
"models-dir":"/opt/models", "models-dir":"/opt/models",
"layoutreader-model-dir":"/opt/layoutreader",
"device-mode":"cuda", "device-mode":"cuda",
"layout-config": {
"model": "doclayout_yolo"
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true
},
"table-config": { "table-config": {
"model": "TableMaster", "model": "rapid_table",
"is_table_recog_enable": false, "sub_model": "slanet_plus",
"enable": true,
"max_time": 400 "max_time": 400
} },
"llm-aided-config": {
"formula_aided": {
"api_key": "your_api_key",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"model": "qwen2.5-7b-instruct",
"enable": false
},
"text_aided": {
"api_key": "your_api_key",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"model": "qwen2.5-7b-instruct",
"enable": false
},
"title_aided": {
"api_key": "your_api_key",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"model": "qwen2.5-32b-instruct",
"enable": false
}
},
"config_version": "1.1.1"
} }
projects/web_api/magic-pdf.template.json deleted 100644 → 0
View file @ e9203f91
{
"bucket_info":{
"bucket-name-1":["ak", "sk", "endpoint"],
"bucket-name-2":["ak", "sk", "endpoint"]
},
"models-dir":"/tmp/models",
"device-mode":"cuda",
"table-config": {
"model": "TableMaster",
"is_table_recog_enable": false,
"max_time": 400
}
}
\ No newline at end of file
projects/web_api/requirements.txt
View file @ 84f84d26
--extra-index-url https://myhloli.github.io/wheels/
magic-pdf[full]
fastapi
uvicorn
python-multipart
projects/web_api/sources.list deleted 100644 → 0
View file @ e9203f91
deb http://mirrors.aliyun.com/ubuntu/ focal main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-security main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-security main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-updates main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-updates main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-proposed main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-proposed main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-backports main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-backports main restricted universe multiverse
\ No newline at end of file
projects/web_api/start_mineru.sh deleted 100644 → 0
View file @ e9203f91
docker run -itd --name=mineru_server --gpus=all -p 8888:8000 quincyqiang/mineru:0.1-models /bin/bash
docker run -itd --name=mineru_server --gpus=all -p 8888:8000 quincyqiang/mineru:0.3-models
docker login --username=1185918903@qq.com registry.cn-beijing.aliyuncs.com
docker tag quincyqiang/mineru:0.3-models registry.cn-beijing.aliyuncs.com/quincyqiang/gomate:0.3-models
docker push registry.cn-beijing.aliyuncs.com/quincyqiang/gomate:0.3-models
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment